@phdthesis{Hesse2022, author = {Hesse, G{\"u}nter}, title = {A benchmark for enterprise stream processing architectures}, doi = {10.25932/publishup-56600}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-566000}, school = {Universit{\"a}t Potsdam}, pages = {ix, 148}, year = {2022}, abstract = {Data stream processing systems (DSPSs) are a key enabler to integrate continuously generated data, such as sensor measurements, into enterprise applications. DSPSs allow to steadily analyze information from data streams, e.g., to monitor manufacturing processes and enable fast reactions to anomalous behavior. Moreover, DSPSs continuously filter, sample, and aggregate incoming streams of data, which reduces the data size, and thus data storage costs. The growing volumes of generated data have increased the demand for high-performance DSPSs, leading to a higher interest in these systems and to the development of new DSPSs. While having more DSPSs is favorable for users as it allows choosing the system that satisfies their requirements the most, it also introduces the challenge of identifying the most suitable DSPS regarding current needs as well as future demands. Having a solution to this challenge is important because replacements of DSPSs require the costly re-writing of applications if no abstraction layer is used for application development. However, quantifying performance differences between DSPSs is a difficult task. Existing benchmarks fail to integrate all core functionalities of DSPSs and lack tool support, which hinders objective result comparisons. Moreover, no current benchmark covers the combination of streaming data with existing structured business data, which is particularly relevant for companies. This thesis proposes a performance benchmark for enterprise stream processing called ESPBench. With enterprise stream processing, we refer to the combination of streaming and structured business data. Our benchmark design represents real-world scenarios and allows for an objective result comparison as well as scaling of data. The defined benchmark query set covers all core functionalities of DSPSs. The benchmark toolkit automates the entire benchmark process and provides important features, such as query result validation and a configurable data ingestion rate. To validate ESPBench and to ease the use of the benchmark, we propose an example implementation of the ESPBench queries leveraging the Apache Beam software development kit (SDK). The Apache Beam SDK is an abstraction layer designed for developing stream processing applications that is applied in academia as well as enterprise contexts. It allows to run the defined applications on any of the supported DSPSs. The performance impact of Apache Beam is studied in this dissertation as well. The results show that there is a significant influence that differs among DSPSs and stream processing applications. For validating ESPBench, we use the example implementation of the ESPBench queries developed using the Apache Beam SDK. We benchmark the implemented queries executed on three modern DSPSs: Apache Flink, Apache Spark Streaming, and Hazelcast Jet. The results of the study prove the functioning of ESPBench and its toolkit. ESPBench is capable of quantifying performance characteristics of DSPSs and of unveiling differences among systems. The benchmark proposed in this thesis covers all requirements to be applied in enterprise stream processing settings, and thus represents an improvement over the current state-of-the-art.}, language = {en} } @phdthesis{Krentz2019, author = {Krentz, Konrad-Felix}, title = {A Denial-of-Sleep-Resilient Medium Access Control Layer for IEEE 802.15.4 Networks}, doi = {10.25932/publishup-43930}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-439301}, school = {Universit{\"a}t Potsdam}, pages = {xiv, 187}, year = {2019}, abstract = {With the emergence of the Internet of things (IoT), plenty of battery-powered and energy-harvesting devices are being deployed to fulfill sensing and actuation tasks in a variety of application areas, such as smart homes, precision agriculture, smart cities, and industrial automation. In this context, a critical issue is that of denial-of-sleep attacks. Such attacks temporarily or permanently deprive battery-powered, energy-harvesting, or otherwise energy-constrained devices of entering energy-saving sleep modes, thereby draining their charge. At the very least, a successful denial-of-sleep attack causes a long outage of the victim device. Moreover, to put battery-powered devices back into operation, their batteries have to be replaced. This is tedious and may even be infeasible, e.g., if a battery-powered device is deployed at an inaccessible location. While the research community came up with numerous defenses against denial-of-sleep attacks, most present-day IoT protocols include no denial-of-sleep defenses at all, presumably due to a lack of awareness and unsolved integration problems. After all, despite there are many denial-of-sleep defenses, effective defenses against certain kinds of denial-of-sleep attacks are yet to be found. The overall contribution of this dissertation is to propose a denial-of-sleep-resilient medium access control (MAC) layer for IoT devices that communicate over IEEE 802.15.4 links. Internally, our MAC layer comprises two main components. The first main component is a denial-of-sleep-resilient protocol for establishing session keys among neighboring IEEE 802.15.4 nodes. The established session keys serve the dual purpose of implementing (i) basic wireless security and (ii) complementary denial-of-sleep defenses that belong to the second main component. The second main component is a denial-of-sleep-resilient MAC protocol. Notably, this MAC protocol not only incorporates novel denial-of-sleep defenses, but also state-of-the-art mechanisms for achieving low energy consumption, high throughput, and high delivery ratios. Altogether, our MAC layer resists, or at least greatly mitigates, all denial-of-sleep attacks against it we are aware of. Furthermore, our MAC layer is self-contained and thus can act as a drop-in replacement for IEEE 802.15.4-compliant MAC layers. In fact, we implemented our MAC layer in the Contiki-NG operating system, where it seamlessly integrates into an existing protocol stack.}, language = {en} } @book{SchneiderLambersOrejas2019, author = {Schneider, Sven and Lambers, Leen and Orejas, Fernando}, title = {A logic-based incremental approach to graph repair}, number = {126}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-462-3}, issn = {1613-5652}, doi = {10.25932/publishup-42751}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-427517}, publisher = {Universit{\"a}t Potsdam}, pages = {34}, year = {2019}, abstract = {Graph repair, restoring consistency of a graph, plays a prominent role in several areas of computer science and beyond: For example, in model-driven engineering, the abstract syntax of models is usually encoded using graphs. Flexible edit operations temporarily create inconsistent graphs not representing a valid model, thus requiring graph repair. Similarly, in graph databases—managing the storage and manipulation of graph data—updates may cause that a given database does not satisfy some integrity constraints, requiring also graph repair. We present a logic-based incremental approach to graph repair, generating a sound and complete (upon termination) overview of least-changing repairs. In our context, we formalize consistency by so-called graph conditions being equivalent to first-order logic on graphs. We present two kind of repair algorithms: State-based repair restores consistency independent of the graph update history, whereas deltabased (or incremental) repair takes this history explicitly into account. Technically, our algorithms rely on an existing model generation algorithm for graph conditions implemented in AutoGraph. Moreover, the delta-based approach uses the new concept of satisfaction (ST) trees for encoding if and how a graph satisfies a graph condition. We then demonstrate how to manipulate these STs incrementally with respect to a graph update.}, language = {en} } @article{StaubitzSerthThomasetal.2023, author = {Staubitz, Thomas and Serth, Sebastian and Thomas, Max and Ebner, Martin and Koschutnig-Ebner, Markus and Rampelt, Florian and von Stetten, Alexander and Wittke, Andreas}, title = {A metastandard for the international exchange of MOOCs}, series = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, journal = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, editor = {Meinel, Christoph and Schweiger, Stefanie and Staubitz, Thomas and Conrad, Robert and Alario Hoyos, Carlos and Ebner, Martin and Sancassani, Susanna and Żur, Agnieszka and Friedl, Christian and Halawa, Sherif and Gamage, Dilrukshi and Scott, Jeffrey and Kristine Jonson Carlon, May and Deville, Yves and Gaebel, Michael and Delgado Kloos, Carlos and von Schmieden, Karen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-62415}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-624154}, pages = {147 -- 161}, year = {2023}, abstract = {The MOOChub is a joined web-based catalog of all relevant German and Austrian MOOC platforms that lists well over 750 Massive Open Online Courses (MOOCs). Automatically building such a catalog requires that all partners describe and publicly offer the metadata of their courses in the same way. The paper at hand presents the genesis of the idea to establish a common metadata standard and the story of its subsequent development. The result of this effort is, first, an open-licensed de-facto-standard, which is based on existing commonly used standards and second, a first prototypical platform that is using this standard: the MOOChub, which lists all courses of the involved partners. This catalog is searchable and provides a more comprehensive overview of basically all MOOCs that are offered by German and Austrian MOOC platforms. Finally, the upcoming developments to further optimize the catalog and the metadata standard are reported.}, language = {en} } @article{PerachAlexandron2021, author = {Perach, Shai and Alexandron, Giora}, title = {A MOOC-Based Computer Science Program for Middle School}, series = {EMOOCs 2021}, volume = {2021}, journal = {EMOOCs 2021}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51713}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-517133}, pages = {111 -- 127}, year = {2021}, abstract = {In an attempt to pave the way for more extensive Computer Science Education (CSE) coverage in K-12, this research developed and made a preliminary evaluation of a blended-learning Introduction to CS program based on an academic MOOC. Using an academic MOOC that is pedagogically effective and engaging, such a program may provide teachers with disciplinary scaffolds and allow them to focus their attention on enhancing students' learning experience and nurturing critical 21st-century skills such as self-regulated learning. As we demonstrate, this enabled us to introduce an academic level course to middle-school students. In this research, we developed the principals and initial version of such a program, targeting ninth-graders in science-track classes who learn CS as part of their standard curriculum. We found that the middle-schoolers who participated in the program achieved academic results on par with undergraduate students taking this MOOC for academic credit. Participating students also developed a more accurate perception of the essence of CS as a scientific discipline. The unplanned school closure due to the COVID19 pandemic outbreak challenged the research but underlined the advantages of such a MOOCbased blended learning program above classic pedagogy in times of global or local crises that lead to school closure. While most of the science track classes seem to stop learning CS almost entirely, and the end-of-year MoE exam was discarded, the program's classes smoothly moved to remote learning mode, and students continued to study at a pace similar to that experienced before the school shut down.}, language = {en} } @misc{GieseHenklerHirsch2017, author = {Giese, Holger and Henkler, Stefan and Hirsch, Martin}, title = {A multi-paradigm approach supporting the modular execution of reconfigurable hybrid systems}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-402896}, pages = {34}, year = {2017}, abstract = {Advanced mechatronic systems have to integrate existing technologies from mechanical, electrical and software engineering. They must be able to adapt their structure and behavior at runtime by reconfiguration to react flexibly to changes in the environment. Therefore, a tight integration of structural and behavioral models of the different domains is required. This integration results in complex reconfigurable hybrid systems, the execution logic of which cannot be addressed directly with existing standard modeling, simulation, and code-generation techniques. We present in this paper how our component-based approach for reconfigurable mechatronic systems, M ECHATRONIC UML, efficiently handles the complex interplay of discrete behavior and continuous behavior in a modular manner. In addition, its extension to even more flexible reconfiguration cases is presented.}, language = {en} } @article{ShlakaOuahibBerrada2023, author = {Shlaka, Souhad and Ouahib, Sara and Berrada, Khalid}, title = {A retrospective feedback of MOOCS in Morocco}, series = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, journal = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, editor = {Meinel, Christoph and Schweiger, Stefanie and Staubitz, Thomas and Conrad, Robert and Alario Hoyos, Carlos and Ebner, Martin and Sancassani, Susanna and Żur, Agnieszka and Friedl, Christian and Halawa, Sherif and Gamage, Dilrukshi and Scott, Jeffrey and Kristine Jonson Carlon, May and Deville, Yves and Gaebel, Michael and Delgado Kloos, Carlos and von Schmieden, Karen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-62482}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-624826}, pages = {317 -- 327}, year = {2023}, abstract = {The integration of MOOCs into the Moroccan Higher Education (MHE) took place in 2013 by developing different partnerships and projects at national and international levels. As elsewhere, the Covid-19 crisis has played an important role in accelerating distance education in MHE. However, based on our experience as both university professors and specialists in educational engineering, the effective execution of the digital transition has not yet been implemented. Thus, in this article, we present a retrospective feedback of MOOCs in Morocco, focusing on the policies taken by the government to better support the digital transition in general and MOOCs in particular. We are therefore seeking to establish an optimal scenario for the promotion of MOOCs, which emphasizes the policies to be considered, and which recalls the importance of conducting a delicate articulation taking into account four levels, namely environmental, institutional, organizational and individual. We conclude with recommendations that are inspired by the Moroccan academic contex that focus on the major role that MOOCs plays for university students and on maintaining lifelong learning.}, language = {en} } @phdthesis{Buschmann2018, author = {Buschmann, Stefan}, title = {A software framework for GPU-based geo-temporal visualization techniques}, doi = {10.25932/publishup-44340}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-443406}, school = {Universit{\"a}t Potsdam}, pages = {viii, 99}, year = {2018}, abstract = {R{\"a}umlich-zeitliche Daten sind Daten, welche sowohl einen Raum- als auch einen Zeitbezug aufweisen. So k{\"o}nnen beispielsweise Zeitreihen von Geodaten, thematische Karten die sich {\"u}ber die Zeit ver{\"a}ndern, oder Bewegungsaufzeichnungen von sich bewegenden Objekten als r{\"a}umlich-zeitliche Daten aufgefasst werden. In der heutigen automatisierten Welt gibt es eine wachsende Anzahl von Datenquellen, die best{\"a}ndig r{\"a}umlich-zeitliche Daten generieren. Hierzu geh{\"o}ren beispielsweise Verkehrs{\"u}berwachungssysteme, die Bewegungsdaten von Menschen oder Fahrzeugen aufzeichnen, Fernerkundungssysteme, welche regelm{\"a}ßig unsere Umgebung scannen und digitale Abbilder wie z.B. Stadt- und Landschaftsmodelle erzeugen, sowie Sensornetzwerke in unterschiedlichsten Anwendungsgebieten, wie z.B. der Logistik, der Verhaltensforschung von Tieren, oder der Klimaforschung. Zur Analyse r{\"a}umlich-zeitlicher Daten werden neben der automatischen Analyse mittels statistischer Methoden und Data-Mining auch explorative Methoden angewendet, welche auf der interaktiven Visualisierung der Daten beruhen. Diese Methode der Analyse basiert darauf, dass Anwender in Form interaktiver Visualisierung die Daten explorieren k{\"o}nnen, wodurch die menschliche Wahrnehmung sowie das Wissen der User genutzt werden, um Muster zu erkennen und dadurch einen Einblick in die Daten zu erlangen. Diese Arbeit beschreibt ein Software-Framework f{\"u}r die Visualisierung r{\"a}umlich-zeitlicher Daten, welches GPU-basierte Techniken beinhaltet, um eine interaktive Visualisierung und Exploration großer r{\"a}umlich-zeitlicher Datens{\"a}tze zu erm{\"o}glichen. Die entwickelten Techniken umfassen Datenhaltung, Prozessierung und Rendering und erm{\"o}glichen es, große Datenmengen in Echtzeit zu prozessieren und zu visualisieren. Die Hauptbeitr{\"a}ge der Arbeit umfassen: - Konzept und Implementierung einer GPU-zentrierten Visualisierungspipeline. Die beschriebenen Techniken basieren auf dem Konzept einer GPU-zentrierten Visualisierungspipeline, in welcher alle Stufen -- Prozessierung,Mapping, Rendering -- auf der GPU ausgef{\"u}hrt werden. Bei diesem Konzept werden die r{\"a}umlich-zeitlichen Daten direkt im GPU-Speicher abgelegt. W{\"a}hrend des Rendering-Prozesses werden dann mittels Shader-Programmen die Daten prozessiert, gefiltert, ein Mapping auf visuelle Attribute vorgenommen, und schließlich die Geometrien f{\"u}r die Visualisierung erzeugt. Datenprozessierung, Filtering und Mapping k{\"o}nnen daher in Echtzeit ausgef{\"u}hrt werden. Dies erm{\"o}glicht es Usern, die Mapping-Parameter sowie den gesamten Visualisierungsprozess interaktiv zu steuern und zu kontrollieren. - Interaktive Visualisierung attributierter 3D-Trajektorien. Es wurde eine Visualisierungsmethode f{\"u}r die interaktive Exploration einer großen Anzahl von 3D Bewegungstrajektorien entwickelt. Die Trajektorien werden dabei innerhalb einer virtuellen geographischen Umgebung in Form von einfachen Geometrien, wie Linien, B{\"a}ndern, Kugeln oder R{\"o}hren dargestellt. Durch interaktives Mapping k{\"o}nnen Attributwerte der Trajektorien oder einzelner Messpunkte auf visuelle Eigenschaften abgebildet werden. Hierzu stehen Form, H{\"o}he, Gr{\"o}ße, Farbe, Textur, sowie Animation zur Verf{\"u}gung. Mithilfe dieses dynamischen Mappings wurden außerdem verschiedene Visualisierungsmethoden implementiert, wie z.B. eine Focus+Context-Visualisierung von Trajektorien mithilfe von interaktiven Dichtekarten, sowie einer Space-Time-Cube-Visualisierung zur Darstellung des zeitlichen Ablaufs einzelner Bewegungen. - Interaktive Visualisierung geographischer Netzwerke. Es wurde eine Visualisierungsmethode zur interaktiven Exploration geo-referenzierter Netzwerke entwickelt, welche die Visualisierung von Netzwerken mit einer großen Anzahl von Knoten und Kanten erm{\"o}glicht. Um die Analyse von Netzwerken verschiedener Gr{\"o}ßen und in unterschiedlichen Kontexten zu erm{\"o}glichen, stehen mehrere virtuelle geographische Umgebungen zur Verf{\"u}gung, wie bspw. ein virtueller 3D-Globus, als auch 2D-Karten mit unterschiedlichen geographischen Projektionen. Zur interaktiven Analyse dieser Netzwerke stehen interaktive Tools wie Filterung, Mapping und Selektion zur Verf{\"u}gung. Des weiteren wurden Visualisierungsmethoden f{\"u}r verschiedene Arten von Netzwerken, wie z.B. 3D-Netzwerke und zeitlich ver{\"a}nderliche Netzwerke, implementiert. Zur Demonstration des Konzeptes wurden interaktive Tools f{\"u}r zwei unterschiedliche Anwendungsf{\"a}lle entwickelt. Das erste beinhaltet die Visualisierung attributierter 3D-Trajektorien, welche die Bewegungen von Flugzeugen um einen Flughafen beschreiben. Es erm{\"o}glicht Nutzern, die Trajektorien von ankommenden und startenden Flugzeugen {\"u}ber den Zeitraum eines Monats interaktiv zu explorieren und zu analysieren. Durch Verwendung der interaktiven Visualisierungsmethoden f{\"u}r 3D-Trajektorien und interaktiven Dichtekarten k{\"o}nnen Einblicke in die Daten gewonnen werden, wie beispielsweise h{\"a}ufig genutzte Flugkorridore, typische sowie untypische Bewegungsmuster, oder ungew{\"o}hnliche Vorkommnisse wie Fehlanfl{\"u}ge. Der zweite Anwendungsfall beinhaltet die Visualisierung von Klimanetzwerken, welche geographischen Netzwerken in der Klimaforschung darstellen. Klimanetzwerke repr{\"a}sentieren die Dynamiken im Klimasystem durch eine Netzwerkstruktur, die die statistische Beziehungen zwischen Orten beschreiben. Das entwickelte Tool erm{\"o}glicht es Analysten, diese großen Netzwerke interaktiv zu explorieren und dadurch die Struktur des Netzwerks zu analysieren und mit den geographischen Daten in Beziehung zu setzen. Interaktive Filterung und Selektion erm{\"o}glichen es, Muster in den Daten zu identifizieren, und so bspw. Cluster in der Netzwerkstruktur oder Str{\"o}mungsmuster zu erkennen.}, language = {en} } @phdthesis{Kraus2021, author = {Kraus, Sara Milena}, title = {A Systems Medicine approach for heart valve diseases}, doi = {10.25932/publishup-52226}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-522266}, school = {Universit{\"a}t Potsdam}, pages = {xi, 186}, year = {2021}, abstract = {In Systems Medicine, in addition to high-throughput molecular data (*omics), the wealth of clinical characterization plays a major role in the overall understanding of a disease. Unique problems and challenges arise from the heterogeneity of data and require new solutions to software and analysis methods. The SMART and EurValve studies establish a Systems Medicine approach to valvular heart disease -- the primary cause of subsequent heart failure. With the aim to ascertain a holistic understanding, different *omics as well as the clinical picture of patients with aortic stenosis (AS) and mitral regurgitation (MR) are collected. Our task within the SMART consortium was to develop an IT platform for Systems Medicine as a basis for data storage, processing, and analysis as a prerequisite for collaborative research. Based on this platform, this thesis deals on the one hand with the transfer of the used Systems Biology methods to their use in the Systems Medicine context and on the other hand with the clinical and biomolecular differences of the two heart valve diseases. To advance differential expression/abundance (DE/DA) analysis software for use in Systems Medicine, we state 21 general software requirements and features of automated DE/DA software, including a novel concept for the simple formulation of experimental designs that can represent complex hypotheses, such as comparison of multiple experimental groups, and demonstrate our handling of the wealth of clinical data in two research applications DEAME and Eatomics. In user interviews, we show that novice users are empowered to formulate and test their multiple DE hypotheses based on clinical phenotype. Furthermore, we describe insights into users' general impression and expectation of the software's performance and show their intention to continue using the software for their work in the future. Both research applications cover most of the features of existing tools or even extend them, especially with respect to complex experimental designs. Eatomics is freely available to the research community as a user-friendly R Shiny application. Eatomics continued to help drive the collaborative analysis and interpretation of the proteomic profile of 75 human left myocardial tissue samples from the SMART and EurValve studies. Here, we investigate molecular changes within the two most common types of valvular heart disease: aortic valve stenosis (AS) and mitral valve regurgitation (MR). Through DE/DA analyses, we explore shared and disease-specific protein alterations, particularly signatures that could only be found in the sex-stratified analysis. In addition, we relate changes in the myocardial proteome to parameters from clinical imaging. We find comparable cardiac hypertrophy but differences in ventricular size, the extent of fibrosis, and cardiac function. We find that AS and MR show many shared remodeling effects, the most prominent of which is an increase in the extracellular matrix and a decrease in metabolism. Both effects are stronger in AS. In muscle and cytoskeletal adaptations, we see a greater increase in mechanotransduction in AS and an increase in cortical cytoskeleton in MR. The decrease in proteostasis proteins is mainly attributable to the signature of female patients with AS. We also find relevant therapeutic targets. In addition to the new findings, our work confirms several concepts from animal and heart failure studies by providing the largest collection of human tissue from in vivo collected biopsies to date. Our dataset contributing a resource for isoform-specific protein expression in two of the most common valvular heart diseases. Apart from the general proteomic landscape, we demonstrate the added value of the dataset by showing proteomic and transcriptomic evidence for increased expression of the SARS-CoV-2- receptor at pressure load but not at volume load in the left ventricle and also provide the basis of a newly developed metabolic model of the heart.}, language = {en} } @misc{ScheibelTrappLimbergeretal.2020, author = {Scheibel, Willy and Trapp, Matthias and Limberger, Daniel and D{\"o}llner, J{\"u}rgen Roland Friedrich}, title = {A taxonomy of treemap visualization techniques}, series = {Postprints der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, journal = {Postprints der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, number = {8}, doi = {10.25932/publishup-52469}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-524693}, pages = {10}, year = {2020}, abstract = {A treemap is a visualization that has been specifically designed to facilitate the exploration of tree-structured data and, more general, hierarchically structured data. The family of visualization techniques that use a visual metaphor for parent-child relationships based "on the property of containment" (Johnson, 1993) is commonly referred to as treemaps. However, as the number of variations of treemaps grows, it becomes increasingly important to distinguish clearly between techniques and their specific characteristics. This paper proposes to discern between Space-filling Treemap TS, Containment Treemap TC, Implicit Edge Representation Tree TIE, and Mapped Tree TMT for classification of hierarchy visualization techniques and highlights their respective properties. This taxonomy is created as a hyponymy, i.e., its classes have an is-a relationship to one another: TS TC TIE TMT. With this proposal, we intend to stimulate a discussion on a more unambiguous classification of treemaps and, furthermore, broaden what is understood by the concept of treemap itself.}, language = {en} } @article{NohrHaugsbakken2023, author = {Nohr, Magnus and Haugsbakken, Halvdan}, title = {A taxonomy of video genres as a scaffolding strategy for video making in education}, series = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, journal = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, editor = {Meinel, Christoph and Schweiger, Stefanie and Staubitz, Thomas and Conrad, Robert and Alario Hoyos, Carlos and Ebner, Martin and Sancassani, Susanna and Żur, Agnieszka and Friedl, Christian and Halawa, Sherif and Gamage, Dilrukshi and Scott, Jeffrey and Kristine Jonson Carlon, May and Deville, Yves and Gaebel, Michael and Delgado Kloos, Carlos and von Schmieden, Karen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-62429}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-624294}, pages = {201 -- 220}, year = {2023}, abstract = {This research paper aims to introduce a novel practitioner-oriented and research-based taxonomy of video genres. This taxonomy can serve as a scaffolding strategy to support educators throughout the entire educational system in creating videos for pedagogical purposes. A taxonomy of video genres is essential as videos are highly valued resources among learners. Although the use of videos in education has been extensively researched and well-documented in systematic research reviews, gaps remain in the literature. Predominantly, researchers employ sophisticated quantitative methods and similar approaches to measure the performance of videos. This trend has led to the emergence of a strong learning analytics research tradition with its embedded literature. This body of research includes analysis of performance of videos in online courses such as Massive Open Online Courses (MOOCs). Surprisingly, this same literature is limited in terms of research outlining approaches to designing and creating educational videos, which applies to both video-based learning and online courses. This issue results in a knowledge gap, highlighting the need for developing pedagogical tools and strategies for video making. These can be found in frameworks, guidelines, and taxonomies, which can serve as scaffolding strategies. In contrast, there appears to be very few frameworks available for designing and creating videos for pedagogica purposes, apart from a few well-known frameworks. In this regard, this research paper proposes a novel taxonomy of video genres that educators can utilize when creating videos intended for use in either video-based learning environments or online courses. To create this taxonomy, a large number of videos from online courses were collected and analyzed using a mixed-method research design approach.}, language = {en} } @phdthesis{Katzmann2023, author = {Katzmann, Maximilian}, title = {About the analysis of algorithms on networks with underlying hyperbolic geometry}, doi = {10.25932/publishup-58296}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-582965}, school = {Universit{\"a}t Potsdam}, pages = {xi, 191}, year = {2023}, abstract = {Many complex systems that we encounter in the world can be formalized using networks. Consequently, they have been in the focus of computer science for decades, where algorithms are developed to understand and utilize these systems. Surprisingly, our theoretical understanding of these algorithms and their behavior in practice often diverge significantly. In fact, they tend to perform much better on real-world networks than one would expect when considering the theoretical worst-case bounds. One way of capturing this discrepancy is the average-case analysis, where the idea is to acknowledge the differences between practical and worst-case instances by focusing on networks whose properties match those of real graphs. Recent observations indicate that good representations of real-world networks are obtained by assuming that a network has an underlying hyperbolic geometry. In this thesis, we demonstrate that the connection between networks and hyperbolic space can be utilized as a powerful tool for average-case analysis. To this end, we first introduce strongly hyperbolic unit disk graphs and identify the famous hyperbolic random graph model as a special case of them. We then consider four problems where recent empirical results highlight a gap between theory and practice and use hyperbolic graph models to explain these phenomena theoretically. First, we develop a routing scheme, used to forward information in a network, and analyze its efficiency on strongly hyperbolic unit disk graphs. For the special case of hyperbolic random graphs, our algorithm beats existing performance lower bounds. Afterwards, we use the hyperbolic random graph model to theoretically explain empirical observations about the performance of the bidirectional breadth-first search. Finally, we develop algorithms for computing optimal and nearly optimal vertex covers (problems known to be NP-hard) and show that, on hyperbolic random graphs, they run in polynomial and quasi-linear time, respectively. Our theoretical analyses reveal interesting properties of hyperbolic random graphs and our empirical studies present evidence that these properties, as well as our algorithmic improvements translate back into practice.}, language = {en} } @techreport{DoellnerFriedrichArnrichetal.2022, author = {D{\"o}llner, J{\"u}rgen Roland Friedrich and Friedrich, Tobias and Arnrich, Bert and Hirschfeld, Robert and Lippert, Christoph and Meinel, Christoph}, title = {Abschlussbericht KI-Labor ITSE}, doi = {10.25932/publishup-57860}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-578604}, pages = {60}, year = {2022}, abstract = {Der Abschlussbericht beschreibt Aufgaben und Ergebnisse des KI-Labors "ITSE". Gegenstand des KI-Labors bildeten Methodik, Technik und Ausbildung in der IT-Systemtechnik zur Analyse, Planung und Konstruktion KI-basierter, komplexer IT-Systeme.}, language = {de} } @article{HaugsbakkenHagelia2023, author = {Haugsbakken, Halvdan and Hagelia, Marianne}, title = {An asynchronous cooperative leaning design in a Small Private Online Course (SPOC)}, series = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, journal = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, editor = {Meinel, Christoph and Schweiger, Stefanie and Staubitz, Thomas and Conrad, Robert and Alario Hoyos, Carlos and Ebner, Martin and Sancassani, Susanna and Żur, Agnieszka and Friedl, Christian and Halawa, Sherif and Gamage, Dilrukshi and Scott, Jeffrey and Kristine Jonson Carlon, May and Deville, Yves and Gaebel, Michael and Delgado Kloos, Carlos and von Schmieden, Karen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-62210}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-622107}, pages = {67 -- 76}, year = {2023}, abstract = {This short paper sets out to propose a novel and interesting learning design that facilitates for cooperative learning in which students do not conduct traditional group work in an asynchronous online education setting. This learning design will be explored in a Small Private Online Course (SPOC) among teachers and school managers at a teacher education. Such an approach can be made possible by applying specific criteria commonly used to define collaborative learning. Collaboration can be defined, among other things, as a structured way of working among students that includes elements of co-laboring. The cooperative learning design involves adapting various traditional collaborative learning approaches for use in an online learning environment. A critical component of this learning design is that students work on a self-defined case project related to their professional practices. Through an iterative process, students will receive ongoing feedback and formative assessments from instructors and follow students at specific points, meaning that co-constructing of knowledge and learning takes place as the SPOC progresses. This learning design can contribute to better learning experiences and outcomes for students, and be a valuable contribution to current research discussions on learning design in Massive Open Online Courses (MOOCs).}, language = {en} } @article{ConciaDistlerLawetal.2023, author = {Concia, Francesca and Distler, Petr and Law, Gareth and Macerata, Elena and Mariani, Mario and Mossini, Eros and Negrin, Maddalena and Štrok, Marko}, title = {An experience in developing models to use MOOCs in teaching and to advocate OERs}, series = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, journal = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, editor = {Meinel, Christoph and Schweiger, Stefanie and Staubitz, Thomas and Conrad, Robert and Alario Hoyos, Carlos and Ebner, Martin and Sancassani, Susanna and Żur, Agnieszka and Friedl, Christian and Halawa, Sherif and Gamage, Dilrukshi and Scott, Jeffrey and Kristine Jonson Carlon, May and Deville, Yves and Gaebel, Michael and Delgado Kloos, Carlos and von Schmieden, Karen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-62460}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-624609}, pages = {239 -- 254}, year = {2023}, abstract = {Loss of expertise in the fields of Nuclear- and Radio-Chemistry (NRC) is problematic at a scientific and social level. This has been addressed by developing a MOOC, in order to let students in scientific matters discover all the benefits of NRC to society and improving their awareness of this discipline. The MOOC "Essential Radiochemistry for Society" includes current societal challenges related to health, clean and sustainable energy for safety and quality of food and agriculture. NRC teachers belonging to CINCH network were invited to use the MOOC in their teaching, according to various usage models: on the basis of these different experiences, some usage patterns were designed, describing context characteristics (number and age of students, course), activities' scheduling and organization, results and students' feedback, with the aim of encouraging the use of MOOCs in university teaching, as an opportunity for both lecturers and students. These models were the basis of a "toolkit for teachers". By experiencing digital teaching resources created by different lecturers, CINCH teachers took a first meaningful step towards understanding the worth of Open Educational Resources (OER) and the importance of their creation, adoption and sharing for knowledge progress. In this paper, the entire path from MOOC concept to MOOC different usage models, to awareness-raising regarding OER is traced in conceptual stages.}, language = {en} } @book{BaltzerHradilakPfennigschmidtetal.2021, author = {Baltzer, Wanda and Hradilak, Theresa and Pfennigschmidt, Lara and Prestin, Luc Maurice and Spranger, Moritz and Stadlinger, Simon and Wendt, Leo and Lincke, Jens and Rein, Patrick and Church, Luke and Hirschfeld, Robert}, title = {An individual-centered approach to visualize people's opinions and demographic information}, number = {136}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-504-0}, issn = {1613-5652}, doi = {10.25932/publishup-49145}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-491457}, publisher = {Universit{\"a}t Potsdam}, pages = {326}, year = {2021}, abstract = {The noble way to substantiate decisions that affect many people is to ask these people for their opinions. For governments that run whole countries, this means asking all citizens for their views to consider their situations and needs. Organizations such as Africa's Voices Foundation, who want to facilitate communication between decision-makers and citizens of a country, have difficulty mediating between these groups. To enable understanding, statements need to be summarized and visualized. Accomplishing these goals in a way that does justice to the citizens' voices and situations proves challenging. Standard charts do not help this cause as they fail to create empathy for the people behind their graphical abstractions. Furthermore, these charts do not create trust in the data they are representing as there is no way to see or navigate back to the underlying code and the original data. To fulfill these functions, visualizations would highly benefit from interactions to explore the displayed data, which standard charts often only limitedly provide. To help improve the understanding of people's voices, we developed and categorized 80 ideas for new visualizations, new interactions, and better connections between different charts, which we present in this report. From those ideas, we implemented 10 prototypes and two systems that integrate different visualizations. We show that this integration allows consistent appearance and behavior of visualizations. The visualizations all share the same main concept: representing each individual with a single dot. To realize this idea, we discuss technologies that efficiently allow the rendering of a large number of these dots. With these visualizations, direct interactions with representations of individuals are achievable by clicking on them or by dragging a selection around them. This direct interaction is only possible with a bidirectional connection from the visualization to the data it displays. We discuss different strategies for bidirectional mappings and the trade-offs involved. Having unified behavior across visualizations enhances exploration. For our prototypes, that includes grouping, filtering, highlighting, and coloring of dots. Our prototyping work was enabled by the development environment Lively4. We explain which parts of Lively4 facilitated our prototyping process. Finally, we evaluate our approach to domain problems and our developed visualization concepts. Our work provides inspiration and a starting point for visualization development in this domain. Our visualizations can improve communication between citizens and their government and motivate empathetic decisions. Our approach, combining low-level entities to create visualizations, provides value to an explorative and empathetic workflow. We show that the design space for visualizing this kind of data has a lot of potential and that it is possible to combine qualitative and quantitative approaches to data analysis.}, language = {en} } @phdthesis{Wolf2021, author = {Wolf, Johannes}, title = {Analysis and visualization of transport infrastructure based on large-scale geospatial mobile mapping data}, doi = {10.25932/publishup-53612}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-536129}, school = {Universit{\"a}t Potsdam}, pages = {vi, 121}, year = {2021}, abstract = {3D point clouds are a universal and discrete digital representation of three-dimensional objects and environments. For geospatial applications, 3D point clouds have become a fundamental type of raw data acquired and generated using various methods and techniques. In particular, 3D point clouds serve as raw data for creating digital twins of the built environment. This thesis concentrates on the research and development of concepts, methods, and techniques for preprocessing, semantically enriching, analyzing, and visualizing 3D point clouds for applications around transport infrastructure. It introduces a collection of preprocessing techniques that aim to harmonize raw 3D point cloud data, such as point density reduction and scan profile detection. Metrics such as, e.g., local density, verticality, and planarity are calculated for later use. One of the key contributions tackles the problem of analyzing and deriving semantic information in 3D point clouds. Three different approaches are investigated: a geometric analysis, a machine learning approach operating on synthetically generated 2D images, and a machine learning approach operating on 3D point clouds without intermediate representation. In the first application case, 2D image classification is applied and evaluated for mobile mapping data focusing on road networks to derive road marking vector data. The second application case investigates how 3D point clouds can be merged with ground-penetrating radar data for a combined visualization and to automatically identify atypical areas in the data. For example, the approach detects pavement regions with developing potholes. The third application case explores the combination of a 3D environment based on 3D point clouds with panoramic imagery to improve visual representation and the detection of 3D objects such as traffic signs. The presented methods were implemented and tested based on software frameworks for 3D point clouds and 3D visualization. In particular, modules for metric computation, classification procedures, and visualization techniques were integrated into a modular pipeline-based C++ research framework for geospatial data processing, extended by Python machine learning scripts. All visualization and analysis techniques scale to large real-world datasets such as road networks of entire cities or railroad networks. The thesis shows that some use cases allow taking advantage of established image vision methods to analyze images rendered from mobile mapping data efficiently. The two presented semantic classification methods working directly on 3D point clouds are use case independent and show similar overall accuracy when compared to each other. While the geometry-based method requires less computation time, the machine learning-based method supports arbitrary semantic classes but requires training the network with ground truth data. Both methods can be used in combination to gradually build this ground truth with manual corrections via a respective annotation tool. This thesis contributes results for IT system engineering of applications, systems, and services that require spatial digital twins of transport infrastructure such as road networks and railroad networks based on 3D point clouds as raw data. It demonstrates the feasibility of fully automated data flows that map captured 3D point clouds to semantically classified models. This provides a key component for seamlessly integrated spatial digital twins in IT solutions that require up-to-date, object-based, and semantically enriched information about the built environment.}, language = {en} } @phdthesis{Meinig2019, author = {Meinig, Michael}, title = {Bedrohungsanalyse f{\"u}r milit{\"a}rische Informationstechnik}, doi = {10.25932/publishup-44160}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-441608}, school = {Universit{\"a}t Potsdam}, pages = {X, 137}, year = {2019}, abstract = {Risiken f{\"u}r Cyberressourcen k{\"o}nnen durch unbeabsichtigte oder absichtliche Bedrohungen entstehen. Dazu geh{\"o}ren Insider-Bedrohungen von unzufriedenen oder nachl{\"a}ssigen Mitarbeitern und Partnern, eskalierende und aufkommende Bedrohungen aus aller Welt, die stetige Weiterentwicklung der Angriffstechnologien und die Entstehung neuer und zerst{\"o}rerischer Angriffe. Informationstechnik spielt mittlerweile in allen Bereichen des Lebens eine entscheidende Rolle, u. a. auch im Bereich des Milit{\"a}rs. Ein ineffektiver Schutz von Cyberressourcen kann hier Sicherheitsvorf{\"a}lle und Cyberattacken erleichtern, welche die kritischen Vorg{\"a}nge st{\"o}ren, zu unangemessenem Zugriff, Offenlegung, {\"A}nderung oder Zerst{\"o}rung sensibler Informationen f{\"u}hren und somit die nationale Sicherheit, das wirtschaftliche Wohlergehen sowie die {\"o}ffentliche Gesundheit und Sicherheit gef{\"a}hrden. Oftmals ist allerdings nicht klar, welche Bedrohungen konkret vorhanden sind und welche der kritischen Systemressourcen besonders gef{\"a}hrdet ist. In dieser Dissertation werden verschiedene Analyseverfahren f{\"u}r Bedrohungen in milit{\"a}rischer Informationstechnik vorgeschlagen und in realen Umgebungen getestet. Dies bezieht sich auf Infrastrukturen, IT-Systeme, Netze und Anwendungen, welche Verschlusssachen (VS)/Staatsgeheimnisse verarbeiten, wie zum Beispiel bei milit{\"a}rischen oder Regierungsorganisationen. Die Besonderheit an diesen Organisationen ist das Konzept der Informationsr{\"a}ume, in denen verschiedene Datenelemente, wie z. B. Papierdokumente und Computerdateien, entsprechend ihrer Sicherheitsempfindlichkeit eingestuft werden, z. B. „STRENG GEHEIM", „GEHEIM", „VS-VERTRAULICH", „VS-NUR-F{\"U}R-DEN-DIENSTGEBRAUCH" oder „OFFEN". Die Besonderheit dieser Arbeit ist der Zugang zu eingestuften Informationen aus verschiedenen Informationsr{\"a}umen und der Prozess der Freigabe dieser. Jede in der Arbeit entstandene Ver{\"o}ffentlichung wurde mit Angeh{\"o}rigen in der Organisation besprochen, gegengelesen und freigegeben, so dass keine eingestuften Informationen an die {\"O}ffentlichkeit gelangen. Die Dissertation beschreibt zun{\"a}chst Bedrohungsklassifikationsschemen und Angreiferstrategien, um daraus ein ganzheitliches, strategiebasiertes Bedrohungsmodell f{\"u}r Organisationen abzuleiten. Im weiteren Verlauf wird die Erstellung und Analyse eines Sicherheitsdatenflussdiagramms definiert, welches genutzt wird, um in eingestuften Informationsr{\"a}umen operationelle Netzknoten zu identifizieren, die aufgrund der Bedrohungen besonders gef{\"a}hrdet sind. Die spezielle, neuartige Darstellung erm{\"o}glicht es, erlaubte und verbotene Informationsfl{\"u}sse innerhalb und zwischen diesen Informationsr{\"a}umen zu verstehen. Aufbauend auf der Bedrohungsanalyse werden im weiteren Verlauf die Nachrichtenfl{\"u}sse der operationellen Netzknoten auf Verst{\"o}ße gegen Sicherheitsrichtlinien analysiert und die Ergebnisse mit Hilfe des Sicherheitsdatenflussdiagramms anonymisiert dargestellt. Durch Anonymisierung der Sicherheitsdatenflussdiagramme ist ein Austausch mit externen Experten zur Diskussion von Sicherheitsproblematiken m{\"o}glich. Der dritte Teil der Arbeit zeigt, wie umfangreiche Protokolldaten der Nachrichtenfl{\"u}sse dahingehend untersucht werden k{\"o}nnen, ob eine Reduzierung der Menge an Daten m{\"o}glich ist. Dazu wird die Theorie der groben Mengen aus der Unsicherheitstheorie genutzt. Dieser Ansatz wird in einer Fallstudie, auch unter Ber{\"u}cksichtigung von m{\"o}glichen auftretenden Anomalien getestet und ermittelt, welche Attribute in Protokolldaten am ehesten redundant sind.}, language = {de} } @article{ŞahinEgloffsteinBotheetal.2021, author = {Şahin, Muhittin and Egloffstein, Marc and Bothe, Max and Rohloff, Tobias and Schenk, Nathanael and Schwerer, Florian and Ifenthaler, Dirk}, title = {Behavioral Patterns in Enterprise MOOCs at openSAP}, series = {EMOOCs 2021}, volume = {2021}, journal = {EMOOCs 2021}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51735}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-517350}, pages = {281 -- 288}, year = {2021}, language = {en} } @book{MeinelGayvoronskayaSchnjakin2018, author = {Meinel, Christoph and Gayvoronskaya, Tatiana and Schnjakin, Maxim}, title = {Blockchain}, number = {124}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-441-8}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-414525}, publisher = {Universit{\"a}t Potsdam}, pages = {102}, year = {2018}, abstract = {The term blockchain has recently become a buzzword, but only few know what exactly lies behind this approach. According to a survey, issued in the first quarter of 2017, the term is only known by 35 percent of German medium-sized enterprise representatives. However, the blockchain technology is very interesting for the mass media because of its rapid development and global capturing of different markets. For example, many see blockchain technology either as an all-purpose weapon— which only a few have access to—or as a hacker technology for secret deals in the darknet. The innovation of blockchain technology is found in its successful combination of already existing approaches: such as decentralized networks, cryptography, and consensus models. This innovative concept makes it possible to exchange values in a decentralized system. At the same time, there is no requirement for trust between its nodes (e.g. users). With this study the Hasso Plattner Institute would like to help readers form their own opinion about blockchain technology, and to distinguish between truly innovative properties and hype. The authors of the present study analyze the positive and negative properties of the blockchain architecture and suggest possible solutions, which can contribute to the efficient use of the technology. We recommend that every company define a clear target for the intended application, which is achievable with a reasonable cost-benefit ration, before deciding on this technology. Both the possibilities and the limitations of blockchain technology need to be considered. The relevant steps that must be taken in this respect are summarized /summed up for the reader in this study. Furthermore, this study elaborates on urgent problems such as the scalability of the blockchain, appropriate consensus algorithm and security, including various types of possible attacks and their countermeasures. New blockchains, for example, run the risk of reducing security, as changes to existing technology can lead to lacks in the security and failures. After discussing the innovative properties and problems of the blockchain technology, its implementation is discussed. There are a lot of implementation opportunities for companies available who are interested in the blockchain realization. The numerous applications have either their own blockchain as a basis or use existing and widespread blockchain systems. Various consortia and projects offer "blockchain-as-a-service{\"a}nd help other companies to develop, test and deploy their own applications. This study gives a detailed overview of diverse relevant applications and projects in the field of blockchain technology. As this technology is still a relatively young and fast developing approach, it still lacks uniform standards to allow the cooperation of different systems and to which all developers can adhere. Currently, developers are orienting themselves to Bitcoin, Ethereum and Hyperledger systems, which serve as the basis for many other blockchain applications. The goal is to give readers a clear and comprehensive overview of blockchain technology and its capabilities.}, language = {en} } @phdthesis{Huegle2024, author = {Huegle, Johannes}, title = {Causal discovery in practice: Non-parametric conditional independence testing and tooling for causal discovery}, doi = {10.25932/publishup-63582}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-635820}, school = {Universit{\"a}t Potsdam}, pages = {xiv, 156}, year = {2024}, abstract = {Knowledge about causal structures is crucial for decision support in various domains. For example, in discrete manufacturing, identifying the root causes of failures and quality deviations that interrupt the highly automated production process requires causal structural knowledge. However, in practice, root cause analysis is usually built upon individual expert knowledge about associative relationships. But, "correlation does not imply causation", and misinterpreting associations often leads to incorrect conclusions. Recent developments in methods for causal discovery from observational data have opened the opportunity for a data-driven examination. Despite its potential for data-driven decision support, omnipresent challenges impede causal discovery in real-world scenarios. In this thesis, we make a threefold contribution to improving causal discovery in practice. (1) The growing interest in causal discovery has led to a broad spectrum of methods with specific assumptions on the data and various implementations. Hence, application in practice requires careful consideration of existing methods, which becomes laborious when dealing with various parameters, assumptions, and implementations in different programming languages. Additionally, evaluation is challenging due to the lack of ground truth in practice and limited benchmark data that reflect real-world data characteristics. To address these issues, we present a platform-independent modular pipeline for causal discovery and a ground truth framework for synthetic data generation that provides comprehensive evaluation opportunities, e.g., to examine the accuracy of causal discovery methods in case of inappropriate assumptions. (2) Applying constraint-based methods for causal discovery requires selecting a conditional independence (CI) test, which is particularly challenging in mixed discrete-continuous data omnipresent in many real-world scenarios. In this context, inappropriate assumptions on the data or the commonly applied discretization of continuous variables reduce the accuracy of CI decisions, leading to incorrect causal structures. Therefore, we contribute a non-parametric CI test leveraging k-nearest neighbors methods and prove its statistical validity and power in mixed discrete-continuous data, as well as the asymptotic consistency when used in constraint-based causal discovery. An extensive evaluation of synthetic and real-world data shows that the proposed CI test outperforms state-of-the-art approaches in the accuracy of CI testing and causal discovery, particularly in settings with low sample sizes. (3) To show the applicability and opportunities of causal discovery in practice, we examine our contributions in real-world discrete manufacturing use cases. For example, we showcase how causal structural knowledge helps to understand unforeseen production downtimes or adds decision support in case of failures and quality deviations in automotive body shop assembly lines.}, language = {en} } @article{NeuboeckLinschinger2023, author = {Neub{\"o}ck, Kristina and Linschinger, Nadine}, title = {Central elements of knowledge and competence development with MOOCs}, series = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, journal = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, editor = {Meinel, Christoph and Schweiger, Stefanie and Staubitz, Thomas and Conrad, Robert and Alario Hoyos, Carlos and Ebner, Martin and Sancassani, Susanna and Żur, Agnieszka and Friedl, Christian and Halawa, Sherif and Gamage, Dilrukshi and Scott, Jeffrey and Kristine Jonson Carlon, May and Deville, Yves and Gaebel, Michael and Delgado Kloos, Carlos and von Schmieden, Karen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-62466}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-624668}, pages = {255 -- 262}, year = {2023}, abstract = {To implement OERs at HEIs sustainably, not just technical infrastructure is required, but also well-trained staff. The University of Graz is in charge of an OER training program for university staff as part of the collaborative project Open Education Austria Advanced (OEAA) with the aim of ensuring long-term competence growth in the use and creation of OERs. The program consists of a MOOC and a guided blended learning format that was evaluated to find out which accompanying teaching and learning concepts can best facilitate targeted competence development. The evaluation of the program shows that learning videos, self-study assignments and synchronous sessions are most useful for the learning process. The results indicate that the creation of OERs is a complex process that can be undergone more effectively in the guided program.}, language = {en} } @article{LorenzBockSchulteOstermann2023, author = {Lorenz, Anja and Bock, Stefanie and Schulte-Ostermann, Juleka}, title = {Challenges and proposals for introducing digital certificates in higher education infrastructures}, series = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, journal = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, editor = {Meinel, Christoph and Schweiger, Stefanie and Staubitz, Thomas and Conrad, Robert and Alario Hoyos, Carlos and Ebner, Martin and Sancassani, Susanna and Żur, Agnieszka and Friedl, Christian and Halawa, Sherif and Gamage, Dilrukshi and Scott, Jeffrey and Kristine Jonson Carlon, May and Deville, Yves and Gaebel, Michael and Delgado Kloos, Carlos and von Schmieden, Karen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-62470}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-624701}, pages = {263 -- 270}, year = {2023}, abstract = {Questions about the recognition of MOOCs within and outside higher education were already being raised in the early 2010s. Today, recognition decisions are still made more or less on a case-by-case basis. However, digital certification approaches are now emerging that could automate recognition processes. The technical development of the required machinereadable documents and infrastructures is already well advanced in some cases. The DigiCerts consortium has developed a solution based on a collective blockchain. There are ongoing and open discussions regarding the particular technology, but the institutional implementation of digital certificates raises further questions. A number of workshops have been held at the Institute for Interactive Systems at Technische Hochschule L{\"u}beck, which have identified the need for new responsibilities for issuing certificates. It has also become clear that all members of higher education institutions need to develop skills in the use of digital certificates.}, language = {en} } @phdthesis{AlhosseiniAlmodarresiYasin2024, author = {Alhosseini Almodarresi Yasin, Seyed Ali}, title = {Classification, prediction and evaluation of graph neural networks on online social media platforms}, doi = {10.25932/publishup-62642}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-626421}, school = {Universit{\"a}t Potsdam}, pages = {xviii, 78}, year = {2024}, abstract = {The vast amount of data generated on social media platforms have made them a valuable source of information for businesses, governments and researchers. Social media data can provide insights into user behavior, preferences, and opinions. In this work, we address two important challenges in social media analytics. Predicting user engagement with online content has become a critical task for content creators to increase user engagement and reach larger audiences. Traditional user engagement prediction approaches rely solely on features derived from the user and content. However, a new class of deep learning methods based on graphs captures not only the content features but also the graph structure of social media networks. This thesis proposes a novel Graph Neural Network (GNN) approach to predict user interaction with tweets. The proposed approach combines the features of users, tweets and their engagement graphs. The tweet text features are extracted using pre-trained embeddings from language models, and a GNN layer is used to embed the user in a vector space. The GNN model then combines the features and graph structure to predict user engagement. The proposed approach achieves an accuracy value of 94.22\% in classifying user interactions, including likes, retweets, replies, and quotes. Another major challenge in social media analysis is detecting and classifying social bot accounts. Social bots are automated accounts used to manipulate public opinion by spreading misinformation or generating fake interactions. Detecting social bots is critical to prevent their negative impact on public opinion and trust in social media. In this thesis, we classify social bots on Twitter by applying Graph Neural Networks. The proposed approach uses a combination of both the features of a node and an aggregation of the features of a node's neighborhood to classify social bot accounts. Our final results indicate a 6\% improvement in the area under the curve score in the final predictions through the utilization of GNN. Overall, our work highlights the importance of social media data and the potential of new methods such as GNNs to predict user engagement and detect social bots. These methods have important implications for improving the quality and reliability of information on social media platforms and mitigating the negative impact of social bots on public opinion and discourse.}, language = {en} } @article{TopaliChountaOrtegaArranzetal.2021, author = {Topali, Paraskevi and Chounta, Irene-Angelica and Ortega-Arranz, Alejandro and Villagr{\´a}-Sobrino, Sara L. and Mart{\´i}nez-Mon{\´e}s, Alejandra}, title = {CoFeeMOOC-v.2}, series = {EMOOCs 2021}, volume = {2021}, journal = {EMOOCs 2021}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51724}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-517241}, pages = {209 -- 217}, year = {2021}, abstract = {Providing adequate support to MOOC participants is often a challenging task due to massiveness of the learners' population and the asynchronous communication among peers and MOOC practitioners. This workshop aims at discussing common learners' problems reported in the literature and reflect on designing adequate feedback interventions with the use of learning data. Our aim is three-fold: a) to pinpoint MOOC aspects that impact the planning of feedback, b) to explore the use of learning data in designing feedback strategies, and c) to propose design guidelines for developing and delivering scaffolding interventions for personalized feedback in MOOCs. To do so, we will carry out hands-on activities that aim to involve participants in interpreting learning data and using them to design adaptive feedback. This workshop appeals to researchers, practitioners and MOOC stakeholders who aim to providing contextualized scaffolding. We envision that this workshop will provide insights for bridging the gap between pedagogical theory and practice when it comes to feedback interventions in MOOCs.}, language = {en} } @phdthesis{Quinzan2023, author = {Quinzan, Francesco}, title = {Combinatorial problems and scalability in artificial intelligence}, doi = {10.25932/publishup-61111}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-611114}, school = {Universit{\"a}t Potsdam}, pages = {xi, 141}, year = {2023}, abstract = {Modern datasets often exhibit diverse, feature-rich, unstructured data, and they are massive in size. This is the case of social networks, human genome, and e-commerce databases. As Artificial Intelligence (AI) systems are increasingly used to detect pattern in data and predict future outcome, there are growing concerns on their ability to process large amounts of data. Motivated by these concerns, we study the problem of designing AI systems that are scalable to very large and heterogeneous data-sets. Many AI systems require to solve combinatorial optimization problems in their course of action. These optimization problems are typically NP-hard, and they may exhibit additional side constraints. However, the underlying objective functions often exhibit additional properties. These properties can be exploited to design suitable optimization algorithms. One of these properties is the well-studied notion of submodularity, which captures diminishing returns. Submodularity is often found in real-world applications. Furthermore, many relevant applications exhibit generalizations of this property. In this thesis, we propose new scalable optimization algorithms for combinatorial problems with diminishing returns. Specifically, we focus on three problems, the Maximum Entropy Sampling problem, Video Summarization, and Feature Selection. For each problem, we propose new algorithms that work at scale. These algorithms are based on a variety of techniques, such as forward step-wise selection and adaptive sampling. Our proposed algorithms yield strong approximation guarantees, and the perform well experimentally. We first study the Maximum Entropy Sampling problem. This problem consists of selecting a subset of random variables from a larger set, that maximize the entropy. By using diminishing return properties, we develop a simple forward step-wise selection optimization algorithm for this problem. Then, we study the problem of selecting a subset of frames, that represent a given video. Again, this problem corresponds to a submodular maximization problem. We provide a new adaptive sampling algorithm for this problem, suitable to handle the complex side constraints imposed by the application. We conclude by studying Feature Selection. In this case, the underlying objective functions generalize the notion of submodularity. We provide a new adaptive sequencing algorithm for this problem, based on the Orthogonal Matching Pursuit paradigm. Overall, we study practically relevant combinatorial problems, and we propose new algorithms to solve them. We demonstrate that these algorithms are suitable to handle massive datasets. However, our analysis is not problem-specific, and our results can be applied to other domains, if diminishing return properties hold. We hope that the flexibility of our framework inspires further research into scalability in AI.}, language = {en} } @book{MaximovaSchneiderGiese2020, author = {Maximova, Maria and Schneider, Sven and Giese, Holger}, title = {Compositional analysis of probabilistic timed graph transformation systems}, number = {133}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-501-9}, issn = {1613-5652}, doi = {10.25932/publishup-49013}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-490131}, publisher = {Universit{\"a}t Potsdam}, pages = {53}, year = {2020}, abstract = {The analysis of behavioral models is of high importance for cyber-physical systems, as the systems often encompass complex behavior based on e.g. concurrent components with mutual exclusion or probabilistic failures on demand. The rule-based formalism of probabilistic timed graph transformation systems is a suitable choice when the models representing states of the system can be understood as graphs and timed and probabilistic behavior is important. However, model checking PTGTSs is limited to systems with rather small state spaces. We present an approach for the analysis of large scale systems modeled as probabilistic timed graph transformation systems by systematically decomposing their state spaces into manageable fragments. To obtain qualitative and quantitative analysis results for a large scale system, we verify that results obtained for its fragments serve as overapproximations for the corresponding results of the large scale system. Hence, our approach allows for the detection of violations of qualitative and quantitative safety properties for the large scale system under analysis. We consider a running example in which we model shuttles driving on tracks of a large scale topology and for which we verify that shuttles never collide and are unlikely to execute emergency brakes. In our evaluation, we apply an implementation of our approach to the running example.}, language = {en} } @misc{Perscheid2021, author = {Perscheid, Cindy}, title = {Comprior: facilitating the implementation and automated benchmarking of prior knowledge-based feature selection approaches on gene expression data sets}, series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, journal = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-54894}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-548943}, pages = {1 -- 15}, year = {2021}, abstract = {Background Reproducible benchmarking is important for assessing the effectiveness of novel feature selection approaches applied on gene expression data, especially for prior knowledge approaches that incorporate biological information from online knowledge bases. However, no full-fledged benchmarking system exists that is extensible, provides built-in feature selection approaches, and a comprehensive result assessment encompassing classification performance, robustness, and biological relevance. Moreover, the particular needs of prior knowledge feature selection approaches, i.e. uniform access to knowledge bases, are not addressed. As a consequence, prior knowledge approaches are not evaluated amongst each other, leaving open questions regarding their effectiveness. Results We present the Comprior benchmark tool, which facilitates the rapid development and effortless benchmarking of feature selection approaches, with a special focus on prior knowledge approaches. Comprior is extensible by custom approaches, offers built-in standard feature selection approaches, enables uniform access to multiple knowledge bases, and provides a customizable evaluation infrastructure to compare multiple feature selection approaches regarding their classification performance, robustness, runtime, and biological relevance. Conclusion Comprior allows reproducible benchmarking especially of prior knowledge approaches, which facilitates their applicability and for the first time enables a comprehensive assessment of their effectiveness}, language = {en} } @phdthesis{Limberger2024, author = {Limberger, Daniel}, title = {Concepts and techniques for 3D-embedded treemaps and their application to software visualization}, doi = {10.25932/publishup-63201}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-632014}, school = {Universit{\"a}t Potsdam}, pages = {xi, 118}, year = {2024}, abstract = {This thesis addresses concepts and techniques for interactive visualization of hierarchical data using treemaps. It explores (1) how treemaps can be embedded in 3D space to improve their information content and expressiveness, (2) how the readability of treemaps can be improved using level-of-detail and degree-of-interest techniques, and (3) how to design and implement a software framework for the real-time web-based rendering of treemaps embedded in 3D. With a particular emphasis on their application, use cases from software analytics are taken to test and evaluate the presented concepts and techniques. Concerning the first challenge, this thesis shows that a 3D attribute space offers enhanced possibilities for the visual mapping of data compared to classical 2D treemaps. In particular, embedding in 3D allows for improved implementation of visual variables (e.g., by sketchiness and color weaving), provision of new visual variables (e.g., by physically based materials and in situ templates), and integration of visual metaphors (e.g., by reference surfaces and renderings of natural phenomena) into the three-dimensional representation of treemaps. For the second challenge—the readability of an information visualization—the work shows that the generally higher visual clutter and increased cognitive load typically associated with three-dimensional information representations can be kept low in treemap-based representations of both small and large hierarchical datasets. By introducing an adaptive level-of-detail technique, we cannot only declutter the visualization results, thereby reducing cognitive load and mitigating occlusion problems, but also summarize and highlight relevant data. Furthermore, this approach facilitates automatic labeling, supports the emphasis on data outliers, and allows visual variables to be adjusted via degree-of-interest measures. The third challenge is addressed by developing a real-time rendering framework with WebGL and accumulative multi-frame rendering. The framework removes hardware constraints and graphics API requirements, reduces interaction response times, and simplifies high-quality rendering. At the same time, the implementation effort for a web-based deployment of treemaps is kept reasonable. The presented visualization concepts and techniques are applied and evaluated for use cases in software analysis. In this domain, data about software systems, especially about the state and evolution of the source code, does not have a descriptive appearance or natural geometric mapping, making information visualization a key technology here. In particular, software source code can be visualized with treemap-based approaches because of its inherently hierarchical structure. With treemaps embedded in 3D, we can create interactive software maps that visually map, software metrics, software developer activities, or information about the evolution of software systems alongside their hierarchical module structure. Discussions on remaining challenges and opportunities for future research for 3D-embedded treemaps and their applications conclude the thesis.}, language = {en} } @phdthesis{Richter2018, author = {Richter, Rico}, title = {Concepts and techniques for processing and rendering of massive 3D point clouds}, doi = {10.25932/publishup-42330}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-423304}, school = {Universit{\"a}t Potsdam}, pages = {v, 131}, year = {2018}, abstract = {Remote sensing technology, such as airborne, mobile, or terrestrial laser scanning, and photogrammetric techniques, are fundamental approaches for efficient, automatic creation of digital representations of spatial environments. For example, they allow us to generate 3D point clouds of landscapes, cities, infrastructure networks, and sites. As essential and universal category of geodata, 3D point clouds are used and processed by a growing number of applications, services, and systems such as in the domains of urban planning, landscape architecture, environmental monitoring, disaster management, virtual geographic environments as well as for spatial analysis and simulation. While the acquisition processes for 3D point clouds become more and more reliable and widely-used, applications and systems are faced with more and more 3D point cloud data. In addition, 3D point clouds, by their very nature, are raw data, i.e., they do not contain any structural or semantics information. Many processing strategies common to GIS such as deriving polygon-based 3D models generally do not scale for billions of points. GIS typically reduce data density and precision of 3D point clouds to cope with the sheer amount of data, but that results in a significant loss of valuable information at the same time. This thesis proposes concepts and techniques designed to efficiently store and process massive 3D point clouds. To this end, object-class segmentation approaches are presented to attribute semantics to 3D point clouds, used, for example, to identify building, vegetation, and ground structures and, thus, to enable processing, analyzing, and visualizing 3D point clouds in a more effective and efficient way. Similarly, change detection and updating strategies for 3D point clouds are introduced that allow for reducing storage requirements and incrementally updating 3D point cloud databases. In addition, this thesis presents out-of-core, real-time rendering techniques used to interactively explore 3D point clouds and related analysis results. All techniques have been implemented based on specialized spatial data structures, out-of-core algorithms, and GPU-based processing schemas to cope with massive 3D point clouds having billions of points. All proposed techniques have been evaluated and demonstrated their applicability to the field of geospatial applications and systems, in particular for tasks such as classification, processing, and visualization. Case studies for 3D point clouds of entire cities with up to 80 billion points show that the presented approaches open up new ways to manage and apply large-scale, dense, and time-variant 3D point clouds as required by a rapidly growing number of applications and systems.}, language = {en} } @article{BeirneNicGiollaMhichilBrownetal.2021, author = {Beirne, Elaine and Nic Giolla Mhich{\´i}l, Mair{\´e}ad and Brown, Mark and Mac Lochlainn, Conch{\´u}r}, title = {Confidence Counts}, series = {EMOOCs 2021}, volume = {2021}, journal = {EMOOCs 2021}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51722}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-517220}, pages = {201 -- 208}, year = {2021}, abstract = {The increasing reliance on online learning in higher education has been further expedited by the on-going Covid-19 pandemic. Students need to be supported as they adapt to this new learning environment. Research has established that learners with positive online learning self-efficacy beliefs are more likely to persevere and achieve their higher education goals when learning online. In this paper, we explore how MOOC design can contribute to the four sources of self-efficacy beliefs posited by Bandura [4]. Specifically, we will explore, drawing on learner reflections, whether design elements of the MOOC, The Digital Edge: Essentials for the Online Learner, provided participants with the necessary mastery experiences, vicarious experiences, verbal persuasion, and affective regulation opportunities, to evaluate and develop their online learning self-efficacy beliefs. Findings from a content analysis of discussion forum posts show that learners referenced three of the four information sources when reflecting on their experience of the MOOC. This paper illustrates the potential of MOOCs as a pedagogical tool for enhancing online learning self-efficacy among students.}, language = {en} } @misc{SoechtingTrapp2020, author = {S{\"o}chting, Maximilian and Trapp, Matthias}, title = {Controlling image-stylization techniques using eye tracking}, series = {Postprints der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, journal = {Postprints der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, number = {7}, doi = {10.25932/publishup-52471}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-524717}, pages = {12}, year = {2020}, abstract = {With the spread of smart phones capable of taking high-resolution photos and the development of high-speed mobile data infrastructure, digital visual media is becoming one of the most important forms of modern communication. With this development, however, also comes a devaluation of images as a media form with the focus becoming the frequency at which visual content is generated instead of the quality of the content. In this work, an interactive system using image-abstraction techniques and an eye tracking sensor is presented, which allows users to experience diverting and dynamic artworks that react to their eye movement. The underlying modular architecture enables a variety of different interaction techniques that share common design principles, making the interface as intuitive as possible. The resulting experience allows users to experience a game-like interaction in which they aim for a reward, the artwork, while being held under constraints, e.g., not blinking. The co nscious eye movements that are required by some interaction techniques hint an interesting, possible future extension for this work into the field of relaxation exercises and concentration training.}, language = {en} } @phdthesis{Koumarelas2020, author = {Koumarelas, Ioannis}, title = {Data preparation and domain-agnostic duplicate detection}, doi = {10.25932/publishup-48913}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-489131}, school = {Universit{\"a}t Potsdam}, pages = {x, 97}, year = {2020}, abstract = {Successfully completing any data science project demands careful consideration across its whole process. Although the focus is often put on later phases of the process, in practice, experts spend more time in earlier phases, preparing data, to make them consistent with the systems' requirements or to improve their models' accuracies. Duplicate detection is typically applied during the data cleaning phase, which is dedicated to removing data inconsistencies and improving the overall quality and usability of data. While data cleaning involves a plethora of approaches to perform specific operations, such as schema alignment and data normalization, the task of detecting and removing duplicate records is particularly challenging. Duplicates arise when multiple records representing the same entities exist in a database. Due to numerous reasons, spanning from simple typographical errors to different schemas and formats of integrated databases. Keeping a database free of duplicates is crucial for most use-cases, as their existence causes false negatives and false positives when matching queries against it. These two data quality issues have negative implications for tasks, such as hotel booking, where users may erroneously select a wrong hotel, or parcel delivery, where a parcel can get delivered to the wrong address. Identifying the variety of possible data issues to eliminate duplicates demands sophisticated approaches. While research in duplicate detection is well-established and covers different aspects of both efficiency and effectiveness, our work in this thesis focuses on the latter. We propose novel approaches to improve data quality before duplicate detection takes place and apply the latter in datasets even when prior labeling is not available. Our experiments show that improving data quality upfront can increase duplicate classification results by up to 19\%. To this end, we propose two novel pipelines that select and apply generic as well as address-specific data preparation steps with the purpose of maximizing the success of duplicate detection. Generic data preparation, such as the removal of special characters, can be applied to any relation with alphanumeric attributes. When applied, data preparation steps are selected only for attributes where there are positive effects on pair similarities, which indirectly affect classification, or on classification directly. Our work on addresses is twofold; first, we consider more domain-specific approaches to improve the quality of values, and, second, we experiment with known and modified versions of similarity measures to select the most appropriate per address attribute, e.g., city or country. To facilitate duplicate detection in applications where gold standard annotations are not available and obtaining them is not possible or too expensive, we propose MDedup. MDedup is a novel, rule-based, and fully automatic duplicate detection approach that is based on matching dependencies. These dependencies can be used to detect duplicates and can be discovered using state-of-the-art algorithms efficiently and without any prior labeling. MDedup uses two pipelines to first train on datasets with known labels, learning to identify useful matching dependencies, and then be applied on unseen datasets, regardless of any existing gold standard. Finally, our work is accompanied by open source code to enable repeatability of our research results and application of our approaches to other datasets.}, language = {en} } @phdthesis{Papenbrock2017, author = {Papenbrock, Thorsten}, title = {Data profiling - efficient discovery of dependencies}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-406705}, school = {Universit{\"a}t Potsdam}, pages = {viii, ii, 141}, year = {2017}, abstract = {Data profiling is the computer science discipline of analyzing a given dataset for its metadata. The types of metadata range from basic statistics, such as tuple counts, column aggregations, and value distributions, to much more complex structures, in particular inclusion dependencies (INDs), unique column combinations (UCCs), and functional dependencies (FDs). If present, these statistics and structures serve to efficiently store, query, change, and understand the data. Most datasets, however, do not provide their metadata explicitly so that data scientists need to profile them. While basic statistics are relatively easy to calculate, more complex structures present difficult, mostly NP-complete discovery tasks; even with good domain knowledge, it is hardly possible to detect them manually. Therefore, various profiling algorithms have been developed to automate the discovery. None of them, however, can process datasets of typical real-world size, because their resource consumptions and/or execution times exceed effective limits. In this thesis, we propose novel profiling algorithms that automatically discover the three most popular types of complex metadata, namely INDs, UCCs, and FDs, which all describe different kinds of key dependencies. The task is to extract all valid occurrences from a given relational instance. The three algorithms build upon known techniques from related work and complement them with algorithmic paradigms, such as divide \& conquer, hybrid search, progressivity, memory sensitivity, parallelization, and additional pruning to greatly improve upon current limitations. Our experiments show that the proposed algorithms are orders of magnitude faster than related work. They are, in particular, now able to process datasets of real-world, i.e., multiple gigabytes size with reasonable memory and time consumption. Due to the importance of data profiling in practice, industry has built various profiling tools to support data scientists in their quest for metadata. These tools provide good support for basic statistics and they are also able to validate individual dependencies, but they lack real discovery features even though some fundamental discovery techniques are known for more than 15 years. To close this gap, we developed Metanome, an extensible profiling platform that incorporates not only our own algorithms but also many further algorithms from other researchers. With Metanome, we make our research accessible to all data scientists and IT-professionals that are tasked with data profiling. Besides the actual metadata discovery, the platform also offers support for the ranking and visualization of metadata result sets. Being able to discover the entire set of syntactically valid metadata naturally introduces the subsequent task of extracting only the semantically meaningful parts. This is challenge, because the complete metadata results are surprisingly large (sometimes larger than the datasets itself) and judging their use case dependent semantic relevance is difficult. To show that the completeness of these metadata sets is extremely valuable for their usage, we finally exemplify the efficient processing and effective assessment of functional dependencies for the use case of schema normalization.}, language = {en} } @phdthesis{Taeumel2020, author = {Taeumel, Marcel}, title = {Data-driven tool construction in exploratory programming environments}, doi = {10.25932/publishup-44428}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-444289}, school = {Universit{\"a}t Potsdam}, pages = {xiv, 299}, year = {2020}, abstract = {This work presents a new design for programming environments that promote the exploration of domain-specific software artifacts and the construction of graphical tools for such program comprehension tasks. In complex software projects, tool building is essential because domain- or task-specific tools can support decision making by representing concerns concisely with low cognitive effort. In contrast, generic tools can only support anticipated scenarios, which usually align with programming language concepts or well-known project domains. However, the creation and modification of interactive tools is expensive because the glue that connects data to graphics is hard to find, change, and test. Even if valuable data is available in a common format and even if promising visualizations could be populated, programmers have to invest many resources to make changes in the programming environment. Consequently, only ideas of predictably high value will be implemented. In the non-graphical, command-line world, the situation looks different and inspiring: programmers can easily build their own tools as shell scripts by configuring and combining filter programs to process data. We propose a new perspective on graphical tools and provide a concept to build and modify such tools with a focus on high quality, low effort, and continuous adaptability. That is, (1) we propose an object-oriented, data-driven, declarative scripting language that reduces the amount of and governs the effects of glue code for view-model specifications, and (2) we propose a scalable UI-design language that promotes short feedback loops in an interactive, graphical environment such as Morphic known from Self or Squeak/Smalltalk systems. We implemented our concept as a tool building environment, which we call VIVIDE, on top of Squeak/Smalltalk and Morphic. We replaced existing code browsing and debugging tools to iterate within our solution more quickly. In several case studies with undergraduate and graduate students, we observed that VIVIDE can be applied to many domains such as live language development, source-code versioning, modular code browsing, and multi-language debugging. Then, we designed a controlled experiment to measure the effect on the time to build tools. Several pilot runs showed that training is crucial and, presumably, takes days or weeks, which implies a need for further research. As a result, programmers as users can directly work with tangible representations of their software artifacts in the VIVIDE environment. Tool builders can write domain-specific scripts to populate views to approach comprehension tasks from different angles. Our novel perspective on graphical tools can inspire the creation of new trade-offs in modularity for both data providers and view designers.}, language = {en} } @book{BartzKrestel2021, author = {Bartz, Christian and Krestel, Ralf}, title = {Deep learning for computer vision in the art domain}, number = {139}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-514-9}, issn = {1613-5652}, doi = {10.25932/publishup-51290}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-512906}, publisher = {Universit{\"a}t Potsdam}, pages = {vii, 79}, year = {2021}, abstract = {In recent years, computer vision algorithms based on machine learning have seen rapid development. In the past, research mostly focused on solving computer vision problems such as image classification or object detection on images displaying natural scenes. Nowadays other fields such as the field of cultural heritage, where an abundance of data is available, also get into the focus of research. In the line of current research endeavours, we collaborated with the Getty Research Institute which provided us with a challenging dataset, containing images of paintings and drawings. In this technical report, we present the results of the seminar "Deep Learning for Computer Vision". In this seminar, students of the Hasso Plattner Institute evaluated state-of-the-art approaches for image classification, object detection and image recognition on the dataset of the Getty Research Institute. The main challenge when applying modern computer vision methods to the available data is the availability of annotated training data, as the dataset provided by the Getty Research Institute does not contain a sufficient amount of annotated samples for the training of deep neural networks. However, throughout the report we show that it is possible to achieve satisfying to very good results, when using further publicly available datasets, such as the WikiArt dataset, for the training of machine learning models.}, language = {en} } @phdthesis{Rezaei2019, author = {Rezaei, Mina}, title = {Deep representation learning from imbalanced medical imaging}, doi = {10.25932/publishup-44275}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-442759}, school = {Universit{\"a}t Potsdam}, pages = {xxviii, 160}, year = {2019}, abstract = {Medical imaging plays an important role in disease diagnosis, treatment planning, and clinical monitoring. One of the major challenges in medical image analysis is imbalanced training data, in which the class of interest is much rarer than the other classes. Canonical machine learning algorithms suppose that the number of samples from different classes in the training dataset is roughly similar or balance. Training a machine learning model on an imbalanced dataset can introduce unique challenges to the learning problem. A model learned from imbalanced training data is biased towards the high-frequency samples. The predicted results of such networks have low sensitivity and high precision. In medical applications, the cost of misclassification of the minority class could be more than the cost of misclassification of the majority class. For example, the risk of not detecting a tumor could be much higher than referring to a healthy subject to a doctor. The current Ph.D. thesis introduces several deep learning-based approaches for handling class imbalanced problems for learning multi-task such as disease classification and semantic segmentation. At the data-level, the objective is to balance the data distribution through re-sampling the data space: we propose novel approaches to correct internal bias towards fewer frequency samples. These approaches include patient-wise batch sampling, complimentary labels, supervised and unsupervised minority oversampling using generative adversarial networks for all. On the other hand, at algorithm-level, we modify the learning algorithm to alleviate the bias towards majority classes. In this regard, we propose different generative adversarial networks for cost-sensitive learning, ensemble learning, and mutual learning to deal with highly imbalanced imaging data. We show evidence that the proposed approaches are applicable to different types of medical images of varied sizes on different applications of routine clinical tasks, such as disease classification and semantic segmentation. Our various implemented algorithms have shown outstanding results on different medical imaging challenges.}, language = {en} } @misc{ZieglerPfitznerSchulzetal.2022, author = {Ziegler, Joceline and Pfitzner, Bjarne and Schulz, Heinrich and Saalbach, Axel and Arnrich, Bert}, title = {Defending against Reconstruction Attacks through Differentially Private Federated Learning for Classification of Heterogeneous Chest X-ray Data}, series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, journal = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, number = {14}, doi = {10.25932/publishup-58132}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-581322}, pages = {25}, year = {2022}, abstract = {Privacy regulations and the physical distribution of heterogeneous data are often primary concerns for the development of deep learning models in a medical context. This paper evaluates the feasibility of differentially private federated learning for chest X-ray classification as a defense against data privacy attacks. To the best of our knowledge, we are the first to directly compare the impact of differentially private training on two different neural network architectures, DenseNet121 and ResNet50. Extending the federated learning environments previously analyzed in terms of privacy, we simulated a heterogeneous and imbalanced federated setting by distributing images from the public CheXpert and Mendeley chest X-ray datasets unevenly among 36 clients. Both non-private baseline models achieved an area under the receiver operating characteristic curve (AUC) of 0.940.94 on the binary classification task of detecting the presence of a medical finding. We demonstrate that both model architectures are vulnerable to privacy violation by applying image reconstruction attacks to local model updates from individual clients. The attack was particularly successful during later training stages. To mitigate the risk of a privacy breach, we integrated R{\´e}nyi differential privacy with a Gaussian noise mechanism into local model training. We evaluate model performance and attack vulnerability for privacy budgets ε∈{1,3,6,10}�∈{1,3,6,10}. The DenseNet121 achieved the best utility-privacy trade-off with an AUC of 0.940.94 for ε=6�=6. Model performance deteriorated slightly for individual clients compared to the non-private baseline. The ResNet50 only reached an AUC of 0.760.76 in the same privacy setting. Its performance was inferior to that of the DenseNet121 for all considered privacy constraints, suggesting that the DenseNet121 architecture is more robust to differentially private training.}, language = {en} } @article{GiannatelliTomasini2023, author = {Giannatelli, Ada and Tomasini, Alessandra}, title = {Descriptors and EU Standards to support the recognition of MOOCs}, series = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, journal = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, editor = {Meinel, Christoph and Schweiger, Stefanie and Staubitz, Thomas and Conrad, Robert and Alario Hoyos, Carlos and Ebner, Martin and Sancassani, Susanna and Żur, Agnieszka and Friedl, Christian and Halawa, Sherif and Gamage, Dilrukshi and Scott, Jeffrey and Kristine Jonson Carlon, May and Deville, Yves and Gaebel, Michael and Delgado Kloos, Carlos and von Schmieden, Karen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-62396}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-623967}, pages = {133 -- 146}, year = {2023}, abstract = {Digital technologies have enabled a variety of learning offers that opened new challenges in terms of recognition of formal, informal and non-formal learning, such as MOOCs. This paper focuses on how providing relevant data to describe a MOOC is conducive to increase the transparency of information and, ultimately, the flexibility of European higher education. The EU-funded project ECCOE took up these challenges and developed a solution by identifying the most relevant descriptors of a learning opportunity with a view to supporting a European system for micro-credentials. Descriptors indicate the specific properties of a learning opportunity according to European standards. They can provide a recognition framework also for small volumes of learning (micro-credentials) to support the integration of non-formal learning (MOOCs) into formal learning (e.g. institutional university courses) and to tackle skills shortage, upskilling and reskilling by acquiring relevant competencies. The focus on learning outcomes can facilitate the recognition of skills and competences of students and enhance both virtual and physical mobility and employability. This paper presents two contexts where ECCOE descriptors have been adopted: the Politecnico di Milano MOOC platform (Polimi Open Knowledge - POK), which is using these descriptors as the standard information to document the features of its learning opportunities, and the EU-funded Uforest project on urban forestry, which developed a blended training program for students of partner universities whose MOOCs used the ECCOE descriptors. Practice with ECCOE descriptors shows how they can be used not only to detail MOOC features, but also as a compass to design the learning offer. In addition, some rules of thumb can be derived and applied when using specific descriptors.}, language = {en} } @phdthesis{Traifeh2023, author = {Traifeh, Hanadi}, title = {Design Thinking in the Arab world}, doi = {10.25932/publishup-59891}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-598911}, school = {Universit{\"a}t Potsdam}, pages = {ix, 196}, year = {2023}, abstract = {Design Thinking is a human-centered approach to innovation that has become increasingly popular globally over the last decade. While the spread of Design Thinking is well understood and documented in the Western cultural contexts, particularly in Europe and the US due to the popularity of the Stanford-Potsdam Design Thinking education model, this is not the case when it comes to non-Western cultural contexts. This thesis fills a gap identified in the literature regarding how Design Thinking emerged, was perceived, adopted, and practiced in the Arab world. The culture in that part of the world differs from that of the Western context, which impacts the mindset of people and how they interact with Design Thinking tools and methods. A mixed-methods research approach was followed in which both quantitative and qualitative methods were employed. First, two methods were used in the quantitative phase: a social media analysis using Twitter as a source of data, and an online questionnaire. The results and analysis of the quantitative data informed the design of the qualitative phase in which two methods were employed: ten semi-structured interviews, and participant observation of seven Design Thinking training events. According to the analyzed data, the Arab world appears to have had an early, though relatively weak, and slow, adoption of Design Thinking since 2006. Increasing adoption, however, has been witnessed over the last decade, especially in Saudi Arabia, the United Arab Emirates and Egypt. The results also show that despite its limited spread, Design Thinking has been practiced the most in education, information technology and communication, administrative services, and the non-profit sectors. The way it is being practiced, though, is not fully aligned with how it is being practiced and taught in the US and Europe, as most people in the region do not necessarily believe in all mindset attributes introduced by the Stanford-Potsdam tradition. Practitioners in the Arab world also seem to shy away from the 'wild side' of Design Thinking in particular, and do not fully appreciate the connection between art-design, and science-engineering. This questions the role of the educational institutions in the region since -according to the findings- they appear to be leading the movement in promoting and developing Design Thinking in the Arab world. Nonetheless, it is notable that people seem to be aware of the positive impact of applying Design Thinking in the region, and its potential to bring meaningful transformation. However, they also seem to be concerned about the current cultural, social, political, and economic challenges that may challenge this transformation. Therefore, they call for more awareness and demand to create Arabic, culturally appropriate programs to respond to the local needs. On another note, the lack of Arabic content and local case studies on Design Thinking were identified by several interviewees and were also confirmed by the participant observation as major challenges that are slowing down the spread of Design Thinking or sometimes hampering capacity building in the region. Other challenges that were revealed by the study are: changing the mindset of people, the lack of dedicated Design Thinking spaces, and the need for clear instructions on how to apply Design Thinking methods and activities. The concept of time and how Arabs deal with it, gender management during trainings, and hierarchy and power dynamics among training participants are also among the identified challenges. Another key finding revealed by the study is the confirmation of التفكير التصميمي as the Arabic term to be most widely adopted in the region to refer to Design Thinking, since four other Arabic terms were found to be associated with Design Thinking. Based on the findings of the study, the thesis concludes by presenting a list of recommendations on how to overcome the mentioned challenges and what factors should be considered when designing and implementing culturally-customized Design Thinking training in the Arab region.}, language = {en} } @book{GerkenUebernickeldePaula2022, author = {Gerken, Stefanie and Uebernickel, Falk and de Paula, Danielly}, title = {Design Thinking: a Global Study on Implementation Practices in Organizations}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-525-5}, doi = {10.25932/publishup-53466}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-534668}, publisher = {Universit{\"a}t Potsdam}, pages = {230}, year = {2022}, abstract = {These days design thinking is no longer a "new approach". Among practitioners, as well as academics, interest in the topic has gathered pace over the last two decades. However, opinions are divided over the longevity of the phenomenon: whether design thinking is merely "old wine in new bottles," a passing trend, or still evolving as it is being spread to an increasing number of organizations and industries. Despite its growing relevance and the diffusion of design thinking, knowledge on the actual status quo in organizations remains scarce. With a new study, the research team of Prof. Uebernickel and Stefanie Gerken investigates temporal developments and changes in design thinking practices in organizations over the past six years comparing the results of the 2015 "Parts without a whole" study with current practices and future developments. Companies of all sizes and from different parts of the world participated in the survey. The findings from qualitative interviews with experts, i.e., people who have years of knowledge with design thinking, were cross-checked with the results from an exploratory analysis of the survey data. This analysis uncovers significant variances and similarities in how design thinking is interpreted and applied in businesses.}, language = {en} } @phdthesis{Santuber2023, author = {Santuber, Joaquin}, title = {Designing for digital justice}, doi = {10.25932/publishup-60417}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-604178}, school = {Universit{\"a}t Potsdam}, pages = {xviii, 183}, year = {2023}, abstract = {At the beginning of 2020, with COVID-19, courts of justice worldwide had to move online to continue providing judicial service. Digital technologies materialized the court practices in ways unthinkable shortly before the pandemic creating resonances with judicial and legal regulation, as well as frictions. A better understanding of the dynamics at play in the digitalization of courts is paramount for designing justice systems that serve their users better, ensure fair and timely dispute resolutions, and foster access to justice. Building on three major bodies of literature —e-justice, digitalization and organization studies, and design research— Designing for Digital Justice takes a nuanced approach to account for human and more-than-human agencies. Using a qualitative approach, I have studied in depth the digitalization of Chilean courts during the pandemic, specifically between April 2020 and September 2022. Leveraging a comprehensive source of primary and secondary data, I traced back the genealogy of the novel materializations of courts' practices structured by the possibilities offered by digital technologies. In five (5) cases studies, I show in detail how the courts got to 1) work remotely, 2) host hearings via videoconference, 3) engage with users via social media (i.e., Facebook and Chat Messenger), 4) broadcast a show with judges answering questions from users via Facebook Live, and 5) record, stream, and upload judicial hearings to YouTube to fulfil the publicity requirement of criminal hearings. The digitalization of courts during the pandemic is characterized by a suspended normativity, which makes innovation possible yet presents risks. While digital technologies enabled the judiciary to provide services continuously, they also created the risk of displacing traditional judicial and legal regulation. Contributing to liminal innovation and digitalization research, Designing for Digital Justice theorizes four phases: 1) the pre-digitalization phase resulting in the development of regulation, 2) the hotspot of digitalization resulting in the extension of regulation, 3) the digital innovation redeveloping regulation (moving to a new, preliminary phase), and 4) the permanence of temporal practices displacing regulation. Contributing to design research Designing for Digital Justice provides new possibilities for innovation in the courts, focusing at different levels to better address tensions generated by digitalization. Fellow researchers will find in these pages a sound theoretical advancement at the intersection of digitalization and justice with novel methodological references. Practitioners will benefit from the actionable governance framework Designing for Digital Justice Model, which provides three fields of possibilities for action to design better justice systems. Only by taking into account digital, legal, and social factors can we design better systems that promote access to justice, the rule of law, and, ultimately social peace.}, language = {en} } @book{MeinelRenzLuderichetal.2019, author = {Meinel, Christoph and Renz, Jan and Luderich, Matthias and Malyska, Vivien and Kaiser, Konstantin and Oberl{\"a}nder, Arne}, title = {Die HPI Schul-Cloud}, number = {125}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-453-1}, issn = {1613-5652}, doi = {10.25932/publishup-42306}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-423062}, publisher = {Universit{\"a}t Potsdam}, pages = {57}, year = {2019}, abstract = {Die digitale Transformation durchdringt alle gesellschaftlichen Ebenen und Felder, nicht zuletzt auch das Bildungssystem. Dieses ist auf die Ver{\"a}nderungen kaum vorbereitet und begegnet ihnen vor allem auf Basis des Eigenengagements seiner Lehrer*innen. Strukturelle Reaktionen auf den Mangel an qualitativ hochwertigen Fortbildungen, auf schlecht ausgestattete Unterrichtsr{\"a}ume und nicht professionell gewartete Computersysteme gibt es erst seit kurzem. Doch auch wenn Beharrungskr{\"a}fte unter P{\"a}dagog*innen verbreitet sind, erfordert die Transformation des Systems Schule auch eine neue Mentalit{\"a}t und neue Arbeits- und Kooperationsformen. Zeitgem{\"a}ßer Unterricht ben{\"o}tigt moderne Technologie und zeitgem{\"a}ße IT-Architekturen. Nur Systeme, die f{\"u}r Lehrer*innen und Sch{\"u}ler*innen problemlos verf{\"u}gbar, benutzerfreundlich zu bedienen und didaktisch flexibel einsetzbar sind, finden in Schulen Akzeptanz. Hierf{\"u}r haben wir die HPI Schul-Cloud entwickelt. Sie erm{\"o}glicht den einfachen Zugang zu neuesten, professionell gewarteten Anwendungen, verschiedensten digitalen Medien, die Vernetzung verschiedener Lernorte und den rechtssicheren Einsatz von Kommunikations- und Kollaborationstools. Die Entwicklung der HPI Schul-Cloud ist umso notwendiger, als dass rechtliche Anforderungen - insbesondere aus der Datenschutzgrundverordnung der EU herr{\"u}hrend - den Einsatz von Cloud-Anwendungen, die in der Arbeitswelt verbreitet sind, in Schulen unm{\"o}glich machen. Im Bildungsbereich verbreitete Anwendungen sind gr{\"o}ßtenteils technisch veraltet und nicht benutzerfreundlich. Dies n{\"o}tigt die Bundesl{\"a}nder zu kostspieligen Eigenentwicklungen mit Aufw{\"a}nden im zweistelligen Millionenbereich - Projekte die teilweise gescheitert sind. Dank der modularen Micro-Service-Architektur k{\"o}nnen die Bundesl{\"a}nder zuk{\"u}nftig auf die HPI Schul-Cloud als technische Grundlage f{\"u}r ihre Eigen- oder Gemeinschaftsprojekte zur{\"u}ckgreifen. Hierf{\"u}r gilt es, eine nachhaltige Struktur f{\"u}r die Weiterentwicklung der Open-Source-Software HPI Schul-Cloud zu schaffen. Dieser Bericht beschreibt den Entwicklungsstand und die weiteren Perspektiven des Projekts HPI Schul-Cloud im Januar 2019. 96 Schulen deutschlandweit nutzen die HPI Schul-Cloud, bereitgestellt durch das Hasso-Plattner-Institut. Weitere 45 Schulen und Studienseminare nutzen die Nieders{\"a}chsische Bildungscloud, die technisch auf der HPI Schul-Cloud basiert. Das vom Bundesministerium f{\"u}r Bildung und Forschung gef{\"o}rderte Projekt l{\"a}uft in der gegenw{\"a}rtigen Roll-Out-Phase bis zum 31. Juli 2021. Gemeinsam mit unserem Kooperationspartner MINT-EC streben wir an, die HPI Schul-Cloud m{\"o}glichst an allen Schulen des Netzwerks einzusetzen.}, language = {de} } @book{MeinelJohnWollowski2022, author = {Meinel, Christoph and John, Catrina and Wollowski, Tobias}, title = {Die HPI Schul-Cloud - Von der Vision zur digitale Infrastruktur f{\"u}r deutsche Schulen}, number = {144}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-526-2}, issn = {1613-5652}, doi = {10.25932/publishup-53586}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-535860}, publisher = {Universit{\"a}t Potsdam}, pages = {v, 77}, year = {2022}, abstract = {Digitale Medien sind aus unserem Alltag kaum noch wegzudenken. Einer der zentralsten Bereiche f{\"u}r unsere Gesellschaft, die schulische Bildung, darf hier nicht hintanstehen. Wann immer der Einsatz digital unterst{\"u}tzter Tools p{\"a}dagogisch sinnvoll ist, muss dieser in einem sicheren Rahmen erm{\"o}glicht werden k{\"o}nnen. Die HPI Schul-Cloud ist dieser Vision gefolgt, die vom Nationalen IT-Gipfel 2016 angestoßen wurde und dem Bericht vorangestellt ist - gefolgt. Sie hat sich in den vergangenen f{\"u}nf Jahren vom Pilotprojekt zur unverzichtbaren IT-Infrastruktur f{\"u}r zahlreiche Schulen entwickelt. W{\"a}hrend der Corona-Pandemie hat sie f{\"u}r viele Tausend Schulen wichtige Unterst{\"u}tzung bei der Umsetzung ihres Bildungsauftrags geboten. Das Ziel, eine zukunftssichere und datenschutzkonforme Infrastruktur zur digitalen Unterst{\"u}tzung des Unterrichts zur Verf{\"u}gung zu stellen, hat sie damit mehr als erreicht. Aktuell greifen rund 1,4 Millionen Lehrkr{\"a}fte und Sch{\"u}lerinnen und Sch{\"u}ler bundesweit und an den deutschen Auslandsschulen auf die HPI Schul-Cloud zu.}, language = {de} } @article{MihaescuAndoneVasiu2021, author = {Mihaescu, Vlad and Andone, Diana and Vasiu, Radu}, title = {DigiCulture MOOC Courses Piloting with Students}, series = {EMOOCs 2021}, volume = {2021}, journal = {EMOOCs 2021}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51733}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-517339}, pages = {275 -- 279}, year = {2021}, language = {en} } @phdthesis{Perlich2019, author = {Perlich, Anja}, title = {Digital collaborative documentation in mental healthcare}, doi = {10.25932/publishup-44029}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-440292}, school = {Universit{\"a}t Potsdam}, pages = {x, 135}, year = {2019}, abstract = {With the growth of information technology, patient attitudes are shifting - away from passively receiving care towards actively taking responsibility for their well- being. Handling doctor-patient relationships collaboratively and providing patients access to their health information are crucial steps in empowering patients. In mental healthcare, the implicit consensus amongst practitioners has been that sharing medical records with patients may have an unpredictable, harmful impact on clinical practice. In order to involve patients more actively in mental healthcare processes, Tele-Board MED (TBM) allows for digital collaborative documentation in therapist-patient sessions. The TBM software system offers a whiteboard-inspired graphical user interface that allows therapist and patient to jointly take notes during the treatment session. Furthermore, it provides features to automatically reuse the digital treatment session notes for the creation of treatment session summaries and clinical case reports. This thesis presents the development of the TBM system and evaluates its effects on 1) the fulfillment of the therapist's duties of clinical case documentation, 2) patient engagement in care processes, and 3) the therapist-patient relationship. Following the design research methodology, TBM was developed and tested in multiple evaluation studies in the domains of cognitive behavioral psychotherapy and addiction care. The results show that therapists are likely to use TBM with patients if they have a technology-friendly attitude and when its use suits the treatment context. Support in carrying out documentation duties as well as fulfilling legal requirements contributes to therapist acceptance. Furthermore, therapists value TBM as a tool to provide a discussion framework and quick access to worksheets during treatment sessions. Therapists express skepticism, however, regarding technology use in patient sessions and towards complete record transparency in general. Patients expect TBM to improve the communication with their therapist and to offer a better recall of discussed topics when taking a copy of their notes home after the session. Patients are doubtful regarding a possible distraction of the therapist and usage in situations when relationship-building is crucial. When applied in a clinical environment, collaborative note-taking with TBM encourages patient engagement and a team feeling between therapist and patient. Furthermore, it increases the patient's acceptance of their diagnosis, which in turn is an important predictor for therapy success. In summary, TBM has a high potential to deliver more than documentation support and record transparency for patients, but also to contribute to a collaborative doctor-patient relationship. This thesis provides design implications for the development of digital collaborative documentation systems in (mental) healthcare as well as recommendations for a successful implementation in clinical practice.}, language = {en} } @book{MeinelGalbasHageboelling2023, author = {Meinel, Christoph and Galbas, Michael and Hageb{\"o}lling, David}, title = {Digital sovereignty: insights from Germany's education sector}, number = {157}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-561-3}, issn = {1613-5652}, doi = {10.25932/publishup-59772}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-597723}, publisher = {Universit{\"a}t Potsdam}, pages = {1 -- 27}, year = {2023}, abstract = {Digital technology offers significant political, economic, and societal opportunities. At the same time, the notion of digital sovereignty has become a leitmotif in German discourse: the state's capacity to assume its responsibilities and safeguard society's - and individuals' - ability to shape the digital transformation in a self-determined way. The education sector is exemplary for the challenge faced by Germany, and indeed Europe, of harnessing the benefits of digital technology while navigating concerns around sovereignty. It encompasses education as a core public good, a rapidly growing field of business, and growing pools of highly sensitive personal data. The report describes pathways to mitigating the tension between digitalization and sovereignty at three different levels - state, economy, and individual - through the lens of concrete technical projects in the education sector: the HPI Schul-Cloud (state sovereignty), the MERLOT data spaces (economic sovereignty), and the openHPI platform (individual sovereignty).}, language = {en} } @phdthesis{Stojanovic2021, author = {Stojanovic, Vladeta}, title = {Digital twins for indoor built environments}, doi = {10.25932/publishup-50913}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-509134}, school = {Universit{\"a}t Potsdam}, pages = {xxiii, 181}, year = {2021}, abstract = {One of the key challenges in modern Facility Management (FM) is to digitally reflect the current state of the built environment, referred to as-is or as-built versus as-designed representation. While the use of Building Information Modeling (BIM) can address the issue of digital representation, the generation and maintenance of BIM data requires a considerable amount of manual work and domain expertise. Another key challenge is being able to monitor the current state of the built environment, which is used to provide feedback and enhance decision making. The need for an integrated solution for all data associated with the operational life cycle of a building is becoming more pronounced as practices from Industry 4.0 are currently being evaluated and adopted for FM use. This research presents an approach for digital representation of indoor environments in their current state within the life cycle of a given building. Such an approach requires the fusion of various sources of digital data. The key to solving such a complex issue of digital data integration, processing and representation is with the use of a Digital Twin (DT). A DT is a digital duplicate of the physical environment, states, and processes. A DT fuses as-designed and as-built digital representations of built environment with as-is data, typically in the form of floorplans, point clouds and BIMs, with additional information layers pertaining to the current and predicted states of an indoor environment or a complete building (e.g., sensor data). The design, implementation and initial testing of prototypical DT software services for indoor environments is presented and described. These DT software services are implemented within a service-oriented paradigm, and their feasibility is presented through functioning and tested key software components within prototypical Service-Oriented System (SOS) implementations. The main outcome of this research shows that key data related to the built environment can be semantically enriched and combined to enable digital representations of indoor environments, based on the concept of a DT. Furthermore, the outcomes of this research show that digital data, related to FM and Architecture, Construction, Engineering, Owner and Occupant (AECOO) activity, can be combined, analyzed and visualized in real-time using a service-oriented approach. This has great potential to benefit decision making related to Operation and Maintenance (O\&M) procedures within the scope of the post-construction life cycle stages of typical office buildings.}, language = {en} } @book{MeinelGalbasHageboelling2023, author = {Meinel, Christoph and Galbas, Michael and Hageb{\"o}lling, David}, title = {Digitale Souver{\"a}nit{\"a}t: Erkenntnisse aus dem deutschen Bildungssektor}, number = {156}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-560-6}, issn = {1613-5652}, doi = {10.25932/publishup-59513}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-595138}, publisher = {Universit{\"a}t Potsdam}, pages = {1 -- 29}, year = {2023}, abstract = {Digitale Technologien bieten erhebliche politische, wirtschaftliche und gesellschaftliche Chancen. Zugleich ist der Begriff digitale Souver{\"a}nit{\"a}t zu einem Leitmotiv im deutschen Diskurs {\"u}ber digitale Technologien geworden: das heißt, die F{\"a}higkeit des Staates, seine Verantwortung wahrzunehmen und die Bef{\"a}higung der Gesellschaft - und des Einzelnen - sicherzustellen, die digitale Transformation selbstbestimmt zu gestalten. Exemplarisch f{\"u}r die Herausforderung in Deutschland und Europa, die Vorteile digitaler Technologien zu nutzen und gleichzeitig Souver{\"a}nit{\"a}tsbedenken zu ber{\"u}cksichtigen, steht der Bildungssektor. Er umfasst Bildung als zentrales {\"o}ffentliches Gut, ein schnell aufkommendes Gesch{\"a}ftsfeld und wachsende Best{\"a}nde an hochsensiblen personenbezogenen Daten. Davon ausgehend beschreibt der Bericht Wege zur Entsch{\"a}rfung des Spannungsverh{\"a}ltnisses zwischen Digitalisierung und Souver{\"a}nit{\"a}t auf drei verschiedenen Ebenen - Staat, Wirtschaft und Individuum - anhand konkreter technischer Projekte im Bildungsbereich: die HPI Schul-Cloud (staatliche Souver{\"a}nit{\"a}t), die MERLOT-Datenr{\"a}ume (wirtschaftliche Souver{\"a}nit{\"a}t) und die openHPI-Plattform (individuelle Souver{\"a}nit{\"a}t).}, language = {de} } @phdthesis{Bano2023, author = {Bano, Dorina}, title = {Discovering data models from event logs}, doi = {10.25932/publishup-58542}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-585427}, school = {Universit{\"a}t Potsdam}, pages = {xvii, 137}, year = {2023}, abstract = {In the last two decades, process mining has developed from a niche discipline to a significant research area with considerable impact on academia and industry. Process mining enables organisations to identify the running business processes from historical execution data. The first requirement of any process mining technique is an event log, an artifact that represents concrete business process executions in the form of sequence of events. These logs can be extracted from the organization's information systems and are used by process experts to retrieve deep insights from the organization's running processes. Considering the events pertaining to such logs, the process models can be automatically discovered and enhanced or annotated with performance-related information. Besides behavioral information, event logs contain domain specific data, albeit implicitly. However, such data are usually overlooked and, thus, not utilized to their full potential. Within the process mining area, we address in this thesis the research gap of discovering, from event logs, the contextual information that cannot be captured by applying existing process mining techniques. Within this research gap, we identify four key problems and tackle them by looking at an event log from different angles. First, we address the problem of deriving an event log in the absence of a proper database access and domain knowledge. The second problem is related to the under-utilization of the implicit domain knowledge present in an event log that can increase the understandability of the discovered process model. Next, there is a lack of a holistic representation of the historical data manipulation at the process model level of abstraction. Last but not least, each process model presumes to be independent of other process models when discovered from an event log, thus, ignoring possible data dependencies between processes within an organization. For each of the problems mentioned above, this thesis proposes a dedicated method. The first method provides a solution to extract an event log only from the transactions performed on the database that are stored in the form of redo logs. The second method deals with discovering the underlying data model that is implicitly embedded in the event log, thus, complementing the discovered process model with important domain knowledge information. The third method captures, on the process model level, how the data affects the running process instances. Lastly, the fourth method is about the discovery of the relations between business processes (i.e., how they exchange data) from a set of event logs and explicitly representing such complex interdependencies in a business process architecture. All the methods introduced in this thesis are implemented as a prototype and their feasibility is proven by being applied on real-life event logs.}, language = {en} } @phdthesis{Jiang2022, author = {Jiang, Lan}, title = {Discovering metadata in data files}, doi = {10.25932/publishup-56620}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-566204}, school = {Universit{\"a}t Potsdam}, pages = {x, ii, 117}, year = {2022}, abstract = {It is estimated that data scientists spend up to 80\% of the time exploring, cleaning, and transforming their data. A major reason for that expenditure is the lack of knowledge about the used data, which are often from different sources and have heterogeneous structures. As a means to describe various properties of data, metadata can help data scientists understand and prepare their data, saving time for innovative and valuable data analytics. However, metadata do not always exist: some data file formats are not capable of storing them; metadata were deleted for privacy concerns; legacy data may have been produced by systems that were not designed to store and handle meta- data. As data are being produced at an unprecedentedly fast pace and stored in diverse formats, manually creating metadata is not only impractical but also error-prone, demanding automatic approaches for metadata detection. In this thesis, we are focused on detecting metadata in CSV files - a type of plain-text file that, similar to spreadsheets, may contain different types of content at arbitrary positions. We propose a taxonomy of metadata in CSV files and specifically address the discovery of three different metadata: line and cell type, aggregations, and primary keys and foreign keys. Data are organized in an ad-hoc manner in CSV files, and do not follow a fixed structure, which is assumed by common data processing tools. Detecting the structure of such files is a prerequisite of extracting information from them, which can be addressed by detecting the semantic type, such as header, data, derived, or footnote, of each line or each cell. We propose the supervised- learning approach Strudel to detect the type of lines and cells. CSV files may also include aggregations. An aggregation represents the arithmetic relationship between a numeric cell and a set of other numeric cells. Our proposed AggreCol algorithm is capable of detecting aggregations of five arithmetic functions in CSV files. Note that stylistic features, such as font style and cell background color, do not exist in CSV files. Our proposed algorithms address the respective problems by using only content, contextual, and computational features. Storing a relational table is also a common usage of CSV files. Primary keys and foreign keys are important metadata for relational databases, which are usually not present for database instances dumped as plain-text files. We propose the HoPF algorithm to holistically detect both constraints in relational databases. Our approach is capable of distinguishing true primary and foreign keys from a great amount of spurious unique column combinations and inclusion dependencies, which can be detected by state-of-the-art data profiling algorithms.}, language = {en} } @phdthesis{Bazhenova2018, author = {Bazhenova, Ekaterina}, title = {Discovery of Decision Models Complementary to Process Models}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-410020}, school = {Universit{\"a}t Potsdam}, year = {2018}, abstract = {Business process management is an acknowledged asset for running an organization in a productive and sustainable way. One of the most important aspects of business process management, occurring on a daily basis at all levels, is decision making. In recent years, a number of decision management frameworks have appeared in addition to existing business process management systems. More recently, Decision Model and Notation (DMN) was developed by the OMG consortium with the aim of complementing the widely used Business Process Model and Notation (BPMN). One of the reasons for the emergence of DMN is the increasing interest in the evolving paradigm known as the separation of concerns. This paradigm states that modeling decisions complementary to processes reduces process complexity by externalizing decision logic from process models and importing it into a dedicated decision model. Such an approach increases the agility of model design and execution. This provides organizations with the flexibility to adapt to the ever increasing rapid and dynamic changes in the business ecosystem. The research gap, identified by us, is that the separation of concerns, recommended by DMN, prescribes the externalization of the decision logic of process models in one or more separate decision models, but it does not specify this can be achieved. The goal of this thesis is to overcome the presented gap by developing a framework for discovering decision models in a semi-automated way from information about existing process decision making. Thus, in this thesis we develop methodologies to extract decision models from: (1) control flow and data of process models that exist in enterprises; and (2) from event logs recorded by enterprise information systems, encapsulating day-to-day operations. Furthermore, we provide an extension of the methodologies to discover decision models from event logs enriched with fuzziness, a tool dealing with partial knowledge of the process execution information. All the proposed techniques are implemented and evaluated in case studies using real-life and synthetic process models and event logs. The evaluation of these case studies shows that the proposed methodologies provide valid and accurate output decision models that can serve as blueprints for executing decisions complementary to process models. Thus, these methodologies have applicability in the real world and they can be used, for example, for compliance checks, among other uses, which could improve the organization's decision making and hence it's overall performance.}, language = {en} } @phdthesis{TorcatoMordido2021, author = {Torcato Mordido, Gon{\c{c}}alo Filipe}, title = {Diversification, compression, and evaluation methods for generative adversarial networks}, doi = {10.25932/publishup-53546}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-535460}, school = {Universit{\"a}t Potsdam}, pages = {xiii, 148}, year = {2021}, abstract = {Generative adversarial networks (GANs) have been broadly applied to a wide range of application domains since their proposal. In this thesis, we propose several methods that aim to tackle different existing problems in GANs. Particularly, even though GANs are generally able to generate high-quality samples, the diversity of the generated set is often sub-optimal. Moreover, the common increase of the number of models in the original GANs framework, as well as their architectural sizes, introduces additional costs. Additionally, even though challenging, the proper evaluation of a generated set is an important direction to ultimately improve the generation process in GANs. We start by introducing two diversification methods that extend the original GANs framework to multiple adversaries to stimulate sample diversity in a generated set. Then, we introduce a new post-training compression method based on Monte Carlo methods and importance sampling to quantize and prune the weights and activations of pre-trained neural networks without any additional training. The previous method may be used to reduce the memory and computational costs introduced by increasing the number of models in the original GANs framework. Moreover, we use a similar procedure to quantize and prune gradients during training, which also reduces the communication costs between different workers in a distributed training setting. We introduce several topology-based evaluation methods to assess data generation in different settings, namely image generation and language generation. Our methods retrieve both single-valued and double-valued metrics, which, given a real set, may be used to broadly assess a generated set or separately evaluate sample quality and sample diversity, respectively. Moreover, two of our metrics use locality-sensitive hashing to accurately assess the generated sets of highly compressed GANs. The analysis of the compression effects in GANs paves the way for their efficient employment in real-world applications. Given their general applicability, the methods proposed in this thesis may be extended beyond the context of GANs. Hence, they may be generally applied to enhance existing neural networks and, in particular, generative frameworks.}, language = {en} } @phdthesis{Che2017, author = {Che, Xiaoyin}, title = {E-lecture material enhancement based on automatic multimedia analysis}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-408224}, school = {Universit{\"a}t Potsdam}, pages = {xviii, 148}, year = {2017}, abstract = {In this era of high-speed informatization and globalization, online education is no longer an exquisite concept in the ivory tower, but a rapidly developing industry closely relevant to people's daily lives. Numerous lectures are recorded in form of multimedia data, uploaded to the Internet and made publicly accessible from anywhere in this world. These lectures are generally addressed as e-lectures. In recent year, a new popular form of e-lectures, the Massive Open Online Courses (MOOCs), boosts the growth of online education industry and somehow turns "learning online" into a fashion. As an e-learning provider, besides to keep improving the quality of e-lecture content, to provide better learning environment for online learners is also a highly important task. This task can be preceded in various ways, and one of them is to enhance and upgrade the learning materials provided: e-lectures could be more than videos. Moreover, this process of enhancement or upgrading should be done automatically, without giving extra burdens to the lecturers or teaching teams, and this is the aim of this thesis. The first part of this thesis is an integrated framework of multi-lingual subtitles production, which can help online learners penetrate the language barrier. The framework consists of Automatic Speech Recognition (ASR), Sentence Boundary Detection (SBD) and Machine Translation (MT), among which the proposed SBD solution is major technical contribution, building on Deep Neural Network (DNN) and Word Vector (WV) and achieving state-of-the-art performance. Besides, a quantitative evaluation with dozens of volunteers is also introduced to measure how these auto-generated subtitles could actually help in context of e-lectures. Secondly, a technical solution "TOG" (Tree-Structure Outline Generation) is proposed to extract textual content from the displaying slides recorded in video and re-organize them into a hierarchical lecture outline, which may serve in multiple functions, such like preview, navigation and retrieval. TOG runs adaptively and can be roughly divided into intra-slide and inter-slides phases. Table detection and lecture video segmentation can be implemented as sub- or post-application in these two phases respectively. Evaluation on diverse e-lectures shows that all the outlines, tables and segments achieved are trustworthily accurate. Based on the subtitles and outlines previously created, lecture videos can be further split into sentence units and slide-based segment units. A lecture highlighting process is further applied on these units, in order to capture and mark the most important parts within the corresponding lecture, just as what people do with a pen when reading paper books. Sentence-level highlighting depends on the acoustic analysis on the audio track, while segment-level highlighting focuses on exploring clues from the statistical information of related transcripts and slide content. Both objective and subjective evaluations prove that the proposed lecture highlighting solution is with decent precision and welcomed by users. All above enhanced e-lecture materials have been already implemented in actual use or made available for implementation by convenient interfaces.}, language = {en} } @misc{LewkowiczWohlbrandtBoettinger2020, author = {Lewkowicz, Daniel and Wohlbrandt, Attila and Boettinger, Erwin}, title = {Economic impact of clinical decision support interventions based on electronic health records}, series = {Postprints der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, journal = {Postprints der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, number = {5}, doi = {10.25932/publishup-50137}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-501376}, pages = {14}, year = {2020}, abstract = {Background Unnecessary healthcare utilization, non-adherence to current clinical guidelines, or insufficient personalized care are perpetual challenges and remain potential major cost-drivers for healthcare systems around the world. Implementing decision support systems into clinical care is promised to improve quality of care and thereby yield substantial effects on reducing healthcare expenditure. In this article, we evaluate the economic impact of clinical decision support (CDS) interventions based on electronic health records (EHR). Methods We searched for studies published after 2014 using MEDLINE, CENTRAL, WEB OF SCIENCE, EBSCO, and TUFTS CEA registry databases that encompass an economic evaluation or consider cost outcome measures of EHR based CDS interventions. Thereupon, we identified best practice application areas and categorized the investigated interventions according to an existing taxonomy of front-end CDS tools. Results and discussion Twenty-seven studies are investigated in this review. Of those, twenty-two studies indicate a reduction of healthcare expenditure after implementing an EHR based CDS system, especially towards prevalent application areas, such as unnecessary laboratory testing, duplicate order entry, efficient transfusion practice, or reduction of antibiotic prescriptions. On the contrary, order facilitators and undiscovered malfunctions revealed to be threats and could lead to new cost drivers in healthcare. While high upfront and maintenance costs of CDS systems are a worldwide implementation barrier, most studies do not consider implementation cost. Finally, four included economic evaluation studies report mixed monetary outcome results and thus highlight the importance of further high-quality economic evaluations for these CDS systems. Conclusion Current research studies lack consideration of comparative cost-outcome metrics as well as detailed cost components in their analyses. Nonetheless, the positive economic impact of EHR based CDS interventions is highly promising, especially with regard to reducing waste in healthcare.}, language = {en} } @phdthesis{Pape2021, author = {Pape, Tobias}, title = {Efficient compound values in virtual machines}, doi = {10.25932/publishup-49913}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-499134}, school = {Universit{\"a}t Potsdam}, pages = {xxix, 242}, year = {2021}, abstract = {Compound values are not universally supported in virtual machine (VM)-based programming systems and languages. However, providing data structures with value characteristics can be beneficial. On one hand, programming systems and languages can adequately represent physical quantities with compound values and avoid inconsistencies, for example, in representation of large numbers. On the other hand, just-in-time (JIT) compilers, which are often found in VMs, can rely on the fact that compound values are immutable, which is an important property in optimizing programs. Considering this, compound values have an optimization potential that can be put to use by implementing them in VMs in a way that is efficient in memory usage and execution time. Yet, optimized compound values in VMs face certain challenges: to maintain consistency, it should not be observable by the program whether compound values are represented in an optimized way by a VM; an optimization should take into account, that the usage of compound values can exhibit certain patterns at run-time; and that necessary value-incompatible properties due to implementation restrictions should be reduced. We propose a technique to detect and compress common patterns of compound value usage at run-time to improve memory usage and execution speed. Our approach identifies patterns of frequent compound value references and introduces abbreviated forms for them. Thus, it is possible to store multiple inter-referenced compound values in an inlined memory representation, reducing the overhead of metadata and object references. We extend our approach by a notion of limited mutability, using cells that act as barriers for our approach and provide a location for shared, mutable access with the possibility of type specialization. We devise an extension to our approach that allows us to express automatic unboxing of boxed primitive data types in terms of our initial technique. We show that our approach is versatile enough to express another optimization technique that relies on values, such as Booleans, that are unique throughout a programming system. Furthermore, we demonstrate how to re-use learned usage patterns and optimizations across program runs, thus reducing the performance impact of pattern recognition. We show in a best-case prototype that the implementation of our approach is feasible and can also be applied to general purpose programming systems, namely implementations of the Racket language and Squeak/Smalltalk. In several micro-benchmarks, we found that our approach can effectively reduce memory consumption and improve execution speed.}, language = {en} } @phdthesis{Draisbach2022, author = {Draisbach, Uwe}, title = {Efficient duplicate detection and the impact of transitivity}, doi = {10.25932/publishup-57214}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-572140}, school = {Universit{\"a}t Potsdam}, pages = {x, 150}, year = {2022}, abstract = {Duplicate detection describes the process of finding multiple representations of the same real-world entity in the absence of a unique identifier, and has many application areas, such as customer relationship management, genealogy and social sciences, or online shopping. Due to the increasing amount of data in recent years, the problem has become even more challenging on the one hand, but has led to a renaissance in duplicate detection research on the other hand. This thesis examines the effects and opportunities of transitive relationships on the duplicate detection process. Transitivity implies that if record pairs ⟨ri,rj⟩ and ⟨rj,rk⟩ are classified as duplicates, then also record pair ⟨ri,rk⟩ has to be a duplicate. However, this reasoning might contradict with the pairwise classification, which is usually based on the similarity of objects. An essential property of similarity, in contrast to equivalence, is that similarity is not necessarily transitive. First, we experimentally evaluate the effect of an increasing data volume on the threshold selection to classify whether a record pair is a duplicate or non-duplicate. Our experiments show that independently of the pair selection algorithm and the used similarity measure, selecting a suitable threshold becomes more difficult with an increasing number of records due to an increased probability of adding a false duplicate to an existing cluster. Thus, the best threshold changes with the dataset size, and a good threshold for a small (possibly sampled) dataset is not necessarily a good threshold for a larger (possibly complete) dataset. As data grows over time, earlier selected thresholds are no longer a suitable choice, and the problem becomes worse for datasets with larger clusters. Second, we present with the Duplicate Count Strategy (DCS) and its enhancement DCS++ two alternatives to the standard Sorted Neighborhood Method (SNM) for the selection of candidate record pairs. DCS adapts SNMs window size based on the number of detected duplicates and DCS++ uses transitive dependencies to save complex comparisons for finding duplicates in larger clusters. We prove that with a proper (domain- and data-independent!) threshold, DCS++ is more efficient than SNM without loss of effectiveness. Third, we tackle the problem of contradicting pairwise classifications. Usually, the transitive closure is used for pairwise classifications to obtain a transitively closed result set. However, the transitive closure disregards negative classifications. We present three new and several existing clustering algorithms and experimentally evaluate them on various datasets and under various algorithm configurations. The results show that the commonly used transitive closure is inferior to most other clustering algorithms, especially for the precision of results. In scenarios with larger clusters, our proposed EMCC algorithm is, together with Markov Clustering, the best performing clustering approach for duplicate detection, although its runtime is longer than Markov Clustering due to the subexponential time complexity. EMCC especially outperforms Markov Clustering regarding the precision of the results and additionally has the advantage that it can also be used in scenarios where edge weights are not available.}, language = {en} } @phdthesis{Benson2024, author = {Benson, Lawrence}, title = {Efficient state management with persistent memory}, doi = {10.25932/publishup-62563}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-625637}, school = {Universit{\"a}t Potsdam}, pages = {xiii, 124}, year = {2024}, abstract = {Efficiently managing large state is a key challenge for data management systems. Traditionally, state is split into fast but volatile state in memory for processing and persistent but slow state on secondary storage for durability. Persistent memory (PMem), as a new technology in the storage hierarchy, blurs the lines between these states by offering both byte-addressability and low latency like DRAM as well persistence like secondary storage. These characteristics have the potential to cause a major performance shift in database systems. Driven by the potential impact that PMem has on data management systems, in this thesis we explore their use of PMem. We first evaluate the performance of real PMem hardware in the form of Intel Optane in a wide range of setups. To this end, we propose PerMA-Bench, a configurable benchmark framework that allows users to evaluate the performance of customizable database-related PMem access. Based on experimental results obtained with PerMA-Bench, we discuss findings and identify general and implementation-specific aspects that influence PMem performance and should be considered in future work to improve PMem-aware designs. We then propose Viper, a hybrid PMem-DRAM key-value store. Based on PMem-aware access patterns, we show how to leverage PMem and DRAM efficiently to design a key database component. Our evaluation shows that Viper outperforms existing key-value stores by 4-18x for inserts while offering full data persistence and achieving similar or better lookup performance. Next, we show which changes must be made to integrate PMem components into larger systems. By the example of stream processing engines, we highlight limitations of current designs and propose a prototype engine that overcomes these limitations. This allows our prototype to fully leverage PMem's performance for its internal state management. Finally, in light of Optane's discontinuation, we discuss how insights from PMem research can be transferred to future multi-tier memory setups by the example of Compute Express Link (CXL). Overall, we show that PMem offers high performance for state management, bridging the gap between fast but volatile DRAM and persistent but slow secondary storage. Although Optane was discontinued, new memory technologies are continuously emerging in various forms and we outline how novel designs for them can build on insights from existing PMem research.}, language = {en} } @inproceedings{JacqminOezdemirFellKurbanetal.2021, author = {Jacqmin, Julien and {\"O}zdemir, Paker Doğu and Fell Kurban, Caroline and Tun{\c{c}} Pekkan, Zelha and Koskinen, Johanna and Suonp{\"a}{\"a}, Maija and Seng, Cheyvuth and Carlon, May Kristine Jonson and Gayed, John Maurice and Cross, Jeffrey S. and Langseth, Inger and Jacobsen, Dan Yngve and Haugsbakken, Halvdan and Bethge, Joseph and Serth, Sebastian and Staubitz, Thomas and Wuttke, Tobias and Nordemann, Oliver and Das, Partha-Pratim and Meinel, Christoph and Ponce, Eva and Srinath, Sindhu and Allegue, Laura and Perach, Shai and Alexandron, Giora and Corti, Paola and Baudo, Valeria and Turr{\´o}, Carlos and Moura Santos, Ana and Nilsson, Charlotta and Maldonado-Mahauad, Jorge and Valdiviezo, Javier and Carvallo, Juan Pablo and Samaniego-Erazo, Nicolay and Poce, Antonella and Re, Maria Rosaria and Valente, Mara and Karp Gershon, Sa'ar and Ruip{\´e}rez-Valiente, Jos{\´e} A. and Despujol, Ignacio and Busquets, Jaime and Kerr, John and Lorenz, Anja and Sch{\"o}n, Sandra and Ebner, Martin and Wittke, Andreas and Beirne, Elaine and Nic Giolla Mhich{\´i}l, Mair{\´e}ad and Brown, Mark and Mac Lochlainn, Conch{\´u}r and Topali, Paraskevi and Chounta, Irene-Angelica and Ortega-Arranz, Alejandro and Villagr{\´a}-Sobrino, Sara L. and Mart{\´i}nez-Mon{\´e}s, Alejandra and Blackwell, Virginia Katherine and Wiltrout, Mary Ellen and Rami Gaddem, Mohamed and Hern{\´a}ndez Reyes, C{\´e}sar Augusto and Nagahama, Toru and Buchem, Ilona and Okatan, Ebru and Khalil, Mohammad and Casiraghi, Daniela and Sancassani, Susanna and Brambilla, Federica and Mihaescu, Vlad and Andone, Diana and Vasiu, Radu and Şahin, Muhittin and Egloffstein, Marc and Bothe, Max and Rohloff, Tobias and Schenk, Nathanael and Schwerer, Florian and Ifenthaler, Dirk and Hense, Julia and Bernd, Mike}, title = {EMOOCs 2021}, editor = {Meinel, Christoph and Staubitz, Thomas and Schweiger, Stefanie and Friedl, Christian and Kiers, Janine and Ebner, Martin and Lorenz, Anja and Ubachs, George and Mongenet, Catherine and Ruip{\´e}rez-Valiente, Jos{\´e} A. and Cortes Mendez, Manoel}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51030}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-510300}, pages = {vii, 295}, year = {2021}, abstract = {From June 22 to June 24, 2021, Hasso Plattner Institute, Potsdam, hosted the seventh European MOOC Stakeholder Summit (EMOOCs 2021) together with the eighth ACM Learning@Scale Conference. Due to the COVID-19 situation, the conference was held fully online. The boost in digital education worldwide as a result of the pandemic was also one of the main topics of this year's EMOOCs. All institutions of learning have been forced to transform and redesign their educational methods, moving from traditional models to hybrid or completely online models at scale. The learnings, derived from practical experience and research, have been explored in EMOOCs 2021 in six tracks and additional workshops, covering various aspects of this field. In this publication, we present papers from the conference's Experience Track, the Policy Track, the Business Track, the International Track, and the Workshops.}, language = {en} } @inproceedings{EsveldVriesBecchettietal.2023, author = {Esveld, Selma van and Vries, Nardo de and Becchetti, Sibilla and Dopper, Sofia and Valkenburg, Willem van and Carlon, May Kristine Jonson and Yokoi, Kensuke and Gayed, John Maurice and Suyama, Hiroshi and Cross, Jeffrey Scott and Jin, Tonje and Xue, Wei and Bruillard, {\´E}ric and Steinbeck, Hendrik and Meinel, Christoph and {\"O}zdemir, Paker Doğu and Can Bayer, Burak and Mercan, Duygu and Buyurucu, Gamze and Haugsbakken, Halvdan and Hagelia, Marianne and Ebner, Martin and Edelsbrunner, Sarah and Hohla-Sejkora, Katharina and Lipp, Silvia and Sch{\"o}n, Sandra and Xiaoxiao, Wang and Shuangshuang, Guo and Morales-Chan, Miguel and Amado-Salvatierra, H{\´e}ctor R. and Hern{\´a}ndez-Rizzardini, Rocael and Egloffstein, Marc and H{\"u}nemohr, Holger and Ifenthaler, Dirk and Dixon, Fred and Trabucchi, Stefania and Khaneboubi, Mehdi and Giannatelli, Ada and Tomasini, Alessandra and Staubitz, Thomas and Serth, Sebastian and Thomas, Max and Koschutnig-Ebner, Markus and Rampelt, Florian and Stetten, Alexander von and Wittke, Andreas and Theeraroungchaisri, Anuchai and Thammetar, Thapanee and Duangchinda, Vorasuang and Khlaisang, Jintavee and Mair, Bettina and Steinkellner, Iris and Stojcevic, Ivana and Zwiauer, Charlotte and Thirouard, Maria and Vill{\`e}sbrunne, Marie de la and Bernaert, Oliver and Nohr, Magnus and Alario Hoyos, Carlos and Delgado Kloos, Carlos and Kiendl, Doris and Terzieva, Liliya and Concia, Francesca and Distler, Petr and Law, Gareth and Macerata, Elena and Mariani, Mario and Mossini, Eros and Negrin, Maddalena and Štrok, Marko and Neub{\"o}ck, Kristina and Linschinger, Nadine and Lorenz, Anja and Bock, Stefanie and Schulte-Ostermann, Juleka and Moura Santos, Ana and Corti, Paola and Costa, Luis Felipe Coimbra and Utunen, Heini and Attias, Melissa and Tokar, Anna and Kennedy, Eileen and Laurillard, Diana and Zeitoun, Samar and Wasilewski, Julie and Shlaka, Souhad and Ouahib, Sara and Berrada, Khalid and Dietz, Michael and Roth, Dennis}, title = {EMOOCs 2023}, editor = {Meinel, Christoph and Schweiger, Stefanie and Staubitz, Thomas and Conrad, Robert and Alario Hoyos, Carlos and Ebner, Martin and Sancassani, Susanna and Żur, Agnieszka and Friedl, Christian and Halawa, Sherif and Gamage, Dilrukshi and Cross, Jeffrey and Jonson Carlon, May Kristine and Deville, Yves and Gaebel, Michael and Delgado Kloos, Carlos and von Schmieden, Karen}, doi = {10.25932/publishup-57645}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-576450}, year = {2023}, abstract = {From June 14 to June 16, 2023, Hasso Plattner Institute, Potsdam, hosted the eighth European MOOC Stakeholder Summit (EMOOCs 2023). The pandemic is fortunately over. It has once again shown how important digital education is. How well-prepared a country was could be seen in our schools, universities, and companies. In different countries, the problems manifested themselves differently. The measures and approaches to solving the problems varied accordingly. Digital education, whether micro-credentials, MOOCs, blended learning formats, or other e-learning tools, received a major boost. EMOOCs 2023 focusses on the effects of this emergency situation. How has it affected the development and delivery of MOOCs and other e-learning offerings all over Europe? Which projects can serve as models for successful digital learning and teaching? Which roles can MOOCs and micro-credentials bear in the current business transformation? Is there a backlash to the routine we knew from pre-Corona times? Or have many things become firmly established in the meantime, e.g. remote work, hybrid conferences, etc.? Furthermore, EMOOCs 2023 has a closer look at the development and formalization of digital learning. Micro-credentials are just the starting point. Further steps in this direction would be complete online study programs or full online universities. Another main topic is the networking of learning offers and the standardization of formats and metadata. Examples of fruitful cooperations are the MOOChub, the European MOOC Consortium, and the Common Micro-Credential Framework. The learnings, derived from practical experience and research, are explored in EMOOCs 2023 in four tracks and additional workshops, covering various aspects of this field. In this publication, we present papers from the conference's Research \& Experience Track, the Business Track and the International Track.}, language = {en} } @phdthesis{Jaeger2018, author = {Jaeger, David}, title = {Enabling Big Data security analytics for advanced network attack detection}, doi = {10.25932/publishup-43571}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-435713}, school = {Universit{\"a}t Potsdam}, pages = {XVII, 201, XXXIII}, year = {2018}, abstract = {The last years have shown an increasing sophistication of attacks against enterprises. Traditional security solutions like firewalls, anti-virus systems and generally Intrusion Detection Systems (IDSs) are no longer sufficient to protect an enterprise against these advanced attacks. One popular approach to tackle this issue is to collect and analyze events generated across the IT landscape of an enterprise. This task is achieved by the utilization of Security Information and Event Management (SIEM) systems. However, the majority of the currently existing SIEM solutions is not capable of handling the massive volume of data and the diversity of event representations. Even if these solutions can collect the data at a central place, they are neither able to extract all relevant information from the events nor correlate events across various sources. Hence, only rather simple attacks are detected, whereas complex attacks, consisting of multiple stages, remain undetected. Undoubtedly, security operators of large enterprises are faced with a typical Big Data problem. In this thesis, we propose and implement a prototypical SIEM system named Real-Time Event Analysis and Monitoring System (REAMS) that addresses the Big Data challenges of event data with common paradigms, such as data normalization, multi-threading, in-memory storage, and distributed processing. In particular, a mostly stream-based event processing workflow is proposed that collects, normalizes, persists and analyzes events in near real-time. In this regard, we have made various contributions in the SIEM context. First, we propose a high-performance normalization algorithm that is highly parallelized across threads and distributed across nodes. Second, we are persisting into an in-memory database for fast querying and correlation in the context of attack detection. Third, we propose various analysis layers, such as anomaly- and signature-based detection, that run on top of the normalized and correlated events. As a result, we demonstrate our capabilities to detect previously known as well as unknown attack patterns. Lastly, we have investigated the integration of cyber threat intelligence (CTI) into the analytical process, for instance, for correlating monitored user accounts with previously collected public identity leaks to identify possible compromised user accounts. In summary, we show that a SIEM system can indeed monitor a large enterprise environment with a massive load of incoming events. As a result, complex attacks spanning across the whole network can be uncovered and mitigated, which is an advancement in comparison to existing SIEM systems on the market.}, language = {en} } @phdthesis{Ladleif2021, author = {Ladleif, Jan}, title = {Enforceability aspects of smart contracts on blockchain networks}, doi = {10.25932/publishup-51908}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-519088}, school = {Universit{\"a}t Potsdam}, pages = {xix, 152}, year = {2021}, abstract = {Smart contracts promise to reform the legal domain by automating clerical and procedural work, and minimizing the risk of fraud and manipulation. Their core idea is to draft contract documents in a way which allows machines to process them, to grasp the operational and non-operational parts of the underlying legal agreements, and to use tamper-proof code execution alongside established judicial systems to enforce their terms. The implementation of smart contracts has been largely limited by the lack of an adequate technological foundation which does not place an undue amount of trust in any contract party or external entity. Only recently did the emergence of Decentralized Applications (DApps) change this: Stored and executed via transactions on novel distributed ledger and blockchain networks, powered by complex integrity and consensus protocols, DApps grant secure computation and immutable data storage while at the same time eliminating virtually all assumptions of trust. However, research on how to effectively capture, deploy, and most of all enforce smart contracts with DApps in mind is still in its infancy. Starting from the initial expression of a smart contract's intent and logic, to the operation of concrete instances in practical environments, to the limits of automatic enforcement---many challenges remain to be solved before a widespread use and acceptance of smart contracts can be achieved. This thesis proposes a model-driven smart contract management approach to tackle some of these issues. A metamodel and semantics of smart contracts are presented, containing concepts such as legal relations, autonomous and non-autonomous actions, and their interplay. Guided by the metamodel, the notion and a system architecture of a Smart Contract Management System (SCMS) is introduced, which facilitates smart contracts in all phases of their lifecycle. Relying on DApps in heterogeneous multi-chain environments, the SCMS approach is evaluated by a proof-of-concept implementation showing both its feasibility and its limitations. Further, two specific enforceability issues are explored in detail: The performance of fully autonomous tamper-proof behavior with external off-chain dependencies and the evaluation of temporal constraints within DApps, both of which are essential for smart contracts but challenging to support in the restricted transaction-driven and closed environment of blockchain networks. Various strategies of implementing or emulating these capabilities, which are ultimately applicable to all kinds of DApp projects independent of smart contracts, are presented and evaluated.}, language = {en} } @phdthesis{Schirneck2022, author = {Schirneck, Friedrich Martin}, title = {Enumeration algorithms in data profiling}, doi = {10.25932/publishup-55672}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-556726}, school = {Universit{\"a}t Potsdam}, pages = {xiv, 192}, year = {2022}, abstract = {Data profiling is the extraction of metadata from relational databases. An important class of metadata are multi-column dependencies. They come associated with two computational tasks. The detection problem is to decide whether a dependency of a given type and size holds in a database. The discovery problem instead asks to enumerate all valid dependencies of that type. We investigate the two problems for three types of dependencies: unique column combinations (UCCs), functional dependencies (FDs), and inclusion dependencies (INDs). We first treat the parameterized complexity of the detection variants. We prove that the detection of UCCs and FDs, respectively, is W[2]-complete when parameterized by the size of the dependency. The detection of INDs is shown to be one of the first natural W[3]-complete problems. We further settle the enumeration complexity of the three discovery problems by presenting parsimonious equivalences with well-known enumeration problems. Namely, the discovery of UCCs is equivalent to the famous transversal hypergraph problem of enumerating the hitting sets of a hypergraph. The discovery of FDs is equivalent to the simultaneous enumeration of the hitting sets of multiple input hypergraphs. Finally, the discovery of INDs is shown to be equivalent to enumerating the satisfying assignments of antimonotone, 3-normalized Boolean formulas. In the remainder of the thesis, we design and analyze discovery algorithms for unique column combinations. Since this is as hard as the general transversal hypergraph problem, it is an open question whether the UCCs of a database can be computed in output-polynomial time in the worst case. For the analysis, we therefore focus on instances that are structurally close to databases in practice, most notably, inputs that have small solutions. The equivalence between UCCs and hitting sets transfers the computational hardness, but also allows us to apply ideas from hypergraph theory to data profiling. We devise an discovery algorithm that runs in polynomial space on arbitrary inputs and achieves polynomial delay whenever the maximum size of any minimal UCC is bounded. Central to our approach is the extension problem for minimal hitting sets, that is, to decide for a set of vertices whether they are contained in any minimal solution. We prove that this is yet another problem that is complete for the complexity class W[3], when parameterized by the size of the set that is to be extended. We also give several conditional lower bounds under popular hardness conjectures such as the Strong Exponential Time Hypothesis (SETH). The lower bounds suggest that the running time of our algorithm for the extension problem is close to optimal. We further conduct an empirical analysis of our discovery algorithm on real-world databases to confirm that the hitting set perspective on data profiling has merits also in practice. We show that the resulting enumeration times undercut their theoretical worst-case bounds on practical data, and that the memory consumption of our method is much smaller than that of previous solutions. During the analysis we make two observations about the connection between databases and their corresponding hypergraphs. On the one hand, the hypergraph representations containing all relevant information are usually significantly smaller than the original inputs. On the other hand, obtaining those hypergraphs is the actual bottleneck of any practical application. The latter often takes much longer than enumerating the solutions, which is in stark contrast to the fact that the preprocessing is guaranteed to be polynomial while the enumeration may take exponential time. To make the first observation rigorous, we introduce a maximum-entropy model for non-uniform random hypergraphs and prove that their expected number of minimal hyperedges undergoes a phase transition with respect to the total number of edges. The result also explains why larger databases may have smaller hypergraphs. Motivated by the second observation, we present a new kind of UCC discovery algorithm called Hitting Set Enumeration with Partial Information and Validation (HPIValid). It utilizes the fast enumeration times in practice in order to speed up the computation of the corresponding hypergraph. This way, we sidestep the bottleneck while maintaining the advantages of the hitting set perspective. An exhaustive empirical evaluation shows that HPIValid outperforms the current state of the art in UCC discovery. It is capable of processing databases that were previously out of reach for data profiling.}, language = {en} } @phdthesis{Marx2024, author = {Marx, Carolin Valerie}, title = {Escalation of commitment in information systems projects: a cognitive-affective perspective}, doi = {10.25932/publishup-62696}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-626969}, school = {Universit{\"a}t Potsdam}, pages = {174}, year = {2024}, abstract = {While information systems (IS) projects are pivotal in guiding organizational strategies and sustaining competitive advantages, they frequently overrun budgets, extend beyond timelines, and experience high failure rates. This dissertation delves into the psychological micro-foundations of human behavior - specifically cognition and emotion - in relation to a prevalent issue in IS project management: the tendency to persist with failing courses of action, also called escalation of commitment (EoC). Through a mixed-methods research approach, this study investigates the emotional and cognitive bases of decision-making during IS project escalation and its evolution over time. The results of a psychophysiological laboratory experiment provide evidence for the predictions on the role of negative and complex situational integral emotions of Cognitive Dissonance over Coping Theory and add to a better understanding of how escalation tendencies change during sequential decision-making due to cognitive learning effects. Using psychophysiological measures, including data triangulation between electrodermal and cardiovascular activity and AI-based analysis of facial micro-expressions, this research reveals physiological markers of behavioral escalation tendencies. Complementing the experiment, a qualitative analysis using free-form narration during decision-making simulations shows that decision-makers employ varied cognitive reasoning patterns to justify escalating behaviors, suggesting a sequence of four distinct cognitive phases. By integrating both qualitative and quantitative findings, this dissertation offers a comprehensive theoretical framework of how cognition and emotion shape behavioral EoC over time. I propose that escalation is a cyclical adaptation of mental models, distinguished by shifts in cognitive reasoning patterns, temporal cognition mode variations, and interactions with situational emotions and their anticipation. The primary contribution of this dissertation lies in disentangling the emotional and cognitive mechanisms that drive IS project escalation. The findings provide the basis for developing de-escalation strategies, thereby helping to improve decision-making under uncertainty. Stakeholders involved in IS projects that get "off track" should be aware of the tendency to persist with failing courses of action and the importance of the underlying emotional and cognitive dynamics.}, language = {de} } @article{PoceReValente2021, author = {Poce, Antonella and Re, Maria Rosaria and Valente, Mara}, title = {Evaluating OERs in Museum Education Context}, series = {EMOOCs 2021}, volume = {2021}, journal = {EMOOCs 2021}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51717}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-517178}, pages = {159 -- 168}, year = {2021}, abstract = {This paper aims to present the results of a higher education experience promoted by the research centres INTELLECT (University of Modena and Reggio Emilia) and CDM (University of Roma Tre), as part of difference master's degrees programme of the academic years 2018/2019, 2019/2020, and 2020/2021. Through different online activities, 37 students attended and evaluated a MOOC on museum education content, such promoting their professionals and transverse skills, such as critical thinking, and developing their knowledge relative to OERs, within culture and heritage education contexts. Moreover, results from the online evaluation activities support the implementation of the MOOC in a collaborative way: during the academic years, evaluation data have been used by researcher to make changes to the course modules, thus realizing a more effective online path from and educational point of view.}, language = {en} } @phdthesis{Sakizloglou2023, author = {Sakizloglou, Lucas}, title = {Evaluating temporal queries over history-aware architectural runtime models}, doi = {10.25932/publishup-60439}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-604396}, school = {Universit{\"a}t Potsdam}, pages = {v, 168}, year = {2023}, abstract = {In model-driven engineering, the adaptation of large software systems with dynamic structure is enabled by architectural runtime models. Such a model represents an abstract state of the system as a graph of interacting components. Every relevant change in the system is mirrored in the model and triggers an evaluation of model queries, which search the model for structural patterns that should be adapted. This thesis focuses on a type of runtime models where the expressiveness of the model and model queries is extended to capture past changes and their timing. These history-aware models and temporal queries enable more informed decision-making during adaptation, as they support the formulation of requirements on the evolution of the pattern that should be adapted. However, evaluating temporal queries during adaptation poses significant challenges. First, it implies the capability to specify and evaluate requirements on the structure, as well as the ordering and timing in which structural changes occur. Then, query answers have to reflect that the history-aware model represents the architecture of a system whose execution may be ongoing, and thus answers may depend on future changes. Finally, query evaluation needs to be adequately fast and memory-efficient despite the increasing size of the history---especially for models that are altered by numerous, rapid changes. The thesis presents a query language and a querying approach for the specification and evaluation of temporal queries. These contributions aim to cope with the challenges of evaluating temporal queries at runtime, a prerequisite for history-aware architectural monitoring and adaptation which has not been systematically treated by prior model-based solutions. The distinguishing features of our contributions are: the specification of queries based on a temporal logic which encodes structural patterns as graphs; the provision of formally precise query answers which account for timing constraints and ongoing executions; the incremental evaluation which avoids the re-computation of query answers after each change; and the option to discard history that is no longer relevant to queries. The query evaluation searches the model for occurrences of a pattern whose evolution satisfies a temporal logic formula. Therefore, besides model-driven engineering, another related research community is runtime verification. The approach differs from prior logic-based runtime verification solutions by supporting the representation and querying of structure via graphs and graph queries, respectively, which is more efficient for queries with complex patterns. We present a prototypical implementation of the approach and measure its speed and memory consumption in monitoring and adaptation scenarios from two application domains, with executions of an increasing size. We assess scalability by a comparison to the state-of-the-art from both related research communities. The implementation yields promising results, which pave the way for sophisticated history-aware self-adaptation solutions and indicate that the approach constitutes a highly effective technique for runtime monitoring on an architectural level.}, language = {en} } @misc{AlbertOwolabiGebeletal.2020, author = {Albert, Justin Amadeus and Owolabi, Victor and Gebel, Arnd and Brahms, Clemens Markus and Granacher, Urs and Arnrich, Bert}, title = {Evaluation of the Pose Tracking Performance of the Azure Kinect and Kinect v2 for Gait Analysis in Comparison with a Gold Standard}, series = {Postprints der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, journal = {Postprints der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, number = {3}, doi = {10.25932/publishup-48413}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-484130}, pages = {24}, year = {2020}, abstract = {Gait analysis is an important tool for the early detection of neurological diseases and for the assessment of risk of falling in elderly people. The availability of low-cost camera hardware on the market today and recent advances in Machine Learning enable a wide range of clinical and health-related applications, such as patient monitoring or exercise recognition at home. In this study, we evaluated the motion tracking performance of the latest generation of the Microsoft Kinect camera, Azure Kinect, compared to its predecessor Kinect v2 in terms of treadmill walking using a gold standard Vicon multi-camera motion capturing system and the 39 marker Plug-in Gait model. Five young and healthy subjects walked on a treadmill at three different velocities while data were recorded simultaneously with all three camera systems. An easy-to-administer camera calibration method developed here was used to spatially align the 3D skeleton data from both Kinect cameras and the Vicon system. With this calibration, the spatial agreement of joint positions between the two Kinect cameras and the reference system was evaluated. In addition, we compared the accuracy of certain spatio-temporal gait parameters, i.e., step length, step time, step width, and stride time calculated from the Kinect data, with the gold standard system. Our results showed that the improved hardware and the motion tracking algorithm of the Azure Kinect camera led to a significantly higher accuracy of the spatial gait parameters than the predecessor Kinect v2, while no significant differences were found between the temporal parameters. Furthermore, we explain in detail how this experimental setup could be used to continuously monitor the progress during gait rehabilitation in older people.}, language = {en} } @phdthesis{Mandal2019, author = {Mandal, Sankalita}, title = {Event handling in business processes}, doi = {10.25932/publishup-44170}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-441700}, school = {Universit{\"a}t Potsdam}, pages = {xix, 151}, year = {2019}, abstract = {Business process management (BPM) deals with modeling, executing, monitoring, analyzing, and improving business processes. During execution, the process communicates with its environment to get relevant contextual information represented as events. Recent development of big data and the Internet of Things (IoT) enables sources like smart devices and sensors to generate tons of events which can be filtered, grouped, and composed to trigger and drive business processes. The industry standard Business Process Model and Notation (BPMN) provides several event constructs to capture the interaction possibilities between a process and its environment, e.g., to instantiate a process, to abort an ongoing activity in an exceptional situation, to take decisions based on the information carried by the events, as well as to choose among the alternative paths for further process execution. The specifications of such interactions are termed as event handling. However, in a distributed setup, the event sources are most often unaware of the status of process execution and therefore, an event is produced irrespective of the process being ready to consume it. BPMN semantics does not support such scenarios and thus increases the chance of processes getting delayed or getting in a deadlock by missing out on event occurrences which might still be relevant. The work in this thesis reviews the challenges and shortcomings of integrating real-world events into business processes, especially the subscription management. The basic integration is achieved with an architecture consisting of a process modeler, a process engine, and an event processing platform. Further, points of subscription and unsubscription along the process execution timeline are defined for different BPMN event constructs. Semantic and temporal dependencies among event subscription, event occurrence, event consumption and event unsubscription are considered. To this end, an event buffer with policies for updating the buffer, retrieving the most suitable event for the current process instance, and reusing the event has been discussed that supports issuing of early subscription. The Petri net mapping of the event handling model provides our approach with a translation of semantics from a business process perspective. Two applications based on this formal foundation are presented to support the significance of different event handling configurations on correct process execution and reachability of a process path. Prototype implementations of the approaches show that realizing flexible event handling is feasible with minor extensions of off-the-shelf process engines and event platforms.}, language = {en} } @phdthesis{Niephaus2022, author = {Niephaus, Fabio}, title = {Exploratory tool-building platforms for polyglot virtual machines}, doi = {10.25932/publishup-57177}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-571776}, school = {Universit{\"a}t Potsdam}, pages = {xxi, 249}, year = {2022}, abstract = {Polyglot programming allows developers to use multiple programming languages within the same software project. While it is common to use more than one language in certain programming domains, developers also apply polyglot programming for other purposes such as to re-use software written in other languages. Although established approaches to polyglot programming come with significant limitations, for example, in terms of performance and tool support, developers still use them to be able to combine languages. Polyglot virtual machines (VMs) such as GraalVM provide a new level of polyglot programming, allowing languages to directly interact with each other. This reduces the amount of glue code needed to combine languages, results in better performance, and enables tools such as debuggers to work across languages. However, only a little research has focused on novel tools that are designed to support developers in building software with polyglot VMs. One reason is that tool-building is often an expensive activity, another one is that polyglot VMs are still a moving target as their use cases and requirements are not yet well understood. In this thesis, we present an approach that builds on existing self-sustaining programming systems such as Squeak/Smalltalk to enable exploratory programming, a practice for exploring and gathering software requirements, and re-use their extensive tool-building capabilities in the context of polyglot VMs. Based on TruffleSqueak, our implementation for the GraalVM, we further present five case studies that demonstrate how our approach helps tool developers to design and build tools for polyglot programming. We further show that TruffleSqueak can also be used by application developers to build and evolve polyglot applications at run-time and by language and runtime developers to understand the dynamic behavior of GraalVM languages and internals. Since our platform allows all these developers to apply polyglot programming, it can further help to better understand the advantages, use cases, requirements, and challenges of polyglot VMs. Moreover, we demonstrate that our approach can also be applied to other polyglot VMs and that insights gained through it are transferable to other programming systems. We conclude that our research on tools for polyglot programming is an important step toward making polyglot VMs more approachable for developers in practice. With good tool support, we believe polyglot VMs can make it much more common for developers to take advantage of multiple languages and their ecosystems when building software.}, language = {en} } @book{EichenrothReinHirschfeld2022, author = {Eichenroth, Friedrich and Rein, Patrick and Hirschfeld, Robert}, title = {Fast packrat parsing in a live programming environment}, series = {Technische Berichte des Hasso-Plattner-Instituts f{\"u}r Digital Engineering an der Universit{\"a}t Potsdam}, journal = {Technische Berichte des Hasso-Plattner-Instituts f{\"u}r Digital Engineering an der Universit{\"a}t Potsdam}, number = {135}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-503-3}, issn = {1613-5652}, doi = {10.25932/publishup-49124}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-491242}, publisher = {Universit{\"a}t Potsdam}, pages = {79}, year = {2022}, abstract = {Language developers who design domain-specific languages or new language features need a way to make fast changes to language definitions. Those fast changes require immediate feedback. Also, it should be possible to parse the developed languages quickly to handle extensive sets of code. Parsing expression grammars provides an easy to understand method for language definitions. Packrat parsing is a method to parse grammars of this kind, but this method is unable to handle left-recursion properly. Existing solutions either partially rewrite left-recursive rules and partly forbid them, or use complex extensions to packrat parsing that are hard to understand and cost-intensive. We investigated methods to make parsing as fast as possible, using easy to follow algorithms while not losing the ability to make fast changes to grammars. We focused our efforts on two approaches. One is to start from an existing technique for limited left-recursion rewriting and enhance it to work for general left-recursive grammars. The second approach is to design a grammar compilation process to find left-recursion before parsing, and in this way, reduce computational costs wherever possible and generate ready to use parser classes. Rewriting parsing expression grammars is a task that, if done in a general way, unveils a large number of cases such that any rewriting algorithm surpasses the complexity of other left-recursive parsing algorithms. Lookahead operators introduce this complexity. However, most languages have only little portions that are left-recursive and in virtually all cases, have no indirect or hidden left-recursion. This means that the distinction of left-recursive parts of grammars from components that are non-left-recursive holds great improvement potential for existing parsers. In this report, we list all the required steps for grammar rewriting to handle left-recursion, including grammar analysis, grammar rewriting itself, and syntax tree restructuring. Also, we describe the implementation of a parsing expression grammar framework in Squeak/Smalltalk and the possible interactions with the already existing parser Ohm/S. We quantitatively benchmarked this framework directing our focus on parsing time and the ability to use it in a live programming context. Compared with Ohm, we achieved massive parsing time improvements while preserving the ability to use our parser it as a live programming tool. The work is essential because, for one, we outlined the difficulties and complexity that come with grammar rewriting. Also, we removed the existing limitations that came with left-recursion by eliminating them before parsing.}, language = {en} } @article{CortiBaudoTurroetal.2021, author = {Corti, Paola and Baudo, Valeria and Turr{\´o}, Carlos and Santos, Ana Moura and Nilsson, Charlotta}, title = {Fostering Women to STEM MOOCs}, series = {EMOOCs 2021}, volume = {2021}, journal = {EMOOCs 2021}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51714}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-517141}, pages = {129 -- 141}, year = {2021}, abstract = {In the context of the Fostering Women to STEM MOOCs (FOSTWOM) project, we present here the general ideas of a gender balance Toolkit, i.e. a collection of recommendations and resources for instructional designers, visual designers, and teaching staff to apply while designing and preparing storyboards for MOOCs and their visual components, so that future STEM online courses have a greater chance to be more inclusive and gender-balanced. Overall, The FOSTWOM project intends to use the inclusive potential of Massive Open Online Courses to propose STEM subjects free of stereotyping assumptions on gender abilities. Moreover, the consortium is interested in attracting girls and young women to science and technology careers, through accessible online content, which can include role models' interviews, relevant real-world situations, and strong conceptual frameworks.}, language = {en} } @article{ThirouarddelaVillesbrunneBernaert2023, author = {Thirouard, Maria and de la Vill{\`e}sbrunne, Marie and Bernaert, Oliver}, title = {From MOOC to "2M-POC"}, series = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, journal = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, editor = {Meinel, Christoph and Schweiger, Stefanie and Staubitz, Thomas and Conrad, Robert and Alario Hoyos, Carlos and Ebner, Martin and Sancassani, Susanna and Żur, Agnieszka and Friedl, Christian and Halawa, Sherif and Gamage, Dilrukshi and Scott, Jeffrey and Kristine Jonson Carlon, May and Deville, Yves and Gaebel, Michael and Delgado Kloos, Carlos and von Schmieden, Karen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-62426}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-624268}, pages = {187 -- 200}, year = {2023}, abstract = {IFP School develops and produces MOOCs since 2014. After the COVID-19 crisis, the demand of our industrial and international partners to offer continuous training to their employees increased drastically in an energy transition and sustainable mobility environment that finds itself in constant and rapid evolution. Therefore, it is time for a new format of digital learning tools to efficiently and rapidly train an important number of employees. To address this new demand, in a more and more digital learning environment, we have completely changed our initial MOOC model to propose an innovative SPOC business model mixing synchronous and asynchronous modules. This paper describes the work that has been done to transform our MOOCs to a hybrid SPOC model. We changed the format itself from a standard MOOC model of several weeks to small modules of one week average more adapted to our client's demand. We precisely engineered the exchanges between learners and the social aspect all along the SPOC duration. We propose a multimodal approach with a combination of asynchronous activities like online module, exercises, and synchronous activities like webinars with experts, and after-work sessions. Additionally, this new format increases the number of uses of the MOOC resources by our professors in our own master programs. With all these actions, we were able to reach a completion rate between 80 and 96\% - total enrolled -, compared to the completion rate of 15 to 28\% - total enrolled - as to be recorded in our original MOOC format. This is to be observed for small groups (50-100 learners) as SPOC but also for large groups (more than 2500 learners), as a Massive and Multimodal Private Online Course ("2M-POC"). Today a MOOC is not a simple assembly of videos, text, discussions forums and validation exercises but a complete multimodal learning path including social learning, personal followup, synchronous and asynchronous modules. We conclude that the original MOOC format is not at all suitable to propose efficient training to companies, and we must re-engineer the learning path to have a SPOC hybrid and multimodal training compatible with a cost-effective business model.}, language = {en} } @phdthesis{Zuo2017, author = {Zuo, Zhe}, title = {From unstructured to structured: Context-based named entity mining from text}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-412576}, school = {Universit{\"a}t Potsdam}, pages = {vii, 112}, year = {2017}, abstract = {With recent advances in the area of information extraction, automatically extracting structured information from a vast amount of unstructured textual data becomes an important task, which is infeasible for humans to capture all information manually. Named entities (e.g., persons, organizations, and locations), which are crucial components in texts, are usually the subjects of structured information from textual documents. Therefore, the task of named entity mining receives much attention. It consists of three major subtasks, which are named entity recognition, named entity linking, and relation extraction. These three tasks build up an entire pipeline of a named entity mining system, where each of them has its challenges and can be employed for further applications. As a fundamental task in the natural language processing domain, studies on named entity recognition have a long history, and many existing approaches produce reliable results. The task is aiming to extract mentions of named entities in text and identify their types. Named entity linking recently received much attention with the development of knowledge bases that contain rich information about entities. The goal is to disambiguate mentions of named entities and to link them to the corresponding entries in a knowledge base. Relation extraction, as the final step of named entity mining, is a highly challenging task, which is to extract semantic relations between named entities, e.g., the ownership relation between two companies. In this thesis, we review the state-of-the-art of named entity mining domain in detail, including valuable features, techniques, evaluation methodologies, and so on. Furthermore, we present two of our approaches that focus on the named entity linking and relation extraction tasks separately. To solve the named entity linking task, we propose the entity linking technique, BEL, which operates on a textual range of relevant terms and aggregates decisions from an ensemble of simple classifiers. Each of the classifiers operates on a randomly sampled subset of the above range. In extensive experiments on hand-labeled and benchmark datasets, our approach outperformed state-of-the-art entity linking techniques, both in terms of quality and efficiency. For the task of relation extraction, we focus on extracting a specific group of difficult relation types, business relations between companies. These relations can be used to gain valuable insight into the interactions between companies and perform complex analytics, such as predicting risk or valuating companies. Our semi-supervised strategy can extract business relations between companies based on only a few user-provided seed company pairs. By doing so, we also provide a solution for the problem of determining the direction of asymmetric relations, such as the ownership_of relation. We improve the reliability of the extraction process by using a holistic pattern identification method, which classifies the generated extraction patterns. Our experiments show that we can accurately and reliably extract new entity pairs occurring in the target relation by using as few as five labeled seed pairs.}, language = {en} } @phdthesis{Staubitz2020, author = {Staubitz, Thomas}, title = {Gradable team assignments in large scale learning environments}, doi = {10.25932/publishup-47183}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-471830}, school = {Universit{\"a}t Potsdam}, pages = {122}, year = {2020}, abstract = {Lifelong learning plays an increasingly important role in many societies. Technology is changing faster than ever and what has been important to learn today, may be obsolete tomorrow. The role of informal programs is becoming increasingly important. Particularly, Massive Open Online Courses have become popular among learners and instructors. In 2008, a group of Canadian education enthusiasts started the first Massive Open Online Courses or MOOCs to prove their cognitive theory of Connectivism. Around 2012, a variety of American start-ups redefined the concept of MOOCs. Instead of following the connectivist doctrine they returned to a more traditional approach. They focussed on video lecturing and combined this with a course forum that allowed the participants to discuss with each other and the teaching team. While this new version of the concept was enormously successful in terms of massiveness—hundreds of thousands of participants from all over the world joined the first of these courses—many educators criticized the re-lapse to the cognitivist model. In the early days, the evolving platforms often did not have more features than a video player, simple multiple-choice quizzes, and the course forum. It soon became a major interest of research to allow the scaling of more modern approaches of learning and teaching for the massiveness of these courses. Hands-on exercises, alternative forms of assessment, collaboration, and teamwork are some of the topics on the agenda. The insights provided by cognitive and pedagogical theories, however, do not necessarily always run in sync with the needs and the preferences of the majority of participants. While the former promote action-learning, hands-on-learning, competence-based-learning, project-based-learning, team-based-learning as the holy grail, many of the latter often rather prefer a more laid-back style of learning, sometimes referred to as edutainment. Obviously, given the large numbers of participants in these courses, there is not just one type of learners. Participants are not a homogeneous mass but a potpourri of individuals with a wildly heterogeneous mix of backgrounds, previous knowledge, familial and professional circumstances, countries of origin, gender, age, and so on. For the majority of participants, a full-time job and/or a family often just does not leave enough room for more time intensive tasks, such as practical exercises or teamwork. Others, however, particularly enjoy these hands-on or collaborative aspects of MOOCs. Furthermore, many subjects particularly require these possibilities and simply cannot be taught or learned in courses that lack collaborative or hands-on features. In this context, the thesis discusses how team assignments have been implemented on the HPI MOOC platform. During the recent years, several experiments have been conducted and a great amount of experience has been gained by employing team assignments in courses in areas, such as Object-Oriented Programming, Design Thinking, and Business Innovation on various instances of this platform: openHPI, openSAP, and mooc.house}, language = {en} } @phdthesis{Sapegin2018, author = {Sapegin, Andrey}, title = {High-Speed Security Log Analytics Using Hybrid Outlier Detection}, doi = {10.25932/publishup-42611}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-426118}, school = {Universit{\"a}t Potsdam}, pages = {162}, year = {2018}, abstract = {The rapid development and integration of Information Technologies over the last decades influenced all areas of our life, including the business world. Yet not only the modern enterprises become digitalised, but also security and criminal threats move into the digital sphere. To withstand these threats, modern companies must be aware of all activities within their computer networks. The keystone for such continuous security monitoring is a Security Information and Event Management (SIEM) system that collects and processes all security-related log messages from the entire enterprise network. However, digital transformations and technologies, such as network virtualisation and widespread usage of mobile communications, lead to a constantly increasing number of monitored devices and systems. As a result, the amount of data that has to be processed by a SIEM system is increasing rapidly. Besides that, in-depth security analysis of the captured data requires the application of rather sophisticated outlier detection algorithms that have a high computational complexity. Existing outlier detection methods often suffer from performance issues and are not directly applicable for high-speed and high-volume analysis of heterogeneous security-related events, which becomes a major challenge for modern SIEM systems nowadays. This thesis provides a number of solutions for the mentioned challenges. First, it proposes a new SIEM system architecture for high-speed processing of security events, implementing parallel, in-memory and in-database processing principles. The proposed architecture also utilises the most efficient log format for high-speed data normalisation. Next, the thesis offers several novel high-speed outlier detection methods, including generic Hybrid Outlier Detection that can efficiently be used for Big Data analysis. Finally, the special User Behaviour Outlier Detection is proposed for better threat detection and analysis of particular user behaviour cases. The proposed architecture and methods were evaluated in terms of both performance and accuracy, as well as compared with classical architecture and existing algorithms. These evaluations were performed on multiple data sets, including simulated data, well-known public intrusion detection data set, and real data from the large multinational enterprise. The evaluation results have proved the high performance and efficacy of the developed methods. All concepts proposed in this thesis were integrated into the prototype of the SIEM system, capable of high-speed analysis of Big Security Data, which makes this integrated SIEM platform highly relevant for modern enterprise security applications.}, language = {en} } @article{WasilewskiKhaneboubiBruillard2023, author = {Wasilewski, Julie and Khaneboubi, Mehdi and Bruillard, {\´E}ric}, title = {How to detect At-Risk learners in professional finance MOOCs}, series = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, journal = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, editor = {Meinel, Christoph and Schweiger, Stefanie and Staubitz, Thomas and Conrad, Robert and Alario Hoyos, Carlos and Ebner, Martin and Sancassani, Susanna and Żur, Agnieszka and Friedl, Christian and Halawa, Sherif and Gamage, Dilrukshi and Scott, Jeffrey and Kristine Jonson Carlon, May and Deville, Yves and Gaebel, Michael and Delgado Kloos, Carlos and von Schmieden, Karen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-62481}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-624818}, pages = {305 -- 316}, year = {2023}, abstract = {"Financial Analysis" is an online course designed for professionals consisting of three MOOCs, offering a professionally and institutionally recognized certificate in finance. The course is open but not free of charge and attracts mostly professionals from the banking industry. The primary objective of this study is to identify indicators that can predict learners at high risk of failure. To achieve this, we analyzed data from a previous course that had 875 enrolled learners and involve in the course during Fall 2021. We utilized correspondence analysis to examine demographic and behavioral variables. The initial results indicate that demographic factors have a minor impact on the risk of failure in comparison to learners' behaviors on the course platform. Two primary profiles were identified: (1) successful learners who utilized all the documents offered and spent between one to two hours per week, and (2) unsuccessful learners who used less than half of the proposed documents and spent less than one hour per week. Between these groups, at-risk students were identified as those who used more than half of the proposed documents and spent more than two hours per week. The goal is to identify those in group 1 who may be at risk of failing and those in group 2 who may succeed in the current MOOC, and to implement strategies to assist all learners in achieving success.}, language = {en} } @article{MouraSantosCortiFelipeCoimbraCosta2023, author = {Moura Santos, Ana and Corti, Paola and Felipe Coimbra Costa, Luis}, title = {How to reuse inclusive stem Moocs in blended settings to engage young girls to scientific careers}, series = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, journal = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, editor = {Meinel, Christoph and Schweiger, Stefanie and Staubitz, Thomas and Conrad, Robert and Alario Hoyos, Carlos and Ebner, Martin and Sancassani, Susanna and Żur, Agnieszka and Friedl, Christian and Halawa, Sherif and Gamage, Dilrukshi and Scott, Jeffrey and Kristine Jonson Carlon, May and Deville, Yves and Gaebel, Michael and Delgado Kloos, Carlos and von Schmieden, Karen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-62475}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-624756}, pages = {271 -- 278}, year = {2023}, abstract = {The FOSTWOM project (2019-2022), an ERASMUS+ funding, gave METID (Politecnico di Milano) and the MOOC T{\´e}cnico (Instituto Superior T{\´e}cnico, University of Lisbon), together with other partners, the opportunity to support the design and creation of gender-inclusive MOOCs. Among other project outputs, we designed a toolkit and a framework that enabled the production of two MOOCs for undergraduate and graduate students in Science, Technology, Engineering and Maths (STEM) and used them as academic content free of gender stereotypes about intellectual ability. In this short paper, the authors aim to 1) briefly share the main outputs of the project; 2) tell the story of how the FOSTWOM approach together with 3) a motivational strategy, the Heroine's Learning Journey, proved to be effective in the context of rural and marginal areas in Brazil, with young girls as a specific target audience.}, language = {en} } @misc{ZhouFischerTuncaetal.2020, author = {Zhou, Lin and Fischer, Eric and Tunca, Can and Brahms, Clemens Markus and Ersoy, Cem and Granacher, Urs and Arnrich, Bert}, title = {How We Found Our IMU}, series = {Postprints der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, journal = {Postprints der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, number = {2}, doi = {10.25932/publishup-48162}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-481628}, pages = {31}, year = {2020}, abstract = {Inertial measurement units (IMUs) are commonly used for localization or movement tracking in pervasive healthcare-related studies, and gait analysis is one of the most often studied topics using IMUs. The increasing variety of commercially available IMU devices offers convenience by combining the sensor modalities and simplifies the data collection procedures. However, selecting the most suitable IMU device for a certain use case is increasingly challenging. In this study, guidelines for IMU selection are proposed. In particular, seven IMUs were compared in terms of their specifications, data collection procedures, and raw data quality. Data collected from the IMUs were then analyzed by a gait analysis algorithm. The difference in accuracy of the calculated gait parameters between the IMUs could be used to retrace the issues in raw data, such as acceleration range or sensor calibration. Based on our algorithm, we were able to identify the best-suited IMUs for our needs. This study provides an overview of how to select the IMUs based on the area of study with concrete examples, and gives insights into the features of seven commercial IMUs using real data.}, language = {en} } @inproceedings{OPUS4-40678, title = {HPI Future SOC Lab}, editor = {Meinel, Christoph and Polze, Andreas and Oswald, Gerhard and Strotmann, Rolf and Seibold, Ulrich and Schulzki, Bernhard}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-406787}, pages = {iii, 180}, year = {2016}, abstract = {The "HPI Future SOC Lab" is a cooperation of the Hasso Plattner Institute (HPI) and industrial partners. Its mission is to enable and promote exchange and interaction between the research community and the industrial partners. The HPI Future SOC Lab provides researchers with free of charge access to a complete infrastructure of state of the art hard and software. This infrastructure includes components, which might be too expensive for an ordinary research environment, such as servers with up to 64 cores and 2 TB main memory. The offerings address researchers particularly from but not limited to the areas of computer science and business information systems. Main areas of research include cloud computing, parallelization, and In-Memory technologies. This technical report presents results of research projects executed in 2016. Selected projects have presented their results on April 5th and November 3th 2016 at the Future SOC Lab Day events.}, language = {en} } @book{ZhangPlauthEberhardtetal.2020, author = {Zhang, Shuhao and Plauth, Max and Eberhardt, Felix and Polze, Andreas and Lehmann, Jens and Sejdiu, Gezim and Jabeen, Hajira and Servadei, Lorenzo and M{\"o}stl, Christian and B{\"a}r, Florian and Netzeband, Andr{\´e} and Schmidt, Rainer and Knigge, Marlene and Hecht, Sonja and Prifti, Loina and Krcmar, Helmut and Sapegin, Andrey and Jaeger, David and Cheng, Feng and Meinel, Christoph and Friedrich, Tobias and Rothenberger, Ralf and Sutton, Andrew M. and Sidorova, Julia A. and Lundberg, Lars and Rosander, Oliver and Sk{\"o}ld, Lars and Di Varano, Igor and van der Walt, Est{\´e}e and Eloff, Jan H. P. and Fabian, Benjamin and Baumann, Annika and Ermakova, Tatiana and Kelkel, Stefan and Choudhary, Yash and Cooray, Thilini and Rodr{\´i}guez, Jorge and Medina-P{\´e}rez, Miguel Angel and Trejo, Luis A. and Barrera-Animas, Ari Yair and Monroy-Borja, Ra{\´u}l and L{\´o}pez-Cuevas, Armando and Ram{\´i}rez-M{\´a}rquez, Jos{\´e} Emmanuel and Grohmann, Maria and Niederleithinger, Ernst and Podapati, Sasidhar and Schmidt, Christopher and Huegle, Johannes and de Oliveira, Roberto C. L. and Soares, F{\´a}bio Mendes and van Hoorn, Andr{\´e} and Neumer, Tamas and Willnecker, Felix and Wilhelm, Mathias and Kuster, Bernhard}, title = {HPI Future SOC Lab - Proceedings 2017}, number = {130}, editor = {Meinel, Christoph and Polze, Andreas and Beins, Karsten and Strotmann, Rolf and Seibold, Ulrich and R{\"o}dszus, Kurt and M{\"u}ller, J{\"u}rgen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-475-3}, issn = {1613-5652}, doi = {10.25932/publishup-43310}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-433100}, publisher = {Universit{\"a}t Potsdam}, pages = {ix, 235}, year = {2020}, abstract = {The "HPI Future SOC Lab" is a cooperation of the Hasso Plattner Institute (HPI) and industry partners. Its mission is to enable and promote exchange and interaction between the research community and the industry partners. The HPI Future SOC Lab provides researchers with free of charge access to a complete infrastructure of state of the art hard and software. This infrastructure includes components, which might be too expensive for an ordinary research environment, such as servers with up to 64 cores and 2 TB main memory. The offerings address researchers particularly from but not limited to the areas of computer science and business information systems. Main areas of research include cloud computing, parallelization, and In-Memory technologies. This technical report presents results of research projects executed in 2017. Selected projects have presented their results on April 25th and November 15th 2017 at the Future SOC Lab Day events.}, language = {en} } @book{RanaMohapatraSidorovaetal.2022, author = {Rana, Kaushik and Mohapatra, Durga Prasad and Sidorova, Julia and Lundberg, Lars and Sk{\"o}ld, Lars and Lopes Grim, Lu{\´i}s Fernando and Sampaio Gradvohl, Andr{\´e} Leon and Cremerius, Jonas and Siegert, Simon and Weltzien, Anton von and Baldi, Annika and Klessascheck, Finn and Kalancha, Svitlana and Lichtenstein, Tom and Shaabani, Nuhad and Meinel, Christoph and Friedrich, Tobias and Lenzner, Pascal and Schumann, David and Wiese, Ingmar and Sarna, Nicole and Wiese, Lena and Tashkandi, Araek Sami and van der Walt, Est{\´e}e and Eloff, Jan H. P. and Schmidt, Christopher and H{\"u}gle, Johannes and Horschig, Siegfried and Uflacker, Matthias and Najafi, Pejman and Sapegin, Andrey and Cheng, Feng and Stojanovic, Dragan and Stojnev Ilić, Aleksandra and Djordjevic, Igor and Stojanovic, Natalija and Predic, Bratislav and Gonz{\´a}lez-Jim{\´e}nez, Mario and de Lara, Juan and Mischkewitz, Sven and Kainz, Bernhard and van Hoorn, Andr{\´e} and Ferme, Vincenzo and Schulz, Henning and Knigge, Marlene and Hecht, Sonja and Prifti, Loina and Krcmar, Helmut and Fabian, Benjamin and Ermakova, Tatiana and Kelkel, Stefan and Baumann, Annika and Morgenstern, Laura and Plauth, Max and Eberhard, Felix and Wolff, Felix and Polze, Andreas and Cech, Tim and Danz, Noel and Noack, Nele Sina and Pirl, Lukas and Beilharz, Jossekin Jakob and De Oliveira, Roberto C. L. and Soares, F{\´a}bio Mendes and Juiz, Carlos and Bermejo, Belen and M{\"u}hle, Alexander and Gr{\"u}ner, Andreas and Saxena, Vageesh and Gayvoronskaya, Tatiana and Weyand, Christopher and Krause, Mirko and Frank, Markus and Bischoff, Sebastian and Behrens, Freya and R{\"u}ckin, Julius and Ziegler, Adrian and Vogel, Thomas and Tran, Chinh and Moser, Irene and Grunske, Lars and Sz{\´a}rnyas, G{\´a}bor and Marton, J{\´o}zsef and Maginecz, J{\´a}nos and Varr{\´o}, D{\´a}niel and Antal, J{\´a}nos Benjamin}, title = {HPI Future SOC Lab - Proceedings 2018}, number = {151}, editor = {Meinel, Christoph and Polze, Andreas and Beins, Karsten and Strotmann, Rolf and Seibold, Ulrich and R{\"o}dszus, Kurt and M{\"u}ller, J{\"u}rgen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-547-7}, issn = {1613-5652}, doi = {10.25932/publishup-56371}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-563712}, publisher = {Universit{\"a}t Potsdam}, pages = {x, 277}, year = {2022}, abstract = {The "HPI Future SOC Lab" is a cooperation of the Hasso Plattner Institute (HPI) and industry partners. Its mission is to enable and promote exchange and interaction between the research community and the industry partners. The HPI Future SOC Lab provides researchers with free of charge access to a complete infrastructure of state of the art hard and software. This infrastructure includes components, which might be too expensive for an ordinary research environment, such as servers with up to 64 cores and 2 TB main memory. The offerings address researchers particularly from but not limited to the areas of computer science and business information systems. Main areas of research include cloud computing, parallelization, and In-Memory technologies. This technical report presents results of research projects executed in 2018. Selected projects have presented their results on April 17th and November 14th 2017 at the Future SOC Lab Day events.}, language = {en} } @phdthesis{Cheng2018, author = {Cheng, Lung-Pan}, title = {Human actuation}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-418371}, school = {Universit{\"a}t Potsdam}, pages = {xiv, 85}, year = {2018}, abstract = {Ever since the conception of the virtual reality headset in 1968, many researchers have argued that the next step in virtual reality is to allow users to not only see and hear, but also feel virtual worlds. One approach is to use mechanical equipment to provide haptic feedback, e.g., robotic arms, exoskeletons and motion platforms. However, the size and the weight of such mechanical equipment tends to be proportional to its target's size and weight, i.e., providing human-scale haptic feedback requires human-scale equipment, often restricting them to arcades and lab environments. The key idea behind this dissertation is to bypass mechanical equipment by instead leveraging human muscle power. We thus create software systems that orchestrate humans in doing such mechanical labor—this is what we call human actuation. A potential benefit of such systems is that humans are more generic, flexible, and versatile than machines. This brings a wide range of haptic feedback to modern virtual reality systems. We start with a proof-of-concept system—Haptic Turk, focusing on delivering motion experiences just like a motion platform. All Haptic Turk setups consist of a user who is supported by one or more human actuators. The user enjoys an interactive motion simulation such as a hang glider experience, but the motion is generated by those human actuators who manually lift, tilt, and push the user's limbs or torso. To get the timing and force right, timed motion instructions in a format familiar from rhythm games are generated by the system. Next, we extend the concept of human actuation from 3-DoF to 6-DoF virtual reality where users have the freedom to walk around. TurkDeck tackles this problem by orchestrating a group of human actuators to reconfigure a set of passive props on the fly while the user is progressing in the virtual environment. TurkDeck schedules human actuators by their distances from the user, and instructs them to reconfigure the props to the right place on the right time using laser projection and voice output. Our studies in Haptic Turk and TurkDeck showed that human actuators enjoyed the experience but not as much as users. To eliminate the need of dedicated human actuators, Mutual Turk makes everyone a user by exchanging mechanical actuation between two or more users. Mutual Turk's main functionality is that it orchestrates the users so as to actuate props at just the right moment and with just the right force to produce the correct feedback in each other's experience. Finally, we further eliminate the need of another user, making human actuation applicable to single-user experiences. iTurk makes the user constantly reconfigure and animate otherwise passive props. This allows iTurk to provide virtual worlds with constantly varying or even animated haptic effects, even though the only animate entity present in the system is the user. Our demo experience features one example each of iTurk's two main types of props, i.e., reconfigurable props (the foldable board from TurkDeck) and animated props (the pendulum). We conclude this dissertation by summarizing the findings of our explorations and pointing out future directions. We discuss the development of human actuation compare to traditional machine actuation, the possibility of combining human and machine actuators and interaction models that involve more human actuators.}, language = {en} } @book{Weber2023, author = {Weber, Benedikt}, title = {Human pose estimation for decubitus prophylaxis}, number = {153}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-551-4}, issn = {1613-5652}, doi = {10.25932/publishup-56719}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-567196}, publisher = {Universit{\"a}t Potsdam}, pages = {73}, year = {2023}, abstract = {Decubitus is one of the most relevant diseases in nursing and the most expensive to treat. It is caused by sustained pressure on tissue, so it particularly affects bed-bound patients. This work lays a foundation for pressure mattress-based decubitus prophylaxis by implementing a solution to the single-frame 2D Human Pose Estimation problem. For this, methods of Deep Learning are employed. Two approaches are examined, a coarse-to-fine Convolutional Neural Network for direct regression of joint coordinates and a U-Net for the derivation of probability distribution heatmaps. We conclude that training our models on a combined dataset of the publicly available Bodies at Rest and SLP data yields the best results. Furthermore, various preprocessing techniques are investigated, and a hyperparameter optimization is performed to discover an improved model architecture. Another finding indicates that the heatmap-based approach outperforms direct regression. This model achieves a mean per-joint position error of 9.11 cm for the Bodies at Rest data and 7.43 cm for the SLP data. We find that it generalizes well on data from mattresses other than those seen during training but has difficulties detecting the arms correctly. Additionally, we give a brief overview of the medical data annotation tool annoto we developed in the bachelor project and furthermore conclude that the Scrum framework and agile practices enhanced our development workflow.}, language = {en} } @phdthesis{Kovacs2022, author = {Kov{\´a}cs, R{\´o}bert}, title = {Human-scale personal fabrication}, doi = {10.25932/publishup-55539}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-555398}, school = {Universit{\"a}t Potsdam}, pages = {139}, year = {2022}, abstract = {The availability of commercial 3D printers and matching 3D design software has allowed a wide range of users to create physical prototypes - as long as these objects are not larger than hand size. However, when attempting to create larger, "human-scale" objects, such as furniture, not only are these machines too small, but also the commonly used 3D design software is not equipped to design with forces in mind — since forces increase disproportionately with scale. In this thesis, we present a series of end-to-end fabrication software systems that support users in creating human-scale objects. They achieve this by providing three main functions that regular "small-scale" 3D printing software does not offer: (1) subdivision of the object into small printable components combined with ready-made objects, (2) editing based on predefined elements sturdy enough for larger scale, i.e., trusses, and (3) functionality for analyzing, detecting, and fixing structural weaknesses. The presented software systems also assist the fabrication process based on either 3D printing or steel welding technology. The presented systems focus on three levels of engineering challenges: (1) fabricating static load-bearing objects, (2) creating mechanisms that involve motion, such as kinematic installations, and finally (3) designing mechanisms with dynamic repetitive movement where power and energy play an important role. We demonstrate and verify the versatility of our systems by building and testing human-scale prototypes, ranging from furniture pieces, pavilions, to animatronic installations and playground equipment. We have also shared our system with schools, fablabs, and fabrication enthusiasts, who have successfully created human-scale objects that can withstand with human-scale forces.}, language = {en} } @article{KoskinenKairikkoSuonpaeae2021, author = {Koskinen, Johanna and Kairikko, Anette and Suonp{\"a}{\"a}, Maija}, title = {Hybrid MOOCs Enabling Global Collaboration Between Learners}, series = {EMOOCs 2021}, journal = {EMOOCs 2021}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51691}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-516917}, pages = {35 -- 48}, year = {2021}, abstract = {The COVID-19 pandemic has accelerated the pace of digital transformation, which has forced people to quickly adapt to working and collaborating online. Learning in digital environments has without a doubt gained increased significance during this rather unique time and, therefore, Massive Open Online Courses (MOOCs) have more potential to attract a wider target audience. This has also brought about more possibilities for global collaboration among learners as learning is not limited to physical spaces. Despite the wide interest in MOOCs, there is a need for further research on the global collaboration potential they offer. The aim of this paper is to adopt an action research approach to study how a hybrid MOOC design enables learners' global collaboration. During the years 2019-2020 together with an international consortium called Corship (Corporate Edupreneurship) we jointly designed, created and implemented a hybrid model MOOC, called the "Co-innovation Journey for Startups and Corporates". It was targeted towards startup entrepreneurs, corporate representatives and higher education students and it was funded by the EU. The MOOC started with 2,438 enrolled learners and the completion rate for the first four weeks was 29.7\%. Out of these 208 learners enrolled for the last two weeks, which in turn had a completion rate of 58\%. These figures were clearly above the general average for MOOCs. According to our findings, we argue that a hybrid MOOC design may foster global collaboration within a learning community even beyond the course boundaries. The course included four weeks of independent learning, an xMOOC part, and two weeks of collaborative learning, a cMOOC part. The xMOOC part supported learners in creating a shared knowledge base, which enhanced the collaborative learning when entering the cMOOC part of the course.}, language = {en} } @misc{MontiRautenstrauchGhanbarietal.2022, author = {Monti, Remo and Rautenstrauch, Pia and Ghanbari, Mahsa and Rani James, Alva and Kirchler, Matthias and Ohler, Uwe and Konigorski, Stefan and Lippert, Christoph}, title = {Identifying interpretable gene-biomarker associations with functionally informed kernel-based tests in 190,000 exomes}, series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, journal = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, number = {16}, doi = {10.25932/publishup-58607}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-586078}, pages = {16}, year = {2022}, abstract = {Here we present an exome-wide rare genetic variant association study for 30 blood biomarkers in 191,971 individuals in the UK Biobank. We compare gene- based association tests for separate functional variant categories to increase interpretability and identify 193 significant gene-biomarker associations. Genes associated with biomarkers were ~ 4.5-fold enriched for conferring Mendelian disorders. In addition to performing weighted gene-based variant collapsing tests, we design and apply variant-category-specific kernel-based tests that integrate quantitative functional variant effect predictions for mis- sense variants, splicing and the binding of RNA-binding proteins. For these tests, we present a computationally efficient combination of the likelihood- ratio and score tests that found 36\% more associations than the score test alone while also controlling the type-1 error. Kernel-based tests identified 13\% more associations than their gene-based collapsing counterparts and had advantages in the presence of gain of function missense variants. We introduce local collapsing by amino acid position for missense variants and use it to interpret associations and identify potential novel gain of function variants in PIEZO1. Our results show the benefits of investigating different functional mechanisms when performing rare-variant association tests, and demonstrate pervasive rare-variant contribution to biomarker variability.}, language = {en} } @phdthesis{Shekhar2023, author = {Shekhar, Sumit}, title = {Image and video processing based on intrinsic attributes}, doi = {10.25932/publishup-62004}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-620049}, school = {Universit{\"a}t Potsdam}, pages = {xii, 143}, year = {2023}, abstract = {Advancements in computer vision techniques driven by machine learning have facilitated robust and efficient estimation of attributes such as depth, optical flow, albedo, and shading. To encapsulate all such underlying properties associated with images and videos, we evolve the concept of intrinsic images towards intrinsic attributes. Further, rapid hardware growth in the form of high-quality smartphone cameras, readily available depth sensors, mobile GPUs, or dedicated neural processing units have made image and video processing pervasive. In this thesis, we explore the synergies between the above two advancements and propose novel image and video processing techniques and systems based on them. To begin with, we investigate intrinsic image decomposition approaches and analyze how they can be implemented on mobile devices. We propose an approach that considers not only diffuse reflection but also specular reflection; it allows us to decompose an image into specularity, albedo, and shading on a resource constrained system (e.g., smartphones or tablets) using the depth data provided by the built-in depth sensors. In addition, we explore how on-device depth data can further be used to add an immersive dimension to 2D photos, e.g., showcasing parallax effects via 3D photography. In this regard, we develop a novel system for interactive 3D photo generation and stylization on mobile devices. Further, we investigate how adaptive manipulation of baseline-albedo (i.e., chromaticity) can be used for efficient visual enhancement under low-lighting conditions. The proposed technique allows for interactive editing of enhancement settings while achieving improved quality and performance. We analyze the inherent optical flow and temporal noise as intrinsic properties of a video. We further propose two new techniques for applying the above intrinsic attributes for the purpose of consistent video filtering. To this end, we investigate how to remove temporal inconsistencies perceived as flickering artifacts. One of the techniques does not require costly optical flow estimation, while both provide interactive consistency control. Using intrinsic attributes for image and video processing enables new solutions for mobile devices - a pervasive visual computing device - and will facilitate novel applications for Augmented Reality (AR), 3D photography, and video stylization. The proposed low-light enhancement techniques can also improve the accuracy of high-level computer vision tasks (e.g., face detection) under low-light conditions. Finally, our approach for consistent video filtering can extend a wide range of image-based processing for videos.}, language = {en} } @article{EbnerEdelsbrunnerHohlaSejkoraetal.2023, author = {Ebner, Martin and Edelsbrunner, Sarah and Hohla-Sejkora, Katharina and Mair, Bettina and Sch{\"o}n, Sandra and Lipp, Silvia and Steinkellner, Iris and Stojcevic, Ivana and Zwiauer, Charlotte}, title = {Impact assessment of a MOOC platform}, series = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, journal = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, editor = {Meinel, Christoph and Schweiger, Stefanie and Staubitz, Thomas and Conrad, Robert and Alario Hoyos, Carlos and Ebner, Martin and Sancassani, Susanna and Żur, Agnieszka and Friedl, Christian and Halawa, Sherif and Gamage, Dilrukshi and Scott, Jeffrey and Kristine Jonson Carlon, May and Deville, Yves and Gaebel, Michael and Delgado Kloos, Carlos and von Schmieden, Karen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-62422}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-624222}, pages = {171 -- 186}, year = {2023}, abstract = {In 2020, the project "iMooX - The MOOC Platform as a Service for all Austrian Universities" was launched. It is co-financed by the Austrian Ministry of Education, Science and Research. After half of the funding period, the project management wants to assess and share results and outcomes but also address (potential) additional "impacts" of the MOOC platform. Building upon work on OER impact assessment, this contribution describes in detail how the specific iMooX.at approach of impact measurement was developed. Literature review, stakeholder analysis, and problem-based interviews were the base for developing a questionnaire addressing the defined key stakeholder "MOOC creators". The article also presents the survey results in English for the first time but focuses more on the development, strengths, and weaknesses of the selected methods. The article is seen as a contribution to the further development of impact assessment for MOOC platforms.}, language = {en} } @article{vanEsvelddeVriesBecchettietal.2023, author = {van Esveld, Selma and de Vries, Nardo and Becchetti, Sibilla and Dopper, Sofia and van Valkenburg, Willem}, title = {Impact of Mooc and Other Online Course Development on Campus Education}, series = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, journal = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, editor = {Meinel, Christoph and Schweiger, Stefanie and Staubitz, Thomas and Conrad, Robert and Alario Hoyos, Carlos and Ebner, Martin and Sancassani, Susanna and Żur, Agnieszka and Friedl, Christian and Halawa, Sherif and Gamage, Dilrukshi and Cross, Jeffrey and Kristine Jonson Carlon, May and Deville, Yves and Gaebel, Michael and Delgado Kloos, Carlos and von Schmieden, Karen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-62078}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-620785}, pages = {1 -- 8}, year = {2023}, abstract = {The TU Delft Extension School for Continuing Education develops and delivers MOOCs, programs and other online courses for lifelong learners and professionals worldwide focused on Science, Engineering \& Design. At the beginning of 2022, we started a project to examine whether creating an online course had any impact on TU Delft campus education. Through a survey, we collected feedback from 68 TU Delft lecturers involved in developing and offering online courses and programs for lifelong learners and professionals. The lecturers reported on the impact of developing an online course on a personal and curricular level. The results showed that the developed online materials, and the acquired skills and experiences from creating online courses, were beneficial for campus education, especially during the transition to remote emergency teaching in the COVID-19 lockdown periods. In this short paper, we will describe the responses in detail and map the benefits and challenges experienced by lecturers when implementing their online course materials and newly acquired educational skills on campus. Finally, we will explore future possibilities to extend the reported, already relevant, impact of MOOCs and of other online courses on campus education.}, language = {en} } @book{FreundRaetschHradilaketal.2022, author = {Freund, Rieke and R{\"a}tsch, Jan Philip and Hradilak, Franziska and Vidic, Benedikt and Heß, Oliver and Lißner, Nils and W{\"o}lert, Hendrik and Lincke, Jens and Beckmann, Tom and Hirschfeld, Robert}, title = {Implementing a crowd-sourced picture archive for Bad Harzburg}, number = {149}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-545-3}, issn = {1613-5652}, doi = {10.25932/publishup-56029}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-560291}, publisher = {Universit{\"a}t Potsdam}, pages = {x, 191}, year = {2022}, abstract = {Pictures are a medium that helps make the past tangible and preserve memories. Without context, they are not able to do so. Pictures are brought to life by their associated stories. However, the older pictures become, the fewer contemporary witnesses can tell these stories. Especially for large, analog picture archives, knowledge and memories are spread over many people. This creates several challenges: First, the pictures must be digitized to save them from decaying and make them available to the public. Since a simple listing of all the pictures is confusing, the pictures should be structured accessibly. Second, known information that makes the stories vivid needs to be added to the pictures. Users should get the opportunity to contribute their knowledge and memories. To make this usable for all interested parties, even for older, less technophile generations, the interface should be intuitive and error-tolerant. The resulting requirements are not covered in their entirety by any existing software solution without losing the intuitive interface or the scalability of the system. Therefore, we have developed our digital picture archive within the scope of a bachelor project in cooperation with the Bad Harzburg-Stiftung. For the implementation of this web application, we use the UI framework React in the frontend, which communicates via a GraphQL interface with the Content Management System Strapi in the backend. The use of this system enables our project partner to create an efficient process from scanning analog pictures to presenting them to visitors in an organized and annotated way. To customize the solution for both picture delivery and information contribution for our target group, we designed prototypes and evaluated them with people from Bad Harzburg. This helped us gain valuable insights into our system's usability and future challenges as well as requirements. Our web application is already being used daily by our project partner. During the project, we still came up with numerous ideas for additional features to further support the exchange of knowledge.}, language = {en} } @misc{KonakWegnerArnrich2021, author = {Konak, Orhan and Wegner, Pit and Arnrich, Bert}, title = {IMU-Based Movement Trajectory Heatmaps for Human Activity Recognition}, series = {Postprints der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, journal = {Postprints der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, number = {4}, doi = {10.25932/publishup-48779}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-487799}, pages = {17}, year = {2021}, abstract = {Recent trends in ubiquitous computing have led to a proliferation of studies that focus on human activity recognition (HAR) utilizing inertial sensor data that consist of acceleration, orientation and angular velocity. However, the performances of such approaches are limited by the amount of annotated training data, especially in fields where annotating data is highly time-consuming and requires specialized professionals, such as in healthcare. In image classification, this limitation has been mitigated by powerful oversampling techniques such as data augmentation. Using this technique, this work evaluates to what extent transforming inertial sensor data into movement trajectories and into 2D heatmap images can be advantageous for HAR when data are scarce. A convolutional long short-term memory (ConvLSTM) network that incorporates spatiotemporal correlations was used to classify the heatmap images. Evaluation was carried out on Deep Inertial Poser (DIP), a known dataset composed of inertial sensor data. The results obtained suggest that for datasets with large numbers of subjects, using state-of-the-art methods remains the best alternative. However, a performance advantage was achieved for small datasets, which is usually the case in healthcare. Moreover, movement trajectories provide a visual representation of human activities, which can help researchers to better interpret and analyze motion patterns.}, language = {en} } @phdthesis{Ghahremani2024, author = {Ghahremani, Sona}, title = {Incremental self-adaptation of dynamic architectures attaining optimality and scalability}, doi = {10.25932/publishup-62423}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-624232}, school = {Universit{\"a}t Potsdam}, pages = {xii, 285}, year = {2024}, abstract = {The landscape of software self-adaptation is shaped in accordance with the need to cost-effectively achieve and maintain (software) quality at runtime and in the face of dynamic operation conditions. Optimization-based solutions perform an exhaustive search in the adaptation space, thus they may provide quality guarantees. However, these solutions render the attainment of optimal adaptation plans time-intensive, thereby hindering scalability. Conversely, deterministic rule-based solutions yield only sub-optimal adaptation decisions, as they are typically bound by design-time assumptions, yet they offer efficient processing and implementation, readability, expressivity of individual rules supporting early verification. Addressing the quality-cost trade-of requires solutions that simultaneously exhibit the scalability and cost-efficiency of rulebased policy formalism and the optimality of optimization-based policy formalism as explicit artifacts for adaptation. Utility functions, i.e., high-level specifications that capture system objectives, support the explicit treatment of quality-cost trade-off. Nevertheless, non-linearities, complex dynamic architectures, black-box models, and runtime uncertainty that makes the prior knowledge obsolete are a few of the sources of uncertainty and subjectivity that render the elicitation of utility non-trivial. This thesis proposes a twofold solution for incremental self-adaptation of dynamic architectures. First, we introduce Venus, a solution that combines in its design a ruleand an optimization-based formalism enabling optimal and scalable adaptation of dynamic architectures. Venus incorporates rule-like constructs and relies on utility theory for decision-making. Using a graph-based representation of the architecture, Venus captures rules as graph patterns that represent architectural fragments, thus enabling runtime extensibility and, in turn, support for dynamic architectures; the architecture is evaluated by assigning utility values to fragments; pattern-based definition of rules and utility enables incremental computation of changes on the utility that result from rule executions, rather than evaluating the complete architecture, which supports scalability. Second, we introduce HypeZon, a hybrid solution for runtime coordination of multiple off-the-shelf adaptation policies, which typically offer only partial satisfaction of the quality and cost requirements. Realized based on meta-self-aware architectures, HypeZon complements Venus by re-using existing policies at runtime for balancing the quality-cost trade-off. The twofold solution of this thesis is integrated in an adaptation engine that leverages state- and event-based principles for incremental execution, therefore, is scalable for large and dynamic software architectures with growing size and complexity. The utility elicitation challenge is resolved by defining a methodology to train utility-change prediction models. The thesis addresses the quality-cost trade-off in adaptation of dynamic software architectures via design-time combination (Venus) and runtime coordination (HypeZon) of rule- and optimization-based policy formalisms, while offering supporting mechanisms for optimal, cost-effective, scalable, and robust adaptation. The solutions are evaluated according to a methodology that is obtained based on our systematic literature review of evaluation in self-healing systems; the applicability and effectiveness of the contributions are demonstrated to go beyond the state-of-the-art in coverage of a wide spectrum of the problem space for software self-adaptation.}, language = {en} } @article{AlarioHoyosDelgadoKloosKiendletal.2023, author = {Alario Hoyos, Carlos and Delgado Kloos, Carlos and Kiendl, Doris and Terzieva, Liliya}, title = {Innovat MOOC}, series = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, journal = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, editor = {Meinel, Christoph and Schweiger, Stefanie and Staubitz, Thomas and Conrad, Robert and Alario Hoyos, Carlos and Ebner, Martin and Sancassani, Susanna and Żur, Agnieszka and Friedl, Christian and Halawa, Sherif and Gamage, Dilrukshi and Scott, Jeffrey and Kristine Jonson Carlon, May and Deville, Yves and Gaebel, Michael and Delgado Kloos, Carlos and von Schmieden, Karen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-62456}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-624560}, pages = {229 -- 237}, year = {2023}, abstract = {The COVID-19 pandemic has revealed the importance for university teachers to have adequate pedagogical and technological competences to cope with the various possible educational scenarios (face-to-face, online, hybrid, etc.), making use of appropriate active learning methodologies and supporting technologies to foster a more effective learning environment. In this context, the InnovaT project has been an important initiative to support the development of pedagogical and technological competences of university teachers in Latin America through several trainings aiming to promote teacher innovation. These trainings combined synchronous online training through webinars and workshops with asynchronous online training through the MOOC "Innovative Teaching in Higher Education." This MOOC was released twice. The first run took place right during the lockdown of 2020, when Latin American teachers needed urgent training to move to emergency remote teaching overnight. The second run took place in 2022 with the return to face-to-face teaching and the implementation of hybrid educational models. This article shares the results of the design of the MOOC considering the constraints derived from the lockdowns applied in each country, the lessons learned from the delivery of such a MOOC to Latin American university teachers, and the results of the two runs of the MOOC.}, language = {en} } @article{KhlaisangDuangchindaThammetaretal.2023, author = {Khlaisang, Jintavee and Duangchinda, Vorasuang and Thammetar, Thapanee and Theeraroungchaisri, Anuchai}, title = {Instructional design for work-based skill MOOCs}, series = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, journal = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, editor = {Meinel, Christoph and Schweiger, Stefanie and Staubitz, Thomas and Conrad, Robert and Alario Hoyos, Carlos and Ebner, Martin and Sancassani, Susanna and Żur, Agnieszka and Friedl, Christian and Halawa, Sherif and Gamage, Dilrukshi and Scott, Jeffrey and Kristine Jonson Carlon, May and Deville, Yves and Gaebel, Michael and Delgado Kloos, Carlos and von Schmieden, Karen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-62431}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-624318}, pages = {221 -- 227}, year = {2023}, abstract = {As Thailand moves towards becoming an innovation-driven economy, the need for human capital development has become crucial. Work-based skill MOOCs, offered on Thai MOOC, a national digital learning platform launched by Thailand Cyber University Project, ministry of Higher Education, Science, Research and Innovation, provide an effective way to overcome this challenge. This paper discusses the challenges faced in designing an instruction for work-based skill MOOCs that can serve as a foundation model for many more to come. The instructional design of work-based skill courses in Thai MOOC involves four simple steps, including course selection, learning from accredited providers, course requirements completion, and certification of acquired skills. The development of such courses is ongoing at the higher education level, vocational level, and pre-university level, which serve as a foundation model for many more work-based skill MOOC that will be offered on Thai MOOC soon. The instructional design of work-based skills courses should focus on the development of currently demanded professional competencies and skills, increasing the efficiency of work in the organization, creativity, and happiness in life that meets the human resources needs of industries in the 4.0 economy era in Thailand. This paper aims to present the challenges of designing instruction for work-based skill MOOCs and suggests effective ways to design instruction to enhance workforce development in Thailand.}, language = {en} } @phdthesis{Halfpap2024, author = {Halfpap, Stefan}, title = {Integer linear programming-based heuristics for partially replicated database clusters and selecting indexes}, doi = {10.25932/publishup-63361}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-633615}, school = {Universit{\"a}t Potsdam}, pages = {iii, 185}, year = {2024}, abstract = {Column-oriented database systems can efficiently process transactional and analytical queries on a single node. However, increasing or peak analytical loads can quickly saturate single-node database systems. Then, a common scale-out option is using a database cluster with a single primary node for transaction processing and read-only replicas. Using (the naive) full replication, queries are distributed among nodes independently of the accessed data. This approach is relatively expensive because all nodes must store all data and apply all data modifications caused by inserts, deletes, or updates. In contrast to full replication, partial replication is a more cost-efficient implementation: Instead of duplicating all data to all replica nodes, partial replicas store only a subset of the data while being able to process a large workload share. Besides lower storage costs, partial replicas enable (i) better scaling because replicas must potentially synchronize only subsets of the data modifications and thus have more capacity for read-only queries and (ii) better elasticity because replicas have to load less data and can be set up faster. However, splitting the overall workload evenly among the replica nodes while optimizing the data allocation is a challenging assignment problem. The calculation of optimized data allocations in a partially replicated database cluster can be modeled using integer linear programming (ILP). ILP is a common approach for solving assignment problems, also in the context of database systems. Because ILP is not scalable, existing approaches (also for calculating partial allocations) often fall back to simple (e.g., greedy) heuristics for larger problem instances. Simple heuristics may work well but can lose optimization potential. In this thesis, we present optimal and ILP-based heuristic programming models for calculating data fragment allocations for partially replicated database clusters. Using ILP, we are flexible to extend our models to (i) consider data modifications and reallocations and (ii) increase the robustness of allocations to compensate for node failures and workload uncertainty. We evaluate our approaches for TPC-H, TPC-DS, and a real-world accounting workload and compare the results to state-of-the-art allocation approaches. Our evaluations show significant improvements for varied allocation's properties: Compared to existing approaches, we can, for example, (i) almost halve the amount of allocated data, (ii) improve the throughput in case of node failures and workload uncertainty while using even less memory, (iii) halve the costs of data modifications, and (iv) reallocate less than 90\% of data when adding a node to the cluster. Importantly, we can calculate the corresponding ILP-based heuristic solutions within a few seconds. Finally, we demonstrate that the ideas of our ILP-based heuristics are also applicable to the index selection problem.}, language = {en} } @article{PonceSrinathAllegue2021, author = {Ponce, Eva and Srinath, Sindhu and Allegue, Laura}, title = {Integrating Community Teaching in MOOCs}, series = {EMOOCs 2021}, volume = {2021}, journal = {EMOOCs 2021}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51712}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-517123}, pages = {95 -- 109}, year = {2021}, abstract = {The MITx MicroMasters Program in Supply Chain Management (SCM) is a Massive Open Online Course (MOOC) based program that aims to impart quantitative and qualitative knowledge to SCM enthusiasts all around the world. The program that started in 2014 with just one course, now offers 5 courses and one final proctored exam, which allows a learner to gain a MicroMasters credential upon completion. While the courses are delivered in the form of pre-recorded videos by the faculty members of Massachusetts Institute of Technology (MIT), the questions and comments posted by learners in discussion forums are addressed by a group of Community Teaching Assistants (CTAs) who volunteer for this role. The MITx staff carefully selects CTAs for each run of the individual courses as they take on a co-facilitator's role in the program. This paper highlights the importance of community teaching, discusses the profile of CTAs involved with the program, their recruitment, training, tasks and responsibilities, engagement, and rewarding process. In the end we also share a few recommendations based on the lessons learned in community teaching during the last five years of running more than 45 MOOC courses, that could help other MOOC teams deliver a high-touch experience.}, language = {en} } @phdthesis{Perscheid2023, author = {Perscheid, Cindy}, title = {Integrative biomarker detection using prior knowledge on gene expression data sets}, doi = {10.25932/publishup-58241}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-582418}, school = {Universit{\"a}t Potsdam}, pages = {ix, 197}, year = {2023}, abstract = {Gene expression data is analyzed to identify biomarkers, e.g. relevant genes, which serve for diagnostic, predictive, or prognostic use. Traditional approaches for biomarker detection select distinctive features from the data based exclusively on the signals therein, facing multiple shortcomings in regards to overfitting, biomarker robustness, and actual biological relevance. Prior knowledge approaches are expected to address these issues by incorporating prior biological knowledge, e.g. on gene-disease associations, into the actual analysis. However, prior knowledge approaches are currently not widely applied in practice because they are often use-case specific and seldom applicable in a different scope. This leads to a lack of comparability of prior knowledge approaches, which in turn makes it currently impossible to assess their effectiveness in a broader context. Our work addresses the aforementioned issues with three contributions. Our first contribution provides formal definitions for both prior knowledge and the flexible integration thereof into the feature selection process. Central to these concepts is the automatic retrieval of prior knowledge from online knowledge bases, which allows for streamlining the retrieval process and agreeing on a uniform definition for prior knowledge. We subsequently describe novel and generalized prior knowledge approaches that are flexible regarding the used prior knowledge and applicable to varying use case domains. Our second contribution is the benchmarking platform Comprior. Comprior applies the aforementioned concepts in practice and allows for flexibly setting up comprehensive benchmarking studies for examining the performance of existing and novel prior knowledge approaches. It streamlines the retrieval of prior knowledge and allows for combining it with prior knowledge approaches. Comprior demonstrates the practical applicability of our concepts and further fosters the overall development and comparability of prior knowledge approaches. Our third contribution is a comprehensive case study on the effectiveness of prior knowledge approaches. For that, we used Comprior and tested a broad range of both traditional and prior knowledge approaches in combination with multiple knowledge bases on data sets from multiple disease domains. Ultimately, our case study constitutes a thorough assessment of a) the suitability of selected knowledge bases for integration, b) the impact of prior knowledge being applied at different integration levels, and c) the improvements in terms of classification performance, biological relevance, and overall robustness. In summary, our contributions demonstrate that generalized concepts for prior knowledge and a streamlined retrieval process improve the applicability of prior knowledge approaches. Results from our case study show that the integration of prior knowledge positively affects biomarker results, particularly regarding their robustness. Our findings provide the first in-depth insights on the effectiveness of prior knowledge approaches and build a valuable foundation for future research.}, language = {en} } @phdthesis{Lopes2018, author = {Lopes, Pedro}, title = {Interactive Systems Based on Electrical Muscle Stimulation}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-421165}, school = {Universit{\"a}t Potsdam}, pages = {171}, year = {2018}, abstract = {How can interactive devices connect with users in the most immediate and intimate way? This question has driven interactive computing for decades. Throughout the last decades, we witnessed how mobile devices moved computing into users' pockets, and recently, wearables put computing in constant physical contact with the user's skin. In both cases moving the devices closer to users allowed devices to sense more of the user, and thus act more personal. The main question that drives our research is: what is the next logical step? Some researchers argue that the next generation of interactive devices will move past the user's skin and be directly implanted inside the user's body. This has already happened in that we have pacemakers, insulin pumps, etc. However, we argue that what we see is not devices moving towards the inside of the user's body, but rather towards the body's biological "interface" they need to address in order to perform their function. To implement our vision, we created a set of devices that intentionally borrow parts of the user's body for input and output, rather than adding more technology to the body. In this dissertation we present one specific flavor of such devices, i.e., devices that borrow the user's muscles. We engineered I/O devices that interact with the user by reading and controlling muscle activity. To achieve the latter, our devices are based on medical-grade signal generators and electrodes attached to the user's skin that send electrical impulses to the user's muscles; these impulses then cause the user's muscles to contract. While electrical muscle stimulation (EMS) devices have been used to regenerate lost motor functions in rehabilitation medicine since the 1960s, in this dissertation, we propose a new perspective: EMS as a means for creating interactive systems. We start by presenting seven prototypes of interactive devices that we have created to illustrate several benefits of EMS. These devices form two main categories: (1) Devices that allow users eyes-free access to information by means of their proprioceptive sense, such as the value of a variable in a computer system, a tool, or a plot; (2) Devices that increase immersion in virtual reality by simulating large forces, such as wind, physical impact, or walls and heavy objects. Then, we analyze the potential of EMS to build interactive systems that miniaturize well and discuss how they leverage our proprioceptive sense as an I/O modality. We proceed by laying out the benefits and disadvantages of both EMS and mechanical haptic devices, such as exoskeletons. We conclude by sketching an outline for future research on EMS by listing open technical, ethical and philosophical questions that we left unanswered.}, language = {en} } @book{MaximovaSchneiderGiese2021, author = {Maximova, Maria and Schneider, Sven and Giese, Holger}, title = {Interval probabilistic timed graph transformation systems}, number = {134}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-502-6}, issn = {1613-5652}, doi = {10.25932/publishup-51289}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-512895}, publisher = {Universit{\"a}t Potsdam}, pages = {58}, year = {2021}, abstract = {The formal modeling and analysis is of crucial importance for software development processes following the model based approach. We present the formalism of Interval Probabilistic Timed Graph Transformation Systems (IPTGTSs) as a high-level modeling language. This language supports structure dynamics (based on graph transformation), timed behavior (based on clocks, guards, resets, and invariants as in Timed Automata (TA)), and interval probabilistic behavior (based on Discrete Interval Probability Distributions). That is, for the probabilistic behavior, the modeler using IPTGTSs does not need to provide precise probabilities, which are often impossible to obtain, but rather provides a probability range instead from which a precise probability is chosen nondeterministically. In fact, this feature on capturing probabilistic behavior distinguishes IPTGTSs from Probabilistic Timed Graph Transformation Systems (PTGTSs) presented earlier. Following earlier work on Interval Probabilistic Timed Automata (IPTA) and PTGTSs, we also provide an analysis tool chain for IPTGTSs based on inter-formalism transformations. In particular, we provide in our tool AutoGraph a translation of IPTGTSs to IPTA and rely on a mapping of IPTA to Probabilistic Timed Automata (PTA) to allow for the usage of the Prism model checker. The tool Prism can then be used to analyze the resulting PTA w.r.t. probabilistic real-time queries asking for worst-case and best-case probabilities to reach a certain set of target states in a given amount of time.}, language = {en} } @book{SchneiderMaximovaGiese2022, author = {Schneider, Sven and Maximova, Maria and Giese, Holger}, title = {Invariant Analysis for Multi-Agent Graph Transformation Systems using k-Induction}, number = {143}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-531-6}, issn = {1613-5652}, doi = {10.25932/publishup-54585}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-545851}, publisher = {Universit{\"a}t Potsdam}, pages = {37}, year = {2022}, abstract = {The analysis of behavioral models such as Graph Transformation Systems (GTSs) is of central importance in model-driven engineering. However, GTSs often result in intractably large or even infinite state spaces and may be equipped with multiple or even infinitely many start graphs. To mitigate these problems, static analysis techniques based on finite symbolic representations of sets of states or paths thereof have been devised. We focus on the technique of k-induction for establishing invariants specified using graph conditions. To this end, k-induction generates symbolic paths backwards from a symbolic state representing a violation of a candidate invariant to gather information on how that violation could have been reached possibly obtaining contradictions to assumed invariants. However, GTSs where multiple agents regularly perform actions independently from each other cannot be analyzed using this technique as of now as the independence among backward steps may prevent the gathering of relevant knowledge altogether. In this paper, we extend k-induction to GTSs with multiple agents thereby supporting a wide range of additional GTSs. As a running example, we consider an unbounded number of shuttles driving on a large-scale track topology, which adjust their velocity to speed limits to avoid derailing. As central contribution, we develop pruning techniques based on causality and independence among backward steps and verify that k-induction remains sound under this adaptation as well as terminates in cases where it did not terminate before.}, language = {en} }