@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{Ziehe2005, author = {Ziehe, Andreas}, title = {Blind source separation based on joint diagonalization of matrices with applications in biomedical signal processing}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-5694}, school = {Universit{\"a}t Potsdam}, year = {2005}, abstract = {This thesis is concerned with the solution of the blind source separation problem (BSS). The BSS problem occurs frequently in various scientific and technical applications. In essence, it consists in separating meaningful underlying components out of a mixture of a multitude of superimposed signals. In the recent research literature there are two related approaches to the BSS problem: The first is known as Independent Component Analysis (ICA), where the goal is to transform the data such that the components become as independent as possible. The second is based on the notion of diagonality of certain characteristic matrices derived from the data. Here the goal is to transform the matrices such that they become as diagonal as possible. In this thesis we study the latter method of approximate joint diagonalization (AJD) to achieve a solution of the BSS problem. After an introduction to the general setting, the thesis provides an overview on particular choices for the set of target matrices that can be used for BSS by joint diagonalization. As the main contribution of the thesis, new algorithms for approximate joint diagonalization of several matrices with non-orthogonal transformations are developed. These newly developed algorithms will be tested on synthetic benchmark datasets and compared to other previous diagonalization algorithms. Applications of the BSS methods to biomedical signal processing are discussed and exemplified with real-life data sets of multi-channel biomagnetic recordings.}, subject = {Signaltrennung}, 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} } @article{XuRazaghiMoghadamNikoloski2021, author = {Xu, Rudan and Razaghi-Moghadam, Zahra and Nikoloski, Zoran}, title = {Maximization of non-idle enzymes improves the coverage of the estimated maximal in vivo enzyme catalytic rates in Escherichia coli}, series = {Bioinformatics}, volume = {37}, journal = {Bioinformatics}, number = {21}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1367-4803}, doi = {10.1093/bioinformatics/btab575}, pages = {3848 -- 3855}, year = {2021}, abstract = {Motivation: Constraint-based modeling approaches allow the estimation of maximal in vivo enzyme catalytic rates that can serve as proxies for enzyme turnover numbers. Yet, genome-scale flux profiling remains a challenge in deploying these approaches to catalogue proxies for enzyme catalytic rates across organisms. Results: Here, we formulate a constraint-based approach, termed NIDLE-flux, to estimate fluxes at a genome-scale level by using the principle of efficient usage of expressed enzymes. Using proteomics data from Escherichia coli, we show that the fluxes estimated by NIDLE-flux and the existing approaches are in excellent qualitative agreement (Pearson correlation > 0.9). We also find that the maximal in vivo catalytic rates estimated by NIDLE-flux exhibits a Pearson correlation of 0.74 with in vitro enzyme turnover numbers. However, NIDLE-flux results in a 1.4-fold increase in the size of the estimated maximal in vivo catalytic rates in comparison to the contenders. Integration of the maximum in vivo catalytic rates with publically available proteomics and metabolomics data provide a better match to fluxes estimated by NIDLE-flux. Therefore, NIDLE-flux facilitates more effective usage of proteomics data to estimate proxies for kcatomes.}, language = {en} } @book{WaetzoldtGiese2015, author = {W{\"a}tzoldt, Sebastian and Giese, Holger}, title = {Modeling collaborations in self-adaptive systems of systems}, number = {96}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-324-4}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-73036}, publisher = {Universit{\"a}t Potsdam}, pages = {72}, year = {2015}, abstract = {An increasing demand on functionality and flexibility leads to an integration of beforehand isolated system solutions building a so-called System of Systems (SoS). Furthermore, the overall SoS should be adaptive to react on changing requirements and environmental conditions. Due SoS are composed of different independent systems that may join or leave the overall SoS at arbitrary point in times, the SoS structure varies during the systems lifetime and the overall SoS behavior emerges from the capabilities of the contained subsystems. In such complex system ensembles new demands of understanding the interaction among subsystems, the coupling of shared system knowledge and the influence of local adaptation strategies to the overall resulting system behavior arise. In this report, we formulate research questions with the focus of modeling interactions between system parts inside a SoS. Furthermore, we define our notion of important system types and terms by retrieving the current state of the art from literature. Having a common understanding of SoS, we discuss a set of typical SoS characteristics and derive general requirements for a collaboration modeling language. Additionally, we retrieve a broad spectrum of real scenarios and frameworks from literature and discuss how these scenarios cope with different characteristics of SoS. Finally, we discuss the state of the art for existing modeling languages that cope with collaborations for different system types such as SoS.}, language = {en} } @phdthesis{Waetzoldt2016, author = {W{\"a}tzoldt, Sebastian}, title = {Modeling collaborations in adaptive systems of systems}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-97494}, school = {Universit{\"a}t Potsdam}, pages = {XII, 380}, year = {2016}, abstract = {Recently, due to an increasing demand on functionality and flexibility, beforehand isolated systems have become interconnected to gain powerful adaptive Systems of Systems (SoS) solutions with an overall robust, flexible and emergent behavior. The adaptive SoS comprises a variety of different system types ranging from small embedded to adaptive cyber-physical systems. On the one hand, each system is independent, follows a local strategy and optimizes its behavior to reach its goals. On the other hand, systems must cooperate with each other to enrich the overall functionality to jointly perform on the SoS level reaching global goals, which cannot be satisfied by one system alone. Due to difficulties of local and global behavior optimizations conflicts may arise between systems that have to be solved by the adaptive SoS. This thesis proposes a modeling language that facilitates the description of an adaptive SoS by considering the adaptation capabilities in form of feedback loops as first class entities. Moreover, this thesis adopts the Models@runtime approach to integrate the available knowledge in the systems as runtime models into the modeled adaptation logic. Furthermore, the modeling language focuses on the description of system interactions within the adaptive SoS to reason about individual system functionality and how it emerges via collaborations to an overall joint SoS behavior. Therefore, the modeling language approach enables the specification of local adaptive system behavior, the integration of knowledge in form of runtime models and the joint interactions via collaboration to place the available adaptive behavior in an overall layered, adaptive SoS architecture. Beside the modeling language, this thesis proposes analysis rules to investigate the modeled adaptive SoS, which enables the detection of architectural patterns as well as design flaws and pinpoints to possible system threats. Moreover, a simulation framework is presented, which allows the direct execution of the modeled SoS architecture. Therefore, the analysis rules and the simulation framework can be used to verify the interplay between systems as well as the modeled adaptation effects within the SoS. This thesis realizes the proposed concepts of the modeling language by mapping them to a state of the art standard from the automotive domain and thus, showing their applicability to actual systems. Finally, the modeling language approach is evaluated by remodeling up to date research scenarios from different domains, which demonstrates that the modeling language concepts are powerful enough to cope with a broad range of existing research problems.}, language = {en} } @phdthesis{Wust2015, author = {Wust, Johannes}, title = {Mixed workload managment for in-memory databases}, pages = {VIII, 167}, year = {2015}, language = {en} } @article{WrightWachsHarper2018, author = {Wright, Michelle F. and Wachs, Sebastian and Harper, Bridgette D.}, title = {The moderation of empathy in the longitudinal association between witnessing cyberbullying, depression, and anxiety}, series = {Journal of Psychosocial Research on Cyberspace}, volume = {12}, journal = {Journal of Psychosocial Research on Cyberspace}, number = {4}, publisher = {Masrykova Univ.}, address = {Brno}, issn = {1802-7962}, doi = {10.5817/CP2018-4-6}, pages = {14}, year = {2018}, abstract = {While the role of and consequences of being a bystander to face-to-face bullying has received some attention in the literature, to date, little is known about the effects of being a bystander to cyberbullying. It is also unknown how empathy might impact the negative consequences associated with being a bystander of cyberbullying. The present study focused on examining the longitudinal association between bystander of cyberbullying depression, and anxiety, and the moderating role of empathy in the relationship between bystander of cyberbullying and subsequent depression and anxiety. There were 1,090 adolescents (M-age = 12.19; 50\% female) from the United States included at Time 1, and they completed questionnaires on empathy, cyberbullying roles (bystander, perpetrator, victim), depression, and anxiety. One year later, at Time 2, 1,067 adolescents (M-age = 13.76; 51\% female) completed questionnaires on depression and anxiety. Results revealed a positive association between bystander of cyberbullying and depression and anxiety. Further, empathy moderated the positive relationship between bystander of cyberbullying and depression, but not for anxiety. Implications for intervention and prevention programs are discussed.}, language = {en} } @misc{WrightWachsHarper2018, author = {Wright, Michelle F. and Wachs, Sebastian and Harper, Bridgette D.}, title = {The moderation of empathy in the longitudinal association between witnessing cyberbullying, depression, and anxiety}, series = {Postprints der Universit{\"a}t Potsdam : Humanwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Humanwissenschaftliche Reihe}, number = {689}, issn = {1866-8364}, doi = {10.25932/publishup-47050}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-470505}, pages = {16}, year = {2018}, abstract = {While the role of and consequences of being a bystander to face-to-face bullying has received some attention in the literature, to date, little is known about the effects of being a bystander to cyberbullying. It is also unknown how empathy might impact the negative consequences associated with being a bystander of cyberbullying. The present study focused on examining the longitudinal association between bystander of cyberbullying depression, and anxiety, and the moderating role of empathy in the relationship between bystander of cyberbullying and subsequent depression and anxiety. There were 1,090 adolescents (M-age = 12.19; 50\% female) from the United States included at Time 1, and they completed questionnaires on empathy, cyberbullying roles (bystander, perpetrator, victim), depression, and anxiety. One year later, at Time 2, 1,067 adolescents (M-age = 13.76; 51\% female) completed questionnaires on depression and anxiety. Results revealed a positive association between bystander of cyberbullying and depression and anxiety. Further, empathy moderated the positive relationship between bystander of cyberbullying and depression, but not for anxiety. Implications for intervention and prevention programs are discussed.}, language = {en} } @phdthesis{Wolff2010, author = {Wolff, Markus}, title = {Geovisual methods and techniques for the development of three-dimensional tactical intelligence assessments}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-50446}, school = {Universit{\"a}t Potsdam}, year = {2010}, abstract = {This thesis presents methods, techniques and tools for developing three-dimensional representations of tactical intelligence assessments. Techniques from GIScience are combined with crime mapping methods. The range of methods applied in this study provides spatio-temporal GIS analysis as well as 3D geovisualisation and GIS programming. The work presents methods to enhance digital three-dimensional city models with application specific thematic information. This information facilitates further geovisual analysis, for instance, estimations of urban risks exposure. Specific methods and workflows are developed to facilitate the integration of spatio-temporal crime scene analysis results into 3D tactical intelligence assessments. Analysis comprises hotspot identification with kernel-density-estimation techniques (KDE), LISA-based verification of KDE hotspots as well as geospatial hotspot area characterisation and repeat victimisation analysis. To visualise the findings of such extensive geospatial analysis, three-dimensional geovirtual environments are created. Workflows are developed to integrate analysis results into these environments and to combine them with additional geospatial data. The resulting 3D visualisations allow for an efficient communication of complex findings of geospatial crime scene 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} } @article{WittigMirandaHoelzeretal.2022, author = {Wittig, Alice and Miranda, Fabio Malcher and H{\"o}lzer, Martin and Altenburg, Tom and Bartoszewicz, Jakub Maciej and Beyvers, Sebastian and Dieckmann, Marius Alfred and Genske, Ulrich and Giese, Sven Hans-Joachim and Nowicka, Melania and Richard, Hugues and Schiebenhoefer, Henning and Schmachtenberg, Anna-Juliane and Sieben, Paul and Tang, Ming and Tembrockhaus, Julius and Renard, Bernhard Y. and Fuchs, Stephan}, title = {CovRadar}, series = {Bioinformatics}, volume = {38}, journal = {Bioinformatics}, number = {17}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1367-4803}, doi = {10.1093/bioinformatics/btac411}, pages = {4223 -- 4225}, year = {2022}, abstract = {The ongoing pandemic caused by SARS-CoV-2 emphasizes the importance of genomic surveillance to understand the evolution of the virus, to monitor the viral population, and plan epidemiological responses. Detailed analysis, easy visualization and intuitive filtering of the latest viral sequences are powerful for this purpose. We present CovRadar, a tool for genomic surveillance of the SARS-CoV-2 Spike protein. CovRadar consists of an analytical pipeline and a web application that enable the analysis and visualization of hundreds of thousand sequences. First, CovRadar extracts the regions of interest using local alignment, then builds a multiple sequence alignment, infers variants and consensus and finally presents the results in an interactive app, making accessing and reporting simple, flexible and fast.}, language = {en} } @book{WistWollowski2007, author = {Wist, Dominic and Wollowski, Ralf}, title = {STG decomposition : avoiding irreducible CSC conflicts by internal communication}, isbn = {978-3-940793-02-7}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-32968}, publisher = {Universit{\"a}t Potsdam}, year = {2007}, abstract = {Inhalt: 1 Introduction 2 Basic Definitions 3 Achieving SI Implementability by Internal Communication 4 Towards a Structural Method 5 Examples 6 Conclusions and Future Work}, language = {en} } @book{WistSchaeferVogleretal.2010, author = {Wist, Dominic and Schaefer, Mark and Vogler, Walter and Wollowski, Ralf}, title = {STG decomposition : internal communication for SI implementability}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-037-3}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-40786}, publisher = {Universit{\"a}t Potsdam}, pages = {36}, year = {2010}, abstract = {STG decomposition is a promising approach to tackle the complexity problems arising in logic synthesis of speed independent circuits, a robust asynchronous (i.e. clockless) circuit type. Unfortunately, STG decomposition can result in components that in isolation have irreducible CSC conflicts. Generalising earlier work, it is shown how to resolve such conflicts by introducing internal communication between the components via structural techniques only.}, language = {en} } @phdthesis{Wist2011, author = {Wist, Dominic}, title = {Attacking complexity in logic synthesis of asynchronous circuits}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-59706}, school = {Universit{\"a}t Potsdam}, year = {2011}, abstract = {Most of the microelectronic circuits fabricated today are synchronous, i.e. they are driven by one or several clock signals. Synchronous circuit design faces several fundamental challenges such as high-speed clock distribution, integration of multiple cores operating at different clock rates, reduction of power consumption and dealing with voltage, temperature, manufacturing and runtime variations. Asynchronous or clockless design plays a key role in alleviating these challenges, however the design and test of asynchronous circuits is much more difficult in comparison to their synchronous counterparts. A driving force for a widespread use of asynchronous technology is the availability of mature EDA (Electronic Design Automation) tools which provide an entire automated design flow starting from an HDL (Hardware Description Language) specification yielding the final circuit layout. Even though there was much progress in developing such EDA tools for asynchronous circuit design during the last two decades, the maturity level as well as the acceptance of them is still not comparable with tools for synchronous circuit design. In particular, logic synthesis (which implies the application of Boolean minimisation techniques) for the entire system's control path can significantly improve the efficiency of the resulting asynchronous implementation, e.g. in terms of chip area and performance. However, logic synthesis, in particular for asynchronous circuits, suffers from complexity problems. Signal Transitions Graphs (STGs) are labelled Petri nets which are a widely used to specify the interface behaviour of speed independent (SI) circuits - a robust subclass of asynchronous circuits. STG decomposition is a promising approach to tackle complexity problems like state space explosion in logic synthesis of SI circuits. The (structural) decomposition of STGs is guided by a partition of the output signals and generates a usually much smaller component STG for each partition member, i.e. a component STG with a much smaller state space than the initial specification. However, decomposition can result in component STGs that in isolation have so-called irreducible CSC conflicts (i.e. these components are not SI synthesisable anymore) even if the specification has none of them. A new approach is presented to avoid such conflicts by introducing internal communication between the components. So far, STG decompositions are guided by the finest output partitions, i.e. one output per component. However, this might not yield optimal circuit implementations. Efficient heuristics are presented to determine coarser partitions leading to improved circuits in terms of chip area. For the new algorithms correctness proofs are given and their implementations are incorporated into the decomposition tool DESIJ. The presented techniques are successfully applied to some benchmarks - including 'real-life' specifications arising in the context of control resynthesis - which delivered promising results.}, language = {en} } @book{WeyandChromikWolfetal.2017, author = {Weyand, Christopher and Chromik, Jonas and Wolf, Lennard and K{\"o}tte, Steffen and Haase, Konstantin and Felgentreff, Tim and Lincke, Jens and Hirschfeld, Robert}, title = {Improving hosted continuous integration services}, number = {108}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-377-0}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-94251}, publisher = {Universit{\"a}t Potsdam}, pages = {viii, 114}, year = {2017}, abstract = {Developing large software projects is a complicated task and can be demanding for developers. Continuous integration is common practice for reducing complexity. By integrating and testing changes often, changesets are kept small and therefore easily comprehensible. Travis CI is a service that offers continuous integration and continuous deployment in the cloud. Software projects are build, tested, and deployed using the Travis CI infrastructure without interrupting the development process. This report describes how Travis CI works, presents how time-driven, periodic building is implemented as well as how CI data visualization can be done, and proposes a way of dealing with dependency problems.}, language = {en} } @book{Wendt2004, author = {Wendt, Siegfried}, title = {Auf dem Weg zu einem Softwareingenieurwesen}, isbn = {978-3-937786-37-7}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-33184}, publisher = {Universit{\"a}t Potsdam}, year = {2004}, abstract = {(1) {\"U}ber die Notwendigkeit, die bisherige Informatik in eine Grundlagenwissenschaft und eine Ingenieurwissenschaft aufzuspalten (2) Was ist Ingenieurskultur? (3) Das Kommunikationsproblem der Informatiker und ihre Unf{\"a}higkeit, es wahrzunehmen (4) Besonderheiten des Softwareingenieurwesens im Vergleich mit den klassischen Ingenieurdisziplinen (5) Softwareingenieurspl{\"a}ne k{\"o}nnen auch f{\"u}r Nichtfachleute verst{\"a}ndlich sein (6) Principles for Planning Curricula in Software Engineering}, language = {de} } @article{WenderingNikoloski2022, author = {Wendering, Philipp and Nikoloski, Zoran}, title = {COMMIT}, series = {PLoS Computational Biology : a new community journal / publ. by the Public Library of Science (PLoS) in association with the International Society for Computational Biology (ISCB)}, volume = {18}, journal = {PLoS Computational Biology : a new community journal / publ. by the Public Library of Science (PLoS) in association with the International Society for Computational Biology (ISCB)}, number = {3}, publisher = {Public Library of Science}, address = {San Fransisco}, issn = {1553-734X}, doi = {10.1371/journal.pcbi.1009906}, pages = {24}, year = {2022}, abstract = {Composition and functions of microbial communities affect important traits in diverse hosts, from crops to humans. Yet, mechanistic understanding of how metabolism of individual microbes is affected by the community composition and metabolite leakage is lacking. Here, we first show that the consensus of automatically generated metabolic reconstructions improves the quality of the draft reconstructions, measured by comparison to reference models. We then devise an approach for gap filling, termed COMMIT, that considers metabolites for secretion based on their permeability and the composition of the community. By applying COMMIT with two soil communities from the Arabidopsis thaliana culture collection, we could significantly reduce the gap-filling solution in comparison to filling gaps in individual reconstructions without affecting the genomic support. Inspection of the metabolic interactions in the soil communities allows us to identify microbes with community roles of helpers and beneficiaries. Therefore, COMMIT offers a versatile fully automated solution for large-scale modelling of microbial communities for diverse biotechnological applications.
Author summaryMicrobial communities are important in ecology, human health, and crop productivity. However, detailed information on the interactions within natural microbial communities is hampered by the community size, lack of detailed information on the biochemistry of single organisms, and the complexity of interactions between community members. Metabolic models are comprised of biochemical reaction networks based on the genome annotation, and can provide mechanistic insights into community functions. Previous analyses of microbial community models have been performed with high-quality reference models or models generated using a single reconstruction pipeline. However, these models do not contain information on the composition of the community that determines the metabolites exchanged between the community members. In addition, the quality of metabolic models is affected by the reconstruction approach used, with direct consequences on the inferred interactions between community members. Here, we use fully automated consensus reconstructions from four approaches to arrive at functional models with improved genomic support while considering the community composition. We applied our pipeline to two soil communities from the Arabidopsis thaliana culture collection, providing only genome sequences. Finally, we show that the obtained models have 90\% genomic support and demonstrate that the derived interactions are corroborated by independent computational predictions.}, language = {en} } @phdthesis{Weise2021, author = {Weise, Matthias}, title = {Auswahl von Selektions- und Manipulationstechniken f{\"u}r Virtual Reality-Anwendungen}, doi = {10.25932/publishup-53458}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-534586}, school = {Universit{\"a}t Potsdam}, pages = {iii, 218}, year = {2021}, abstract = {Die stetige Weiterentwicklung von VR-Systemen bietet neue M{\"o}glichkeiten der Interaktion mit virtuellen Objekten im dreidimensionalen Raum, stellt Entwickelnde von VRAnwendungen aber auch vor neue Herausforderungen. Selektions- und Manipulationstechniken m{\"u}ssen unter Ber{\"u}cksichtigung des Anwendungsszenarios, der Zielgruppe und der zur Verf{\"u}gung stehenden Ein- und Ausgabeger{\"a}te ausgew{\"a}hlt werden. Diese Arbeit leistet einen Beitrag dazu, die Auswahl von passenden Interaktionstechniken zu unterst{\"u}tzen. Hierf{\"u}r wurde eine repr{\"a}sentative Menge von Selektions- und Manipulationstechniken untersucht und, unter Ber{\"u}cksichtigung existierender Klassifikationssysteme, eine Taxonomie entwickelt, die die Analyse der Techniken hinsichtlich interaktionsrelevanter Eigenschaften erm{\"o}glicht. Auf Basis dieser Taxonomie wurden Techniken ausgew{\"a}hlt, die in einer explorativen Studie verglichen wurden, um R{\"u}ckschl{\"u}sse auf die Dimensionen der Taxonomie zu ziehen und neue Indizien f{\"u}r Vor- und Nachteile der Techniken in spezifischen Anwendungsszenarien zu generieren. Die Ergebnisse der Arbeit m{\"u}nden in eine Webanwendung, die Entwickelnde von VR-Anwendungen gezielt dabei unterst{\"u}tzt, passende Selektions- und Manipulationstechniken f{\"u}r ein Anwendungsszenario auszuw{\"a}hlen, indem Techniken auf Basis der Taxonomie gefiltert und unter Verwendung der Resultate aus der Studie sortiert werden k{\"o}nnen.}, language = {de} } @phdthesis{Weigend2007, author = {Weigend, Michael}, title = {Intuitive Modelle der Informatik}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-940793-08-9}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-15787}, school = {Universit{\"a}t Potsdam}, pages = {331}, year = {2007}, abstract = {Intuitive Modelle der Informatik sind gedankliche Vorstellungen {\"u}ber informatische Konzepte, die mit subjektiver Gewissheit verbunden sind. Menschen verwenden sie, wenn sie die Arbeitsweise von Computerprogrammen nachvollziehen oder anderen erkl{\"a}ren, die logische Korrektheit eines Programms pr{\"u}fen oder in einem kreativen Prozess selbst Programme entwickeln. Intuitive Modelle k{\"o}nnen auf verschiedene Weise repr{\"a}sentiert und kommuniziert werden, etwa verbal-abstrakt, durch ablauf- oder strukturorientierte Abbildungen und Filme oder konkrete Beispiele. Diskutiert werden in dieser Arbeit grundlegende intuitive Modelle f{\"u}r folgende inhaltliche Aspekte einer Programmausf{\"u}hrung: Allokation von Aktivit{\"a}t bei einer Programmausf{\"u}hrung, Benennung von Entit{\"a}ten, Daten, Funktionen, Verarbeitung, Kontrollstrukturen zur Steuerung von Programml{\"a}ufen, Rekursion, Klassen und Objekte. Mit Hilfe eines Systems von Online-Spielen, der Python Visual Sandbox, werden die psychische Realit{\"a}t verschiedener intuitiver Modelle bei Programmieranf{\"a}ngern nachgewiesen und fehlerhafte Anwendungen (Fehlvorstellungen) identifiziert.}, language = {de} } @phdthesis{Weidlich2011, author = {Weidlich, Matthias}, title = {Behavioural profiles : a relational approach to behaviour consistency}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-55590}, school = {Universit{\"a}t Potsdam}, year = {2011}, abstract = {Business Process Management (BPM) emerged as a means to control, analyse, and optimise business operations. Conceptual models are of central importance for BPM. Most prominently, process models define the behaviour that is performed to achieve a business value. In essence, a process model is a mapping of properties of the original business process to the model, created for a purpose. Different modelling purposes, therefore, result in different models of a business process. Against this background, the misalignment of process models often observed in the field of BPM is no surprise. Even if the same business scenario is considered, models created for strategic decision making differ in content significantly from models created for process automation. Despite their differences, process models that refer to the same business process should be consistent, i.e., free of contradictions. Apparently, there is a trade-off between strictness of a notion of consistency and appropriateness of process models serving different purposes. Existing work on consistency analysis builds upon behaviour equivalences and hierarchical refinements between process models. Hence, these approaches are computationally hard and do not offer the flexibility to gradually relax consistency requirements towards a certain setting. This thesis presents a framework for the analysis of behaviour consistency that takes a fundamentally different approach. As a first step, an alignment between corresponding elements of related process models is constructed. Then, this thesis conducts behavioural analysis grounded on a relational abstraction of the behaviour of a process model, its behavioural profile. Different variants of these profiles are proposed, along with efficient computation techniques for a broad class of process models. Using behavioural profiles, consistency of an alignment between process models is judged by different notions and measures. The consistency measures are also adjusted to assess conformance of process logs that capture the observed execution of a process. Further, this thesis proposes various complementary techniques to support consistency management. It elaborates on how to implement consistent change propagation between process models, addresses the exploration of behavioural commonalities and differences, and proposes a model synthesis for behavioural profiles.}, language = {en} } @article{WegnerZenderLucke2015, author = {Wegner, Christian and Zender, Raphael and Lucke, Ulrike}, title = {ProtoSense}, series = {KEYCIT 2014 - Key Competencies in Informatics and ICT}, journal = {KEYCIT 2014 - Key Competencies in Informatics and ICT}, number = {7}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, issn = {1868-0844}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-82970}, pages = {405 -- 407}, year = {2015}, language = {en} } @misc{WeberTiefenbacherGronau2019, author = {Weber, Edzard and Tiefenbacher, Anselm and Gronau, Norbert}, title = {Need for standardization and systematization of test data for job-shop scheduling}, series = {Postprints der Universit{\"a}t Potsdam Wirtschafts- und Sozialwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam Wirtschafts- und Sozialwissenschaftliche Reihe}, number = {134}, issn = {1867-5808}, doi = {10.25932/publishup-47222}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-472229}, pages = {23}, year = {2019}, abstract = {The development of new and better optimization and approximation methods for Job Shop Scheduling Problems (JSP) uses simulations to compare their performance. The test data required for this has an uncertain influence on the simulation results, because the feasable search space can be changed drastically by small variations of the initial problem model. Methods could benefit from this to varying degrees. This speaks in favor of defining standardized and reusable test data for JSP problem classes, which in turn requires a systematic describability of the test data in order to be able to compile problem adequate data sets. This article looks at the test data used for comparing methods by literature review. It also shows how and why the differences in test data have to be taken into account. From this, corresponding challenges are derived which the management of test data must face in the context of JSP research. Keywords}, language = {en} } @article{WeberTiefenbacherGronau2019, author = {Weber, Edzard and Tiefenbacher, Anselm and Gronau, Norbert}, title = {Need for Standardization and Systematization of Test Data for Job-Shop Scheduling}, series = {Data}, volume = {4}, journal = {Data}, number = {1}, publisher = {MDPI}, address = {Basel}, issn = {2306-5729}, doi = {10.3390/data4010032}, pages = {21}, year = {2019}, abstract = {The development of new and better optimization and approximation methods for Job Shop Scheduling Problems (JSP) uses simulations to compare their performance. The test data required for this has an uncertain influence on the simulation results, because the feasable search space can be changed drastically by small variations of the initial problem model. Methods could benefit from this to varying degrees. This speaks in favor of defining standardized and reusable test data for JSP problem classes, which in turn requires a systematic describability of the test data in order to be able to compile problem adequate data sets. This article looks at the test data used for comparing methods by literature review. It also shows how and why the differences in test data have to be taken into account. From this, corresponding challenges are derived which the management of test data must face in the context of JSP research.}, language = {en} } @phdthesis{Weber2015, author = {Weber, Edzard}, title = {Erarbeitung einer Methodik der Wandlungsf{\"a}higkeit}, school = {Universit{\"a}t Potsdam}, pages = {471}, year = {2015}, language = {de} } @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} } @book{WassermannFelgentreffPapeetal.2016, author = {Wassermann, Lars and Felgentreff, Tim and Pape, Tobias and Bolz, Carl Friedrich and Hirschfeld, Robert}, title = {Tracing Algorithmic Primitives in RSqueak/VM}, number = {104}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-355-8}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-91277}, publisher = {Universit{\"a}t Potsdam}, pages = {45}, year = {2016}, abstract = {When realizing a programming language as VM, implementing behavior as part of the VM, as primitive, usually results in reduced execution times. But supporting and developing primitive functions requires more effort than maintaining and using code in the hosted language since debugging is harder, and the turn-around times for VM parts are higher. Furthermore, source artifacts of primitive functions are seldom reused in new implementations of the same language. And if they are reused, the existing API usually is emulated, reducing the performance gains. Because of recent results in tracing dynamic compilation, the trade-off between performance and ease of implementation, reuse, and changeability might now be decided adversely. In this work, we investigate the trade-offs when creating primitives, and in particular how large a difference remains between primitive and hosted function run times in VMs with tracing just-in-time compiler. To that end, we implemented the algorithmic primitive BitBlt three times for RSqueak/VM. RSqueak/VM is a Smalltalk VM utilizing the PyPy RPython toolchain. We compare primitive implementations in C, RPython, and Smalltalk, showing that due to the tracing just-in-time compiler, the performance gap has lessened by one magnitude to one magnitude.}, language = {en} } @phdthesis{Wang2011, author = {Wang, Long}, title = {X-tracking the usage interest on web sites}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-51077}, school = {Universit{\"a}t Potsdam}, year = {2011}, abstract = {The exponential expanding of the numbers of web sites and Internet users makes WWW the most important global information resource. From information publishing and electronic commerce to entertainment and social networking, the Web allows an inexpensive and efficient access to the services provided by individuals and institutions. The basic units for distributing these services are the web sites scattered throughout the world. However, the extreme fragility of web services and content, the high competence between similar services supplied by different sites, and the wide geographic distributions of the web users drive the urgent requirement from the web managers to track and understand the usage interest of their web customers. This thesis, "X-tracking the Usage Interest on Web Sites", aims to fulfill this requirement. "X" stands two meanings: one is that the usage interest differs from various web sites, and the other is that usage interest is depicted from multi aspects: internal and external, structural and conceptual, objective and subjective. "Tracking" shows that our concentration is on locating and measuring the differences and changes among usage patterns. This thesis presents the methodologies on discovering usage interest on three kinds of web sites: the public information portal site, e-learning site that provides kinds of streaming lectures and social site that supplies the public discussions on IT issues. On different sites, we concentrate on different issues related with mining usage interest. The educational information portal sites were the first implementation scenarios on discovering usage patterns and optimizing the organization of web services. In such cases, the usage patterns are modeled as frequent page sets, navigation paths, navigation structures or graphs. However, a necessary requirement is to rebuild the individual behaviors from usage history. We give a systematic study on how to rebuild individual behaviors. Besides, this thesis shows a new strategy on building content clusters based on pair browsing retrieved from usage logs. The difference between such clusters and the original web structure displays the distance between the destinations from usage side and the expectations from design side. Moreover, we study the problem on tracking the changes of usage patterns in their life cycles. The changes are described from internal side integrating conceptual and structure features, and from external side for the physical features; and described from local side measuring the difference between two time spans, and global side showing the change tendency along the life cycle. A platform, Web-Cares, is developed to discover the usage interest, to measure the difference between usage interest and site expectation and to track the changes of usage patterns. E-learning site provides the teaching materials such as slides, recorded lecture videos and exercise sheets. We focus on discovering the learning interest on streaming lectures, such as real medias, mp4 and flash clips. Compared to the information portal site, the usage on streaming lectures encapsulates the variables such as viewing time and actions during learning processes. The learning interest is discovered in the form of answering 6 questions, which covers finding the relations between pieces of lectures and the preference among different forms of lectures. We prefer on detecting the changes of learning interest on the same course from different semesters. The differences on the content and structure between two courses leverage the changes on the learning interest. We give an algorithm on measuring the difference on learning interest integrated with similarity comparison between courses. A search engine, TASK-Moniminer, is created to help the teacher query the learning interest on their streaming lectures on tele-TASK site. Social site acts as an online community attracting web users to discuss the common topics and share their interesting information. Compared to the public information portal site and e-learning web site, the rich interactions among users and web content bring the wider range of content quality, on the other hand, provide more possibilities to express and model usage interest. We propose a framework on finding and recommending high reputation articles in a social site. We observed that the reputation is classified into global and local categories; the quality of the articles having high reputation is related with the content features. Based on these observations, our framework is implemented firstly by finding the articles having global or local reputation, and secondly clustering articles based on their content relations, and then the articles are selected and recommended from each cluster based on their reputation ranks.}, language = {en} } @article{WangYangMeinel2018, author = {Wang, Cheng and Yang, Haojin and Meinel, Christoph}, title = {Image Captioning with Deep Bidirectional LSTMs and Multi-Task Learning}, series = {ACM transactions on multimedia computing, communications, and applications}, volume = {14}, journal = {ACM transactions on multimedia computing, communications, and applications}, number = {2}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {1551-6857}, doi = {10.1145/3115432}, pages = {20}, year = {2018}, abstract = {Generating a novel and descriptive caption of an image is drawing increasing interests in computer vision, natural language processing, and multimedia communities. In this work, we propose an end-to-end trainable deep bidirectional LSTM (Bi-LSTM (Long Short-Term Memory)) model to address the problem. By combining a deep convolutional neural network (CNN) and two separate LSTM networks, our model is capable of learning long-term visual-language interactions by making use of history and future context information at high-level semantic space. We also explore deep multimodal bidirectional models, in which we increase the depth of nonlinearity transition in different ways to learn hierarchical visual-language embeddings. Data augmentation techniques such as multi-crop, multi-scale, and vertical mirror are proposed to prevent over-fitting in training deep models. To understand how our models "translate" image to sentence, we visualize and qualitatively analyze the evolution of Bi-LSTM internal states over time. The effectiveness and generality of proposed models are evaluated on four benchmark datasets: Flickr8K, Flickr30K, MSCOCO, and Pascal1K datasets. We demonstrate that Bi-LSTM models achieve highly competitive performance on both caption generation and image-sentence retrieval even without integrating an additional mechanism (e.g., object detection, attention model). Our experiments also prove that multi-task learning is beneficial to increase model generality and gain performance. We also demonstrate the performance of transfer learning of the Bi-LSTM model significantly outperforms previous methods on the Pascal1K dataset.}, language = {en} } @phdthesis{Wang2016, author = {Wang, Cheng}, title = {Deep Learning of Multimodal Representations}, school = {Universit{\"a}t Potsdam}, pages = {142}, year = {2016}, language = {en} } @misc{Wallenta2014, author = {Wallenta, Daniel}, title = {A Lefschetz fixed point formula for elliptic quasicomplexes}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch Naturwissenschaftliche Reihe}, number = {885}, issn = {1866-8372}, doi = {10.25932/publishup-43547}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-435471}, pages = {577 -- 587}, year = {2014}, abstract = {In a recent paper, the Lefschetz number for endomorphisms (modulo trace class operators) of sequences of trace class curvature was introduced. We show that this is a well defined, canonical extension of the classical Lefschetz number and establish the homotopy invariance of this number. Moreover, we apply the results to show that the Lefschetz fixed point formula holds for geometric quasiendomorphisms of elliptic quasicomplexes.}, language = {en} } @article{vonSteinauSteinrueckSura2023, author = {von Steinau-Steinr{\"u}ck, Robert and Sura, Stephan}, title = {Die (Rest-)Zul{\"a}ssigkeit von Verboten religi{\"o}ser Zeichen am Arbeitsplatz}, series = {NJW spezial}, volume = {20}, journal = {NJW spezial}, number = {8}, publisher = {C.H. Beck}, address = {M{\"u}nchen}, issn = {1613-4621}, pages = {242 -- 243}, year = {2023}, abstract = {In einer Reihe von Urteilen hat der EuGH seit 2017 die Zul{\"a}ssigkeit von Verboten religi{\"o}ser Zeichen und Kleidung am Arbeitsplatz bewertet. Obwohl die Einordnungen des Gerichtshofs der deutschen Rechtslage zun{\"a}chst diametral entgegenstanden, hat sich diese letztlich nicht ver{\"a}ndert.}, language = {de} } @article{vonSteinauSteinrueckMiller2022, author = {von Steinau-Steinr{\"u}ck, Robert and Miller, Denis}, title = {R{\"u}ckzahlungsklauseln f{\"u}r Fortbildungen}, series = {Neue juristische Wochenschrift : NJW Spezial}, volume = {19}, journal = {Neue juristische Wochenschrift : NJW Spezial}, number = {12}, publisher = {C.H. Beck}, address = {M{\"u}nchen}, issn = {1613-4621}, pages = {370 -- 371}, year = {2022}, abstract = {Mit Urteil vom 1.3.2022 (NZA2022, NZA Jahr 2022 Seite 780) hat das BAG erneut {\"u}ber die Wirksamkeit einer R{\"u}ckzahlungsklausel in einer Fortbildungsvereinbarung entschieden. Die Entscheidung reiht sich in eine nicht leicht zu durchschauende Anzahl von Urteilen hierzu ein. Sie dient uns zum Anlass, einen {\"U}berblick {\"u}ber die Rechtsprechung zu geben.}, language = {de} } @article{vonSteinauSteinrueckKurth2022, author = {von Steinau-Steinr{\"u}ck, Robert and Kurth, Paula Sophie}, title = {Das reformierte Statusfeststellungsverfahren in der Praxis}, series = {NJW spezial}, volume = {19}, journal = {NJW spezial}, number = {24}, publisher = {C.H. Beck}, address = {M{\"u}nchen}, issn = {1613-4621}, pages = {754 -- 755}, year = {2022}, abstract = {Das Statusfeststellungsverfahren erm{\"o}glicht auf Antrag bei der alleinzust{\"a}ndigen Deutschen Rentenversicherung Bund den Erhalt einer verbindlichen Einsch{\"a}tzung der h{\"a}ufig komplizierten und folgenschweren Abgrenzung einer selbstst{\"a}ndigen T{\"a}tigkeit von einer abh{\"a}ngigen Besch{\"a}ftigung. Zum 1.4.2022 wurde das Statusfeststellungsverfahren umfassend reformiert. In der Praxis haben sich die eingef{\"u}hrten Novellierungen bislang unterschiedlich bew{\"a}hrt.}, language = {de} } @article{vonSteinauSteinrueckJoeris2021, author = {von Steinau-Steinr{\"u}ck, Robert and J{\"o}ris, Nils}, title = {Brexit-Arbeitsrecht und die Folgen}, series = {NJW spezial}, volume = {18}, journal = {NJW spezial}, number = {8}, publisher = {C.H. Beck}, address = {M{\"u}nchen}, issn = {1613-4621}, pages = {242 -- 243}, year = {2021}, abstract = {Die Corona-Pandemie hat den Brexit ein wenig in den Hintergrund gedr{\"a}ngt. Dabei hat er gerade im Arbeitsrecht ganz erhebliche Auswirkungen. {\"U}ber sie geben wir einen {\"U}berblick.}, language = {de} } @article{vonSteinauSteinrueckJoeris2020, author = {von Steinau-Steinr{\"u}ck, Robert and J{\"o}ris, Nils}, title = {Arbeitsschutz bei Corona}, series = {NJW spezial}, volume = {17}, journal = {NJW spezial}, number = {12}, publisher = {C.H. Beck}, address = {M{\"u}nchen}, issn = {1613-4621}, pages = {370 -- 371}, year = {2020}, abstract = {Den {\"U}berblick im Arbeitsschutzrecht zu behalten, ist schwierig. Der Arbeitsschutz spielt sich in unterschiedlichen Bereichen und auf verschiedenen Ebenen ab. Außerdem sind die einschl{\"a}gigen Rechtsnormen {\"u}beraus ver{\"a}stelt. Der folgende Beitrag soll daher zur Entwirrung beitragen.}, language = {de} } @article{vonSteinauSteinrueckHoeltge2022, author = {von Steinau-Steinr{\"u}ck, Robert and H{\"o}ltge, Clara}, title = {Krieg in Europa}, series = {NJW spezial}, volume = {19}, journal = {NJW spezial}, number = {8}, publisher = {C.H. Beck}, address = {M{\"u}nchen}, issn = {1613-4621}, pages = {242 -- 243}, year = {2022}, abstract = {Am 24.2.2022 begann der russische Angriffskrieg in der Ukraine. Seitdem fliehen t{\"a}glich zahlreiche ukrainische Staatsb{\"u}rger in die Europ{\"a}ische Union, viele davon nach Deutschland. Vorrangig ist jetzt die Sicherung der Grundbed{\"u}rfnisse, wie Verpflegung, Unterkunft und medizinischer Versorgung. Daneben fragen sich Arbeitgeber, wie sie ukrainische Staatsb{\"u}rger m{\"o}glichst schnell besch{\"a}ftigen k{\"o}nnen. Wir geben einen {\"U}berblick {\"u}ber die M{\"o}glichkeiten, ukrainische Gefl{\"u}chtete m{\"o}glichst schnell in den deutschen Arbeitsmarkt zu integrieren.}, language = {de} } @article{vonSteinauSteinrueckBruhn2021, author = {von Steinau-Steinr{\"u}ck, Robert and Bruhn, Emma}, title = {Der Impfmuffel im Arbeitsrecht}, series = {NJW spezial}, volume = {18}, journal = {NJW spezial}, number = {16}, publisher = {C.H. Beck}, address = {M{\"u}nchen}, issn = {1613-4621}, pages = {498 -- 499}, year = {2021}, abstract = {Trotz erfolgreicher Impfkampagne droht nach dem Sommer eine vierte Infektionswelle der Corona-Pandemie. Ob es dazu kommen wird, h{\"a}ngt maßgeblich davon ab, wie viele Menschen sich f{\"u}r eine Corona-Schutzimpfung entscheiden. Am Impfstoff mangelt es nicht mehr, daf{\"u}r an der Impfbereitschaft. Viele Arbeitgeber fragen sich daher, was sie unternehmen k{\"o}nnen, um die Impfquote in ihren Betrieben zu erh{\"o}hen.}, language = {de} } @article{vonSteinauSteinrueckBeismann2020, author = {von Steinau-Steinr{\"u}ck, Robert and Beismann, Lukas}, title = {(Corona-)Homeoffice und betriebliche {\"U}bung}, series = {NJW spezial}, volume = {17}, journal = {NJW spezial}, number = {20}, publisher = {C.H. Beck}, address = {M{\"u}nchen}, issn = {1613-4621}, pages = {626 -- 627}, year = {2020}, abstract = {Homeoffice und mobiles Arbeiten haben sich infolge der Covid-19-Pandemie bei vielen Unternehmen bekanntlich etabliert. Die Anweisung bzw. „Duldung" des Homeoffice beruhte allerdings meist mehr auf tats{\"a}chlicher als auf rechtlicher Grundlage. Letztere k{\"o}nnte aber aus betrieblicher {\"U}bung erwachsen. Dieser Beitrag geht dem rechtlichen Rahmen daf{\"u}r nach.}, language = {de} } @article{vonSteinauSteinrueck2021, author = {von Steinau-Steinr{\"u}ck, Robert}, title = {Was ist bei "Workation" und "Bleisure" rechtlich zu beachten?}, series = {NJW spezial}, volume = {18}, journal = {NJW spezial}, number = {20}, publisher = {C.H. Beck}, address = {M{\"u}nchen}, issn = {1613-4621}, pages = {626 -- 627}, year = {2021}, abstract = {Die Digitalisierung unseres Lebens l{\"o}st die Grenzen zwischen Privat- und Berufsleben immer weiter auf. Bekanntes Beispiel ist das Homeoffice. Arbeitgeber begegnen aber auch zahlreichen weiteren Trends in diesem Zusammenhang. Dazu geh{\"o}ren „workation", also die Verbindung zwischen Arbeit („work") und Urlaub („vacation") ebenso wie „bleisure", dh die Verbindung von Dienstreisen („business") und Urlaub („leisure"). Der Beitrag geht den rechtlichen Rahmenbedingungen hierf{\"u}r nach.}, language = {de} } @misc{vonSteinauSteinrueck2020, author = {von Steinau-Steinr{\"u}ck, Robert}, title = {Gesetzesentwurf zu Corona-bedingten {\"A}nderungen des ArbGG/SGG}, series = {NJW spezial}, volume = {17}, journal = {NJW spezial}, number = {11}, publisher = {C.H. Beck}, address = {M{\"u}nchen}, issn = {1613-4621}, pages = {340 -- 340}, year = {2020}, language = {de} } @misc{vonSteinauSteinrueck2020, author = {von Steinau-Steinr{\"u}ck, Robert}, title = {Koalitionsausschuss beschließt Verl{\"a}ngerung des Kurzarbeitergelds}, series = {NJW spezial}, volume = {17}, journal = {NJW spezial}, number = {19}, publisher = {C.H. Beck}, address = {M{\"u}nchen}, issn = {1613-4621}, pages = {596 -- 596}, year = {2020}, language = {de} } @misc{Voland2014, type = {Master Thesis}, author = {Voland, Patrick}, title = {Webbasierte Visualisierung von Extended Floating Car Data (XFCD)}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-96751}, school = {Universit{\"a}t Potsdam}, pages = {VIII, 176}, year = {2014}, abstract = {Moderne Kraftfahrzeuge verf{\"u}gen {\"u}ber eine Vielzahl an Sensoren, welche f{\"u}r einen reibungslosen technischen Betrieb ben{\"o}tigt werden. Hierzu z{\"a}hlen neben fahrzeugspezifischen Sensoren (wie z.B. Motordrehzahl und Fahrzeuggeschwindigkeit) auch umweltspezifische Sensoren (wie z.B. Luftdruck und Umgebungstemperatur). Durch die zunehmende technische Vernetzung wird es m{\"o}glich, diese Daten der Kraftfahrzeugelektronik aus dem Fahrzeug heraus f{\"u}r die verschiedensten Zwecke zu verwenden. Die vorliegende Arbeit soll einen Beitrag dazu leisten, diese neue Art an massenhaften Daten im Sinne des Konzepts der „Extended Floating Car Data" (XFCD) als Geoinformationen nutzbar zu machen und diese f{\"u}r raumzeitliche Visualisierungen (zur visuellen Analyse) anwenden zu k{\"o}nnen. In diesem Zusammenhang wird speziell die Perspektive des Umwelt- und Verkehrsmonitoring betrachtet, wobei die Anforderungen und Potentiale mit Hilfe von Experteninterviews untersucht werden. Es stellt sich die Frage, welche Daten durch die Kraftfahrzeugelektronik geliefert und wie diese m{\"o}glichst automatisiert erfasst, verarbeitet, visualisiert und {\"o}ffentlich bereitgestellt werden k{\"o}nnen. Neben theoretischen und technischen Grundlagen zur Datenerfassung und -nutzung liegt der Fokus auf den Methoden der kartographischen Visualisierung. Dabei soll der Frage nachgegangenen werden, ob eine technische Implementierung ausschließlich unter Verwendung von Open Source Software m{\"o}glich ist. Das Ziel der Arbeit bildet ein zweigliedriger Ansatz, welcher zum einen die Visualisierung f{\"u}r ein exemplarisch gew{\"a}hltes Anwendungsszenario und zum anderen die prototypische Implementierung von der Datenerfassung im Fahrzeug unter Verwendung der gesetzlich vorgeschriebenen „On Board Diagnose"-Schnittstelle und einem Smartphone-gest{\"u}tzten Ablauf bis zur webbasierten Visualisierung umfasst.}, language = {de} } @misc{Voigt2009, type = {Master Thesis}, author = {Voigt, Matthias}, title = {Entwicklung von bioinformatischen Visualisierungswerkzeugen f{\"u}r Metabolitdaten von N{\"a}hrstoffmangelsituationen bei Arabidopsis thaliana}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-33047}, school = {Universit{\"a}t Potsdam}, year = {2009}, abstract = {Diese Arbeit umfasst die Archivierung, Visualisierung anhand bioinformatischer Methoden und Interpretation eines vorhandenen Messdatensatz (Element [ICP-MS]-, Ionen [IC]- und Metabolitdaten [RP-HPLC und GC/TOF-MS]) der Pflanze Arabidopsis thaliana getrennt in Bl{\"a}tter und Wurzeln. Die Pflanzen wurden den sechs Mangelsituationen der N{\"a}hrstoffe Eisen, Kalium, Magnesium, Stickstoff, Phosphor und Schwefel ausgesetzt und zu neun Messzeitpunkten [0.5-, 1-, 2-, 3-, 4-, 5-, 6-, 7-in Tagen und „resupply" (vier Stunden nach dem vierten Tag)] analysiert. Es erfolgte die Integration der Messdaten in eine SQlite-Datenbank. Die Veranschaulichung erfolgte mit Hilfe der Programmiersprache R. Anhand einiger Pakete zur Erweiterung des Funktionsumfangs von R wurde erstens eine Schnittstelle zur SQLite- Datenbank hergestellt, was ein Abfragen an diese erm{\"o}glichte und zweitens verhalfen sie zu der Erstellung einer Reihe zus{\"a}tzlicher Darstellungsformen (Heatmap, Wireframe, PCA). Selbstgeschriebene Skripte erlaubten den Datenzugriff und die grafische Ausgabe als z. B. Heatmaps. In der Entstehung dieser Arbeit sind weiterhin zwei weitere Visualisierungsformen von PCA-Daten entwickelt worden: Das Abstandsdiagramm und die animierte PCA. Beides sind hilfreiche Werkzeuge zur Interpretation von PCA-Plots eines zeitlichen Verlaufes. Anhand der Darstellungen der Element- und Ionendaten ließen sich die N{\"a}hrstoffmangelsituationen durch Abnahme der entsprechenden Totalelemente und Ionen nachweisen. Weiterhin sind starke {\"A}hnlichkeiten der durch RP-HPLC bestimmten Metaboliten unter Eisen-, Kalium und Magnesiummangel erkannt worden. Allerdings gibt es nur eine geringe Anzahl an Interkationen der Metabolitgehalte, da der Großteil der Metabolitlevel im Vergleich zur Kontrolle unver{\"a}ndert blieb. Der Literaturvergleich mit zwei Publikationen, die den Phosphat- und Schwefelmangel in Arabidopsis thaliana untersuchten, zeigte ein durchwachsenes Ergebnis. Einerseits gab es eine gleiche Tendenz der verglichenen Aminos{\"a}uren zu verzeichen, aber andererseits wiesen die Visualisierungen auch Gegens{\"a}tzlichkeiten auf. Der Vergleich der mit RP-HPLC und GC/TOF-MS gemessenen Metaboliten erbrachte ein sehr kontroverses Ergebnis. Zum einen wurden {\"U}bereinstimmungen der gleichen Metaboliten durch gemeinsame Cluster in den Heatmaps beobachtet, zum anderen auch Widerspr{\"u}che, exemplarisch in den Abstandsdiagrammen der Bl{\"a}tterdaten jedes Verfahrens, in welchen unterschiedliche Abstandsh{\"o}hepunkte erkennbar sind.}, language = {de} } @book{VogelGiese2013, author = {Vogel, Thomas and Giese, Holger}, title = {Model-driven engineering of adaptation engines for self-adaptive software : executable runtime megamodels}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-227-8}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-63825}, publisher = {Universit{\"a}t Potsdam}, pages = {vi, 59}, year = {2013}, abstract = {The development of self-adaptive software requires the engineering of an adaptation engine that controls and adapts the underlying adaptable software by means of feedback loops. The adaptation engine often describes the adaptation by using runtime models representing relevant aspects of the adaptable software and particular activities such as analysis and planning that operate on these runtime models. To systematically address the interplay between runtime models and adaptation activities in adaptation engines, runtime megamodels have been proposed for self-adaptive software. A runtime megamodel is a specific runtime model whose elements are runtime models and adaptation activities. Thus, a megamodel captures the interplay between multiple models and between models and activities as well as the activation of the activities. In this article, we go one step further and present a modeling language for ExecUtable RuntimE MegAmodels (EUREMA) that considerably eases the development of adaptation engines by following a model-driven engineering approach. We provide a domain-specific modeling language and a runtime interpreter for adaptation engines, in particular for feedback loops. Megamodels are kept explicit and alive at runtime and by interpreting them, they are directly executed to run feedback loops. Additionally, they can be dynamically adjusted to adapt feedback loops. Thus, EUREMA supports development by making feedback loops, their runtime models, and adaptation activities explicit at a higher level of abstraction. Moreover, it enables complex solutions where multiple feedback loops interact or even operate on top of each other. Finally, it leverages the co-existence of self-adaptation and off-line adaptation for evolution.}, language = {en} } @phdthesis{Vogel2018, author = {Vogel, Thomas}, title = {Model-driven engineering of self-adaptive software}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-409755}, school = {Universit{\"a}t Potsdam}, pages = {xvi, 357}, year = {2018}, abstract = {The development of self-adaptive software requires the engineering of an adaptation engine that controls the underlying adaptable software by a feedback loop. State-of-the-art approaches prescribe the feedback loop in terms of numbers, how the activities (e.g., monitor, analyze, plan, and execute (MAPE)) and the knowledge are structured to a feedback loop, and the type of knowledge. Moreover, the feedback loop is usually hidden in the implementation or framework and therefore not visible in the architectural design. Additionally, an adaptation engine often employs runtime models that either represent the adaptable software or capture strategic knowledge such as reconfiguration strategies. State-of-the-art approaches do not systematically address the interplay of such runtime models, which would otherwise allow developers to freely design the entire feedback loop. This thesis presents ExecUtable RuntimE MegAmodels (EUREMA), an integrated model-driven engineering (MDE) solution that rigorously uses models for engineering feedback loops. EUREMA provides a domain-specific modeling language to specify and an interpreter to execute feedback loops. The language allows developers to freely design a feedback loop concerning the activities and runtime models (knowledge) as well as the number of feedback loops. It further supports structuring the feedback loops in the adaptation engine that follows a layered architectural style. Thus, EUREMA makes the feedback loops explicit in the design and enables developers to reason about design decisions. To address the interplay of runtime models, we propose the concept of a runtime megamodel, which is a runtime model that contains other runtime models as well as activities (e.g., MAPE) working on the contained models. This concept is the underlying principle of EUREMA. The resulting EUREMA (mega)models are kept alive at runtime and they are directly executed by the EUREMA interpreter to run the feedback loops. Interpretation provides the flexibility to dynamically adapt a feedback loop. In this context, EUREMA supports engineering self-adaptive software in which feedback loops run independently or in a coordinated fashion within the same layer as well as on top of each other in different layers of the adaptation engine. Moreover, we consider preliminary means to evolve self-adaptive software by providing a maintenance interface to the adaptation engine. This thesis discusses in detail EUREMA by applying it to different scenarios such as single, multiple, and stacked feedback loops for self-repairing and self-optimizing the mRUBiS application. Moreover, it investigates the design and expressiveness of EUREMA, reports on experiments with a running system (mRUBiS) and with alternative solutions, and assesses EUREMA with respect to quality attributes such as performance and scalability. The conducted evaluation provides evidence that EUREMA as an integrated and open MDE approach for engineering self-adaptive software seamlessly integrates the development and runtime environments using the same formalism to specify and execute feedback loops, supports the dynamic adaptation of feedback loops in layered architectures, and achieves an efficient execution of feedback loops by leveraging incrementality.}, language = {en} } @inproceedings{VladovaUllrichSultanowetal.2023, author = {Vladova, Gergana and Ullrich, Andr{\´e} and Sultanow, Eldar and Tobolla, Marinho and Sebrak, Sebastian and Czarnecki, Christian and Brockmann, Carsten}, title = {Visual analytics for knowledge management}, series = {Informatik 2023}, booktitle = {Informatik 2023}, editor = {Klein, Maike and Krupka, Daniel and Winter, Cornelia and Wohlgemuth, Volker}, publisher = {Gesellschaft f{\"u}r Informatik e.V. (GI)}, address = {Bonn}, isbn = {978-3-88579-731-9}, issn = {1617-5468}, doi = {10.18420/inf2023_187}, pages = {1851 -- 1870}, year = {2023}, abstract = {The management of knowledge in organizations considers both established long-term processes and cooperation in agile project teams. Since knowledge can be both tacit and explicit, its transfer from the individual to the organizational knowledge base poses a challenge in organizations. This challenge increases when the fluctuation of knowledge carriers is exceptionally high. Especially in large projects in which external consultants are involved, there is a risk that critical, company-relevant knowledge generated in the project will leave the company with the external knowledge carrier and thus be lost. In this paper, we show the advantages of an early warning system for knowledge management to avoid this loss. In particular, the potential of visual analytics in the context of knowledge management systems is presented and discussed. We present a project for the development of a business-critical software system and discuss the first implementations and results.}, language = {en} } @article{VitaglianoJiangNaumann2021, author = {Vitagliano, Gerardo and Jiang, Lan and Naumann, Felix}, title = {Detecting layout templates in complex multiregion files}, series = {Proceedings of the VLDB Endowment}, volume = {15}, journal = {Proceedings of the VLDB Endowment}, number = {3}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {2150-8097}, doi = {10.14778/3494124.3494145}, pages = {646 -- 658}, year = {2021}, abstract = {Spreadsheets are among the most commonly used file formats for data management, distribution, and analysis. Their widespread employment makes it easy to gather large collections of data, but their flexible canvas-based structure makes automated analysis difficult without heavy preparation. One of the common problems that practitioners face is the presence of multiple, independent regions in a single spreadsheet, possibly separated by repeated empty cells. We define such files as "multiregion" files. In collections of various spreadsheets, we can observe that some share the same layout. We present the Mondrian approach to automatically identify layout templates across multiple files and systematically extract the corresponding regions. Our approach is composed of three phases: first, each file is rendered as an image and inspected for elements that could form regions; then, using a clustering algorithm, the identified elements are grouped to form regions; finally, every file layout is represented as a graph and compared with others to find layout templates. We compare our method to state-of-the-art table recognition algorithms on two corpora of real-world enterprise spreadsheets. Our approach shows the best performances in detecting reliable region boundaries within each file and can correctly identify recurring layouts across files.}, language = {en} } @phdthesis{Vitagliano2024, author = {Vitagliano, Gerardo}, title = {Modeling the structure of tabular files for data preparation}, doi = {10.25932/publishup-62435}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-624351}, school = {Universit{\"a}t Potsdam}, pages = {ii, 114}, year = {2024}, abstract = {To manage tabular data files and leverage their content in a given downstream task, practitioners often design and execute complex transformation pipelines to prepare them. The complexity of such pipelines stems from different factors, including the nature of the preparation tasks, often exploratory or ad-hoc to specific datasets; the large repertory of tools, algorithms, and frameworks that practitioners need to master; and the volume, variety, and velocity of the files to be prepared. Metadata plays a fundamental role in reducing this complexity: characterizing a file assists end users in the design of data preprocessing pipelines, and furthermore paves the way for suggestion, automation, and optimization of data preparation tasks. Previous research in the areas of data profiling, data integration, and data cleaning, has focused on extracting and characterizing metadata regarding the content of tabular data files, i.e., about the records and attributes of tables. Content metadata are useful for the latter stages of a preprocessing pipeline, e.g., error correction, duplicate detection, or value normalization, but they require a properly formed tabular input. Therefore, these metadata are not relevant for the early stages of a preparation pipeline, i.e., to correctly parse tables out of files. In this dissertation, we turn our focus to what we call the structure of a tabular data file, i.e., the set of characters within a file that do not represent data values but are required to parse and understand the content of the file. We provide three different approaches to represent file structure, an explicit representation based on context-free grammars; an implicit representation based on file-wise similarity; and a learned representation based on machine learning. In our first contribution, we use the grammar-based representation to characterize a set of over 3000 real-world csv files and identify multiple structural issues that let files deviate from the csv standard, e.g., by having inconsistent delimiters or containing multiple tables. We leverage our learnings about real-world files and propose Pollock, a benchmark to test how well systems parse csv files that have a non-standard structure, without any previous preparation. We report on our experiments on using Pollock to evaluate the performance of 16 real-world data management systems. Following, we characterize the structure of files implicitly, by defining a measure of structural similarity for file pairs. We design a novel algorithm to compute this measure, which is based on a graph representation of the files' content. We leverage this algorithm and propose Mondrian, a graphical system to assist users in identifying layout templates in a dataset, classes of files that have the same structure, and therefore can be prepared by applying the same preparation pipeline. Finally, we introduce MaGRiTTE, a novel architecture that uses self-supervised learning to automatically learn structural representations of files in the form of vectorial embeddings at three different levels: cell level, row level, and file level. We experiment with the application of structural embeddings for several tasks, namely dialect detection, row classification, and data preparation efforts estimation. Our experimental results show that structural metadata, either identified explicitly on parsing grammars, derived implicitly as file-wise similarity, or learned with the help of machine learning architectures, is fundamental to automate several tasks, to scale up preparation to large quantities of files, and to provide repeatable preparation pipelines.}, language = {en} } @article{Vierheller2014, author = {Vierheller, Janine}, title = {Exploratory Data Analysis}, series = {Process Design for Natural Scientists: an agile model-driven approach}, journal = {Process Design for Natural Scientists: an agile model-driven approach}, number = {500}, editor = {Lambrecht, Anna-Lena and Margaria, Tiziana}, publisher = {Axel Springer Verlag}, address = {Berlin}, isbn = {978-3-662-45005-5}, issn = {1865-0929}, pages = {110 -- 126}, year = {2014}, abstract = {In bioinformatics the term exploratory data analysis refers to different methods to get an overview of large biological data sets. Hence, it helps to create a framework for further analysis and hypothesis testing. The workflow facilitates this first important step of the data analysis created by high-throughput technologies. The results are different plots showing the structure of the measurements. The goal of the workflow is the automatization of the exploratory data analysis, but also the flexibility should be guaranteed. The basic tool is the free software R.}, language = {en} } @phdthesis{Videla2014, author = {Videla, Santiago}, title = {Reasoning on the response of logical signaling networks with answer set programming}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-71890}, school = {Universit{\"a}t Potsdam}, year = {2014}, abstract = {Deciphering the functioning of biological networks is one of the central tasks in systems biology. In particular, signal transduction networks are crucial for the understanding of the cellular response to external and internal perturbations. Importantly, in order to cope with the complexity of these networks, mathematical and computational modeling is required. We propose a computational modeling framework in order to achieve more robust discoveries in the context of logical signaling networks. More precisely, we focus on modeling the response of logical signaling networks by means of automated reasoning using Answer Set Programming (ASP). ASP provides a declarative language for modeling various knowledge representation and reasoning problems. Moreover, available ASP solvers provide several reasoning modes for assessing the multitude of answer sets. Therefore, leveraging its rich modeling language and its highly efficient solving capacities, we use ASP to address three challenging problems in the context of logical signaling networks: learning of (Boolean) logical networks, experimental design, and identification of intervention strategies. Overall, the contribution of this thesis is three-fold. Firstly, we introduce a mathematical framework for characterizing and reasoning on the response of logical signaling networks. Secondly, we contribute to a growing list of successful applications of ASP in systems biology. Thirdly, we present a software providing a complete pipeline for automated reasoning on the response of logical signaling networks.}, language = {en} } @book{vanderWaltOdunAyoBastianetal.2018, author = {van der Walt, Estee and Odun-Ayo, Isaac and Bastian, Matthias and Eldin Elsaid, Mohamed Esam}, title = {Proceedings of the Fifth HPI Cloud Symposium "Operating the Cloud" 2017}, number = {122}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-432-6}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-411330}, publisher = {Universit{\"a}t Potsdam}, pages = {70}, year = {2018}, abstract = {Every year, the Hasso Plattner Institute (HPI) invites guests from industry and academia to a collaborative scientific workshop on the topic Operating the Cloud. Our goal is to provide a forum for the exchange of knowledge and experience between industry and academia. Co-located with the event is the HPI's Future SOC Lab day, which offers an additional attractive and conducive environment for scientific and industry related discussions. Operating the Cloud aims to be a platform for productive interactions of innovative ideas, visions, and upcoming technologies in the field of cloud operation and administration. In these proceedings, the results of the fifth HPI cloud symposium Operating the Cloud 2017 are published. We thank the authors for exciting presentations and insights into their current work and research. Moreover, we look forward to more interesting submissions for the upcoming symposium in 2018.}, language = {en} } @article{UlrichLutfiRutzenetal.2022, author = {Ulrich, Jens-Uwe and Lutfi, Ahmad and Rutzen, Kilian and Renard, Bernhard Y.}, title = {ReadBouncer}, series = {Bioinformatics}, volume = {38}, journal = {Bioinformatics}, number = {SUPPL 1}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1367-4803}, doi = {10.1093/bioinformatics/btac223}, pages = {153 -- 160}, year = {2022}, abstract = {Motivation: Nanopore sequencers allow targeted sequencing of interesting nucleotide sequences by rejecting other sequences from individual pores. This feature facilitates the enrichment of low-abundant sequences by depleting overrepresented ones in-silico. Existing tools for adaptive sampling either apply signal alignment, which cannot handle human-sized reference sequences, or apply read mapping in sequence space relying on fast graphical processing units (GPU) base callers for real-time read rejection. Using nanopore long-read mapping tools is also not optimal when mapping shorter reads as usually analyzed in adaptive sampling applications. Results: Here, we present a new approach for nanopore adaptive sampling that combines fast CPU and GPU base calling with read classification based on Interleaved Bloom Filters. ReadBouncer improves the potential enrichment of low abundance sequences by its high read classification sensitivity and specificity, outperforming existing tools in the field. It robustly removes even reads belonging to large reference sequences while running on commodity hardware without GPUs, making adaptive sampling accessible for in-field researchers. Readbouncer also provides a user-friendly interface and installer files for end-users without a bioinformatics background.}, language = {en} } @misc{UllrichVladovaEigelshovenetal.2022, author = {Ullrich, Andr{\´e} and Vladova, Gergana and Eigelshoven, Felix and Renz, Andr{\´e}}, title = {Data mining of scientific research on artificial intelligence in teaching and administration in higher education institutions}, series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Wirtschafts- und Sozialwissenschaftliche Reihe}, journal = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Wirtschafts- und Sozialwissenschaftliche Reihe}, number = {160}, issn = {1867-5808}, doi = {10.25932/publishup-58907}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-589077}, pages = {18}, year = {2022}, abstract = {Teaching and learning as well as administrative processes are still experiencing intensive changes with the rise of artificial intelligence (AI) technologies and its diverse application opportunities in the context of higher education. Therewith, the scientific interest in the topic in general, but also specific focal points rose as well. However, there is no structured overview on AI in teaching and administration processes in higher education institutions that allows to identify major research topics and trends, and concretizing peculiarities and develops recommendations for further action. To overcome this gap, this study seeks to systematize the current scientific discourse on AI in teaching and administration in higher education institutions. This study identified an (1) imbalance in research on AI in educational and administrative contexts, (2) an imbalance in disciplines and lack of interdisciplinary research, (3) inequalities in cross-national research activities, as well as (4) neglected research topics and paths. In this way, a comparative analysis between AI usage in administration and teaching and learning processes, a systematization of the state of research, an identification of research gaps as well as further research path on AI in higher education institutions are contributed to research.}, language = {en} } @article{UllrichVladovaEigelshovenetal.2022, author = {Ullrich, Andr{\´e} and Vladova, Gergana and Eigelshoven, Felix and Renz, Andr{\´e}}, title = {Data mining of scientific research on artificial intelligence in teaching and administration in higher education institutions}, series = {Discover artificial intelligence}, volume = {2}, journal = {Discover artificial intelligence}, publisher = {Springer}, address = {Cham}, issn = {2731-0809}, doi = {10.1007/s44163-022-00031-7}, pages = {18}, year = {2022}, abstract = {Teaching and learning as well as administrative processes are still experiencing intensive changes with the rise of artificial intelligence (AI) technologies and its diverse application opportunities in the context of higher education. Therewith, the scientific interest in the topic in general, but also specific focal points rose as well. However, there is no structured overview on AI in teaching and administration processes in higher education institutions that allows to identify major research topics and trends, and concretizing peculiarities and develops recommendations for further action. To overcome this gap, this study seeks to systematize the current scientific discourse on AI in teaching and administration in higher education institutions. This study identified an (1) imbalance in research on AI in educational and administrative contexts, (2) an imbalance in disciplines and lack of interdisciplinary research, (3) inequalities in cross-national research activities, as well as (4) neglected research topics and paths. In this way, a comparative analysis between AI usage in administration and teaching and learning processes, a systematization of the state of research, an identification of research gaps as well as further research path on AI in higher education institutions are contributed to research.}, language = {en} } @article{UllrichTeichmannGronau2021, author = {Ullrich, Andr{\´e} and Teichmann, Malte and Gronau, Norbert}, title = {Fast trainable capabilities in software engineering-skill development in learning factories}, series = {Ji suan ji jiao yu = Computer Education / Qing hua da xue}, journal = {Ji suan ji jiao yu = Computer Education / Qing hua da xue}, number = {12}, publisher = {[Verlag nicht ermittelbar]}, address = {Bei jing shi}, issn = {1672-5913}, doi = {10.16512/j.cnki.jsjjy.2020.12.002}, pages = {2 -- 10}, year = {2021}, abstract = {The increasing demand for software engineers cannot completely be fulfilled by university education and conventional training approaches due to limited capacities. Accordingly, an alternative approach is necessary where potential software engineers are being educated in software engineering skills using new methods. We suggest micro tasks combined with theoretical lessons to overcome existing skill deficits and acquire fast trainable capabilities. This paper addresses the gap between demand and supply of software engineers by introducing an actionoriented and scenario-based didactical approach, which enables non-computer scientists to code. Therein, the learning content is provided in small tasks and embedded in learning factory scenarios. Therefore, different requirements for software engineers from the market side and from an academic viewpoint are analyzed and synthesized into an integrated, yet condensed skills catalogue. This enables the development of training and education units that focus on the most important skills demanded on the market. To achieve this objective, individual learning scenarios are developed. Of course, proper basic skills in coding cannot be learned over night but software programming is also no sorcery.}, language = {en} } @article{TscherejkinaMorgielMoebert2018, author = {Tscherejkina, Anna and Morgiel, Anna and Moebert, Tobias}, title = {Computergest{\"u}tztes Training von sozio-emotionalen Kompetenzen durch Minispiele}, series = {E-Learning Symposium 2018}, journal = {E-Learning Symposium 2018}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-42193}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-421937}, pages = {41 -- 52}, year = {2018}, abstract = {Das Training sozioemotionaler Kompetenzen ist gerade f{\"u}r Menschen mit Autismus n{\"u}tzlich. Ein solches Training kann mithilfe einer spielbasierten Anwendung effektiv gestaltet werden. Zwei Minispiele, Mimikry und Emo-Mahjong, wurden realisiert und hinsichtlich User Experience evaluiert. Die jeweiligen Konzepte und die Evaluationsergebnisse sollen hier vorgestellt werden.}, language = {de} } @phdthesis{Truemper2014, author = {Tr{\"u}mper, Jonas}, title = {Visualization techniques for the analysis of software behavior and related structures}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-72145}, school = {Universit{\"a}t Potsdam}, year = {2014}, abstract = {Software maintenance encompasses any changes made to a software system after its initial deployment and is thereby one of the key phases in the typical software-engineering lifecycle. In software maintenance, we primarily need to understand structural and behavioral aspects, which are difficult to obtain, e.g., by code reading. Software analysis is therefore a vital tool for maintaining these systems: It provides - the preferably automated - means to extract and evaluate information from their artifacts such as software structure, runtime behavior, and related processes. However, such analysis typically results in massive raw data, so that even experienced engineers face difficulties directly examining, assessing, and understanding these data. Among other things, they require tools with which to explore the data if no clear question can be formulated beforehand. For this, software analysis and visualization provide its users with powerful interactive means. These enable the automation of tasks and, particularly, the acquisition of valuable and actionable insights into the raw data. For instance, one means for exploring runtime behavior is trace visualization. This thesis aims at extending and improving the tool set for visual software analysis by concentrating on several open challenges in the fields of dynamic and static analysis of software systems. This work develops a series of concepts and tools for the exploratory visualization of the respective data to support users in finding and retrieving information on the system artifacts concerned. This is a difficult task, due to the lack of appropriate visualization metaphors; in particular, the visualization of complex runtime behavior poses various questions and challenges of both a technical and conceptual nature. This work focuses on a set of visualization techniques for visually representing control-flow related aspects of software traces from shared-memory software systems: A trace-visualization concept based on icicle plots aids in understanding both single-threaded as well as multi-threaded runtime behavior on the function level. The concept's extensibility further allows the visualization and analysis of specific aspects of multi-threading such as synchronization, the correlation of such traces with data from static software analysis, and a comparison between traces. Moreover, complementary techniques for simultaneously analyzing system structures and the evolution of related attributes are proposed. These aim at facilitating long-term planning of software architecture and supporting management decisions in software projects by extensions to the circular-bundle-view technique: An extension to 3-dimensional space allows for the use of additional variables simultaneously; interaction techniques allow for the modification of structures in a visual manner. The concepts and techniques presented here are generic and, as such, can be applied beyond software analysis for the visualization of similarly structured data. The techniques' practicability is demonstrated by several qualitative studies using subject data from industry-scale software systems. The studies provide initial evidence that the techniques' application yields useful insights into the subject data and its interrelationships in several scenarios.}, language = {en} } @article{TrautmannZhouBrahmsetal.2021, author = {Trautmann, Justin and Zhou, Lin and Brahms, Clemens Markus and Tunca, Can and Ersoy, Cem and Granacher, Urs and Arnrich, Bert}, title = {TRIPOD}, series = {Data : open access ʻData in scienceʼ journal}, volume = {6}, journal = {Data : open access ʻData in scienceʼ journal}, number = {9}, publisher = {MDPI}, address = {Basel}, issn = {2306-5729}, doi = {10.3390/data6090095}, pages = {19}, year = {2021}, abstract = {Inertial measurement units (IMUs) enable easy to operate and low-cost data recording for gait analysis. When combined with treadmill walking, a large number of steps can be collected in a controlled environment without the need of a dedicated gait analysis laboratory. In order to evaluate existing and novel IMU-based gait analysis algorithms for treadmill walking, a reference dataset that includes IMU data as well as reliable ground truth measurements for multiple participants and walking speeds is needed. This article provides a reference dataset consisting of 15 healthy young adults who walked on a treadmill at three different speeds. Data were acquired using seven IMUs placed on the lower body, two different reference systems (Zebris FDMT-HQ and OptoGait), and two RGB cameras. Additionally, in order to validate an existing IMU-based gait analysis algorithm using the dataset, an adaptable modular data analysis pipeline was built. Our results show agreement between the pressure-sensitive Zebris and the photoelectric OptoGait system (r = 0.99), demonstrating the quality of our reference data. As a use case, the performance of an algorithm originally designed for overground walking was tested on treadmill data using the data pipeline. The accuracy of stride length and stride time estimations was comparable to that reported in other studies with overground data, indicating that the algorithm is equally applicable to treadmill data. The Python source code of the data pipeline is publicly available, and the dataset will be provided by the authors upon request, enabling future evaluations of IMU gait analysis algorithms without the need of recording new data.}, language = {en} } @misc{Trapp2007, type = {Master Thesis}, author = {Trapp, Matthias}, title = {Analysis and exploration of virtual 3D city models using 3D information lenses}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-13930}, school = {Universit{\"a}t Potsdam}, year = {2007}, abstract = {This thesis addresses real-time rendering techniques for 3D information lenses based on the focus \& context metaphor. It analyzes, conceives, implements, and reviews its applicability to objects and structures of virtual 3D city models. In contrast to digital terrain models, the application of focus \& context visualization to virtual 3D city models is barely researched. However, the purposeful visualization of contextual data of is extreme importance for the interactive exploration and analysis of this field. Programmable hardware enables the implementation of new lens techniques, that allow the augmentation of the perceptive and cognitive quality of the visualization compared to classical perspective projections. A set of 3D information lenses is integrated into a 3D scene-graph system: • Occlusion lenses modify the appearance of virtual 3D city model objects to resolve their occlusion and consequently facilitate the navigation. • Best-view lenses display city model objects in a priority-based manner and mediate their meta information. Thus, they support exploration and navigation of virtual 3D city models. • Color and deformation lenses modify the appearance and geometry of 3D city models to facilitate their perception. The presented techniques for 3D information lenses and their application to virtual 3D city models clarify their potential for interactive visualization and form a base for further development.}, language = {en} } @phdthesis{Trapp2013, author = {Trapp, Matthias}, title = {Interactive rendering techniques for focus+context visualization of 3D geovirtual environments}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-66824}, school = {Universit{\"a}t Potsdam}, year = {2013}, abstract = {This thesis introduces a collection of new real-time rendering techniques and applications for focus+context visualization of interactive 3D geovirtual environments such as virtual 3D city and landscape models. These environments are generally characterized by a large number of objects and are of high complexity with respect to geometry and textures. For these reasons, their interactive 3D rendering represents a major challenge. Their 3D depiction implies a number of weaknesses such as occlusions, cluttered image contents, and partial screen-space usage. To overcome these limitations and, thus, to facilitate the effective communication of geo-information, principles of focus+context visualization can be used for the design of real-time 3D rendering techniques for 3D geovirtual environments (see Figure). In general, detailed views of a 3D geovirtual environment are combined seamlessly with abstracted views of the context within a single image. To perform the real-time image synthesis required for interactive visualization, dedicated parallel processors (GPUs) for rasterization of computer graphics primitives are used. For this purpose, the design and implementation of appropriate data structures and rendering pipelines are necessary. The contribution of this work comprises the following five real-time rendering methods: • The rendering technique for 3D generalization lenses enables the combination of different 3D city geometries (e.g., generalized versions of a 3D city model) in a single image in real time. The method is based on a generalized and fragment-precise clipping approach, which uses a compressible, raster-based data structure. It enables the combination of detailed views in the focus area with the representation of abstracted variants in the context area. • The rendering technique for the interactive visualization of dynamic raster data in 3D geovirtual environments facilitates the rendering of 2D surface lenses. It enables a flexible combination of different raster layers (e.g., aerial images or videos) using projective texturing for decoupling image and geometry data. Thus, various overlapping and nested 2D surface lenses of different contents can be visualized interactively. • The interactive rendering technique for image-based deformation of 3D geovirtual environments enables the real-time image synthesis of non-planar projections, such as cylindrical and spherical projections, as well as multi-focal 3D fisheye-lenses and the combination of planar and non-planar projections. • The rendering technique for view-dependent multi-perspective views of 3D geovirtual environments, based on the application of global deformations to the 3D scene geometry, can be used for synthesizing interactive panorama maps to combine detailed views close to the camera (focus) with abstract views in the background (context). This approach reduces occlusions, increases the usage the available screen space, and reduces the overload of image contents. • The object-based and image-based rendering techniques for highlighting objects and focus areas inside and outside the view frustum facilitate preattentive perception. The concepts and implementations of interactive image synthesis for focus+context visualization and their selected applications enable a more effective communication of spatial information, and provide building blocks for design and development of new applications and systems in the field of 3D geovirtual environments.}, language = {en} } @article{TorkuraSukmanaChengetal.2020, author = {Torkura, Kennedy A. and Sukmana, Muhammad Ihsan Haikal and Cheng, Feng and Meinel, Christoph}, title = {CloudStrike}, series = {IEEE access : practical research, open solutions}, volume = {8}, journal = {IEEE access : practical research, open solutions}, publisher = {Institute of Electrical and Electronics Engineers }, address = {Piscataway}, issn = {2169-3536}, doi = {10.1109/ACCESS.2020.3007338}, pages = {123044 -- 123060}, year = {2020}, abstract = {Most cyber-attacks and data breaches in cloud infrastructure are due to human errors and misconfiguration vulnerabilities. Cloud customer-centric tools are imperative for mitigating these issues, however existing cloud security models are largely unable to tackle these security challenges. Therefore, novel security mechanisms are imperative, we propose Risk-driven Fault Injection (RDFI) techniques to address these challenges. RDFI applies the principles of chaos engineering to cloud security and leverages feedback loops to execute, monitor, analyze and plan security fault injection campaigns, based on a knowledge-base. The knowledge-base consists of fault models designed from secure baselines, cloud security best practices and observations derived during iterative fault injection campaigns. These observations are helpful for identifying vulnerabilities while verifying the correctness of security attributes (integrity, confidentiality and availability). Furthermore, RDFI proactively supports risk analysis and security hardening efforts by sharing security information with security mechanisms. We have designed and implemented the RDFI strategies including various chaos engineering algorithms as a software tool: CloudStrike. Several evaluations have been conducted with CloudStrike against infrastructure deployed on two major public cloud infrastructure: Amazon Web Services and Google Cloud Platform. The time performance linearly increases, proportional to increasing attack rates. Also, the analysis of vulnerabilities detected via security fault injection has been used to harden the security of cloud resources to demonstrate the effectiveness of the security information provided by CloudStrike. Therefore, we opine that our approaches are suitable for overcoming contemporary cloud security issues.}, 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{Tiwari2019, author = {Tiwari, Abhishek}, title = {Enhancing Users' Privacy: Static Resolution of the Dynamic Properties of Android}, school = {Universit{\"a}t Potsdam}, pages = {xiii, 111}, year = {2019}, abstract = {The usage of mobile devices is rapidly growing with Android being the most prevalent mobile operating system. Thanks to the vast variety of mobile applications, users are preferring smartphones over desktops for day to day tasks like Internet surfing. Consequently, smartphones store a plenitude of sensitive data. This data together with the high values of smartphones make them an attractive target for device/data theft (thieves/malicious applications). Unfortunately, state-of-the-art anti-theft solutions do not work if they do not have an active network connection, e.g., if the SIM card was removed from the device. In the majority of these cases, device owners permanently lose their smartphone together with their personal data, which is even worse. Apart from that malevolent applications perform malicious activities to steal sensitive information from smartphones. Recent research considered static program analysis to detect dangerous data leaks. These analyses work well for data leaks due to inter-component communication, but suffer from shortcomings for inter-app communication with respect to precision, soundness, and scalability. This thesis focuses on enhancing users' privacy on Android against physical device loss/theft and (un)intentional data leaks. It presents three novel frameworks: (1) ThiefTrap, an anti-theft framework for Android, (2) IIFA, a modular inter-app intent information flow analysis of Android applications, and (3) PIAnalyzer, a precise approach for PendingIntent vulnerability analysis. ThiefTrap is based on a novel concept of an anti-theft honeypot account that protects the owner's data while preventing a thief from resetting the device. We implemented the proposed scheme and evaluated it through an empirical user study with 35 participants. In this study, the owner's data could be protected, recovered, and anti-theft functionality could be performed unnoticed from the thief in all cases. IIFA proposes a novel approach for Android's inter-component/inter-app communication (ICC/IAC) analysis. Our main contribution is the first fully automatic, sound, and precise ICC/IAC information flow analysis that is scalable for realistic apps due to modularity, avoiding combinatorial explosion: Our approach determines communicating apps using short summaries rather than inlining intent calls between components and apps, which requires simultaneously analyzing all apps installed on a device. We evaluate IIFA in terms of precision, recall, and demonstrate its scalability to a large corpus of real-world apps. IIFA reports 62 problematic ICC-/IAC-related information flows via two or more apps/components. PIAnalyzer proposes a novel approach to analyze PendingIntent related vulnerabilities. PendingIntents are a powerful and universal feature of Android for inter-component communication. We empirically evaluate PIAnalyzer on a set of 1000 randomly selected applications and find 1358 insecure usages of PendingIntents, including 70 severe vulnerabilities.}, language = {en} } @phdthesis{Tinnefeld2014, author = {Tinnefeld, Christian}, title = {Building a columnar database on shared main memory-based storage}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-72063}, school = {Universit{\"a}t Potsdam}, pages = {175}, year = {2014}, abstract = {In the field of disk-based parallel database management systems exists a great variety of solutions based on a shared-storage or a shared-nothing architecture. In contrast, main memory-based parallel database management systems are dominated solely by the shared-nothing approach as it preserves the in-memory performance advantage by processing data locally on each server. We argue that this unilateral development is going to cease due to the combination of the following three trends: a) Nowadays network technology features remote direct memory access (RDMA) and narrows the performance gap between accessing main memory inside a server and of a remote server to and even below a single order of magnitude. b) Modern storage systems scale gracefully, are elastic, and provide high-availability. c) A modern storage system such as Stanford's RAMCloud even keeps all data resident in main memory. Exploiting these characteristics in the context of a main-memory parallel database management system is desirable. The advent of RDMA-enabled network technology makes the creation of a parallel main memory DBMS based on a shared-storage approach feasible. This thesis describes building a columnar database on shared main memory-based storage. The thesis discusses the resulting architecture (Part I), the implications on query processing (Part II), and presents an evaluation of the resulting solution in terms of performance, high-availability, and elasticity (Part III). In our architecture, we use Stanford's RAMCloud as shared-storage, and the self-designed and developed in-memory AnalyticsDB as relational query processor on top. AnalyticsDB encapsulates data access and operator execution via an interface which allows seamless switching between local and remote main memory, while RAMCloud provides not only storage capacity, but also processing power. Combining both aspects allows pushing-down the execution of database operators into the storage system. We describe how the columnar data processed by AnalyticsDB is mapped to RAMCloud's key-value data model and how the performance advantages of columnar data storage can be preserved. The combination of fast network technology and the possibility to execute database operators in the storage system opens the discussion for site selection. We construct a system model that allows the estimation of operator execution costs in terms of network transfer, data processed in memory, and wall time. This can be used for database operators that work on one relation at a time - such as a scan or materialize operation - to discuss the site selection problem (data pull vs. operator push). Since a database query translates to the execution of several database operators, it is possible that the optimal site selection varies per operator. For the execution of a database operator that works on two (or more) relations at a time, such as a join, the system model is enriched by additional factors such as the chosen algorithm (e.g. Grace- vs. Distributed Block Nested Loop Join vs. Cyclo-Join), the data partitioning of the respective relations, and their overlapping as well as the allowed resource allocation. We present an evaluation on a cluster with 60 nodes where all nodes are connected via RDMA-enabled network equipment. We show that query processing performance is about 2.4x slower if everything is done via the data pull operator execution strategy (i.e. RAMCloud is being used only for data access) and about 27\% slower if operator execution is also supported inside RAMCloud (in comparison to operating only on main memory inside a server without any network communication at all). The fast-crash recovery feature of RAMCloud can be leveraged to provide high-availability, e.g. a server crash during query execution only delays the query response for about one second. Our solution is elastic in a way that it can adapt to changing workloads a) within seconds, b) without interruption of the ongoing query processing, and c) without manual intervention.}, language = {en} } @book{TietzPelchenMeineletal.2017, author = {Tietz, Christian and Pelchen, Chris and Meinel, Christoph and Schnjakin, Maxim}, title = {Management Digitaler Identit{\"a}ten}, number = {114}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-395-4}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-103164}, publisher = {Universit{\"a}t Potsdam}, pages = {65}, year = {2017}, abstract = {Um den zunehmenden Diebstahl digitaler Identit{\"a}ten zu bek{\"a}mpfen, gibt es bereits mehr als ein Dutzend Technologien. Sie sind, vor allem bei der Authentifizierung per Passwort, mit spezifischen Nachteilen behaftet, haben andererseits aber auch jeweils besondere Vorteile. Wie solche Kommunikationsstandards und -Protokolle wirkungsvoll miteinander kombiniert werden k{\"o}nnen, um dadurch mehr Sicherheit zu erreichen, haben die Autoren dieser Studie analysiert. Sie sprechen sich f{\"u}r neuartige Identit{\"a}tsmanagement-Systeme aus, die sich flexibel auf verschiedene Rollen eines einzelnen Nutzers einstellen k{\"o}nnen und bequemer zu nutzen sind als bisherige Verfahren. Als ersten Schritt auf dem Weg hin zu einer solchen Identit{\"a}tsmanagement-Plattform beschreiben sie die M{\"o}glichkeiten einer Analyse, die sich auf das individuelle Verhalten eines Nutzers oder einer Sache st{\"u}tzt. Ausgewertet werden dabei Sensordaten mobiler Ger{\"a}te, welche die Nutzer h{\"a}ufig bei sich tragen und umfassend einsetzen, also z.B. internetf{\"a}hige Mobiltelefone, Fitness-Tracker und Smart Watches. Die Wissenschaftler beschreiben, wie solche Kleincomputer allein z.B. anhand der Analyse von Bewegungsmustern, Positionsund Netzverbindungsdaten kontinuierlich ein „Vertrauens-Niveau" errechnen k{\"o}nnen. Mit diesem ermittelten „Trust Level" kann jedes Ger{\"a}t st{\"a}ndig die Wahrscheinlichkeit angeben, mit der sein aktueller Benutzer auch der tats{\"a}chliche Besitzer ist, dessen typische Verhaltensmuster es genauestens „kennt". Wenn der aktuelle Wert des Vertrauens-Niveaus (nicht aber die biometrischen Einzeldaten) an eine externe Instanz wie einen Identit{\"a}tsprovider {\"u}bermittelt wird, kann dieser das Trust Level allen Diensten bereitstellen, welche der Anwender nutzt und dar{\"u}ber informieren will. Jeder Dienst ist in der Lage, selbst festzulegen, von welchem Vertrauens-Niveau an er einen Nutzer als authentifiziert ansieht. Erf{\"a}hrt er von einem unter das Limit gesunkenen Trust Level, kann der Identit{\"a}tsprovider seine Nutzung und die anderer Services verweigern. Die besonderen Vorteile dieses Identit{\"a}tsmanagement-Ansatzes liegen darin, dass er keine spezifische und teure Hardware ben{\"o}tigt, um spezifische Daten auszuwerten, sondern lediglich Smartphones und so genannte Wearables. Selbst Dinge wie Maschinen, die Daten {\"u}ber ihr eigenes Verhalten per Sensor-Chip ins Internet funken, k{\"o}nnen einbezogen werden. Die Daten werden kontinuierlich im Hintergrund erhoben, ohne dass sich jemand darum k{\"u}mmern muss. Sie sind nur f{\"u}r die Berechnung eines Wahrscheinlichkeits-Messwerts von Belang und verlassen niemals das Ger{\"a}t. Meldet sich ein Internetnutzer bei einem Dienst an, muss er sich nicht zun{\"a}chst an ein vorher festgelegtes Geheimnis - z.B. ein Passwort - erinnern, sondern braucht nur die Weitergabe seines aktuellen Vertrauens-Wertes mit einem „OK" freizugeben. {\"A}ndert sich das Nutzungsverhalten - etwa durch andere Bewegungen oder andere Orte des Einloggens ins Internet als die {\"u}blichen - wird dies schnell erkannt. Unbefugten kann dann sofort der Zugang zum Smartphone oder zu Internetdiensten gesperrt werden. K{\"u}nftig kann die Auswertung von Verhaltens-Faktoren noch erweitert werden, indem z.B. Routinen an Werktagen, an Wochenenden oder im Urlaub erfasst werden. Der Vergleich mit den live erhobenen Daten zeigt dann an, ob das Verhalten in das {\"u}bliche Muster passt, der Benutzer also mit h{\"o}chster Wahrscheinlichkeit auch der ausgewiesene Besitzer des Ger{\"a}ts ist. {\"U}ber die Techniken des Managements digitaler Identit{\"a}ten und die damit verbundenen Herausforderungen gibt diese Studie einen umfassenden {\"U}berblick. Sie beschreibt zun{\"a}chst, welche Arten von Angriffen es gibt, durch die digitale Identit{\"a}ten gestohlen werden k{\"o}nnen. Sodann werden die unterschiedlichen Verfahren von Identit{\"a}tsnachweisen vorgestellt. Schließlich liefert die Studie noch eine zusammenfassende {\"U}bersicht {\"u}ber die 15 wichtigsten Protokolle und technischen Standards f{\"u}r die Kommunikation zwischen den drei beteiligten Akteuren: Service Provider/Dienstanbieter, Identit{\"a}tsprovider und Nutzer. Abschließend wird aktuelle Forschung des Hasso-Plattner-Instituts zum Identit{\"a}tsmanagement vorgestellt.}, language = {de} } @phdthesis{Thiele2011, author = {Thiele, Sven}, title = {Modeling biological systems with Answer Set Programming}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-59383}, school = {Universit{\"a}t Potsdam}, year = {2011}, abstract = {Biology has made great progress in identifying and measuring the building blocks of life. The availability of high-throughput methods in molecular biology has dramatically accelerated the growth of biological knowledge for various organisms. The advancements in genomic, proteomic and metabolomic technologies allow for constructing complex models of biological systems. An increasing number of biological repositories is available on the web, incorporating thousands of biochemical reactions and genetic regulations. Systems Biology is a recent research trend in life science, which fosters a systemic view on biology. In Systems Biology one is interested in integrating the knowledge from all these different sources into models that capture the interaction of these entities. By studying these models one wants to understand the emerging properties of the whole system, such as robustness. However, both measurements as well as biological networks are prone to considerable incompleteness, heterogeneity and mutual inconsistency, which makes it highly non-trivial to draw biologically meaningful conclusions in an automated way. Therefore, we want to promote Answer Set Programming (ASP) as a tool for discrete modeling in Systems Biology. ASP is a declarative problem solving paradigm, in which a problem is encoded as a logic program such that its answer sets represent solutions to the problem. ASP has intrinsic features to cope with incompleteness, offers a rich modeling language and highly efficient solving technology. We present ASP solutions, for the analysis of genetic regulatory networks, determining consistency with observed measurements and identifying minimal causes for inconsistency. We extend this approach for computing minimal repairs on model and data that restore consistency. This method allows for predicting unobserved data even in case of inconsistency. Further, we present an ASP approach to metabolic network expansion. This approach exploits the easy characterization of reachability in ASP and its various reasoning methods, to explore the biosynthetic capabilities of metabolic reaction networks and generate hypotheses for extending the network. Finally, we present the BioASP library, a Python library which encapsulates our ASP solutions into the imperative programming paradigm. The library allows for an easy integration of ASP solution into system rich environments, as they exist in Systems Biology.}, language = {en} } @book{TessenowFelgentreffBrachaetal.2016, author = {Tessenow, Philipp and Felgentreff, Tim and Bracha, Gilad and Hirschfeld, Robert}, title = {Extending a dynamic programming language and runtime environment with access control}, number = {107}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-373-2}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-92560}, publisher = {Universit{\"a}t Potsdam}, pages = {83}, year = {2016}, abstract = {Complexity in software systems is a major factor driving development and maintenance costs. To master this complexity, software is divided into modules that can be developed and tested separately. In order to support this separation of modules, each module should provide a clean and concise public interface. Therefore, the ability to selectively hide functionality using access control is an important feature in a programming language intended for complex software systems. Software systems are increasingly distributed, adding not only to their inherent complexity, but also presenting security challenges. The object-capability approach addresses these challenges by defining language properties providing only minimal capabilities to objects. One programming language that is based on the object-capability approach is Newspeak, a dynamic programming language designed for modularity and security. The Newspeak specification describes access control as one of Newspeak's properties, because it is a requirement for the object-capability approach. However, access control, as defined in the Newspeak specification, is currently not enforced in its implementation. This work introduces an access control implementation for Newspeak, enabling the security of object-capabilities and enhancing modularity. We describe our implementation of access control for Newspeak. We adapted the runtime environment, the reflective system, the compiler toolchain, and the virtual machine. Finally, we describe a migration strategy for the existing Newspeak code base, so that our access control implementation can be integrated with minimal effort.}, language = {en} } @article{Teske2014, author = {Teske, Daniel}, title = {Geocoder accuracy ranking}, series = {Process design for natural scientists: an agile model-driven approach}, journal = {Process design for natural scientists: an agile model-driven approach}, number = {500}, publisher = {Springer}, address = {Berlin}, isbn = {978-3-662-45005-5}, issn = {1865-0929}, pages = {161 -- 174}, year = {2014}, abstract = {Finding an address on a map is sometimes tricky: the chosen map application may be unfamiliar with the enclosed region. There are several geocoders on the market, they have different databases and algorithms to compute the query. Consequently, the geocoding results differ in their quality. Fortunately the geocoders provide a rich set of metadata. The workflow described in this paper compares this metadata with the aim to find out which geocoder is offering the best-fitting coordinate for a given address.}, language = {en} } @article{TeichmannUllrichWenzetal.2020, author = {Teichmann, Malte and Ullrich, Andr{\´e} and Wenz, Julian and Gronau, Norbert}, title = {Herausforderungen und Handlungsempfehlungen betrieblicher Weiterbildungspraxis in Zeiten der Digitalisierung}, series = {HMD Praxis der Wirtschaftsinformatik}, volume = {57}, journal = {HMD Praxis der Wirtschaftsinformatik}, publisher = {Springer Vieweg}, address = {Wiesbaden}, issn = {1436-3011}, doi = {10.1365/s40702-020-00614-x}, pages = {512 -- 527}, year = {2020}, abstract = {Die Digitalisierung von Produktionsprozessen schreitet mit einer hohen Intensit{\"a}t voran. Weiterbildung hat eine hohe Relevanz f{\"u}r betriebliche Transformationsprozesse. Die betriebliche Weiterbildungspraxis ist den aktuellen Herausforderungen der Digitalisierung jedoch nicht gewachsen. Herausforderungen sind Kompetenzl{\"u}cken der Mitarbeiter, ungewisse Anforderungsprofile und T{\"a}tigkeitstypen, demographischer Wandel sowie veraltete didaktische Ans{\"a}tze. Zudem wird bestehender inhaltlicher und p{\"a}dagogischer Freiraum bei der Gestaltung von Weiterbildung oftmals nur unzureichend ausgenutzt. Die skizzierte Situation f{\"u}hrt dazu, dass der Mehrwert gegenw{\"a}rtiger Qualifizierungsangebote sowohl f{\"u}r Unternehmen als auch Besch{\"a}ftigte nicht ausgesch{\"o}pft wird. Ausgehend von Ver{\"a}nderungen durch Digitalisierung in der Produktion und deren Auswirkungen auf die Kompetenzentwicklung diskutiert dieser Beitrag Herausforderungen gegenw{\"a}rtiger betrieblicher Weiterbildung. Er leitet Handlungsempfehlungen ab, die mithilfe von Beispielen gewerkschaftlich unterst{\"u}tzter Weiterbildungspraxis illustriert werden. Im Ergebnis erhalten Interessierte einen {\"U}berblick {\"u}ber gegenw{\"a}rtige Herausforderungen und Handlungsempfehlungen f{\"u}r die Gestaltung und Durchf{\"u}hrung von Weiterbildung in Zeiten der Digitalisierung.}, language = {de} } @article{TavakoliAlirezazadehHedayatipouretal.2021, author = {Tavakoli, Hamad and Alirezazadeh, Pendar and Hedayatipour, Ava and Nasib, A. H. Banijamali and Landwehr, Niels}, title = {Leaf image-based classification of some common bean cultivars using discriminative convolutional neural networks}, series = {Computers and electronics in agriculture : COMPAG online ; an international journal}, volume = {181}, journal = {Computers and electronics in agriculture : COMPAG online ; an international journal}, publisher = {Elsevier}, address = {Amsterdam [u.a.]}, issn = {0168-1699}, doi = {10.1016/j.compag.2020.105935}, pages = {11}, year = {2021}, abstract = {In recent years, many efforts have been made to apply image processing techniques for plant leaf identification. However, categorizing leaf images at the cultivar/variety level, because of the very low inter-class variability, is still a challenging task. In this research, we propose an automatic discriminative method based on convolutional neural networks (CNNs) for classifying 12 different cultivars of common beans that belong to three various species. We show that employing advanced loss functions, such as Additive Angular Margin Loss and Large Margin Cosine Loss, instead of the standard softmax loss function for the classification can yield better discrimination between classes and thereby mitigate the problem of low inter-class variability. The method was evaluated by classifying species (level I), cultivars from the same species (level II), and cultivars from different species (level III), based on images from the leaf foreside and backside. The results indicate that the performance of the classification algorithm on the leaf backside image dataset is superior. The maximum mean classification accuracies of 95.86, 91.37 and 86.87\% were obtained at the levels I, II and III, respectively. The proposed method outperforms the previous relevant works and provides a reliable approach for plant cultivars identification.}, language = {en} } @article{TalebRohrerBergneretal.2022, author = {Taleb, Aiham and Rohrer, Csaba and Bergner, Benjamin and De Leon, Guilherme and Rodrigues, Jonas Almeida and Schwendicke, Falk and Lippert, Christoph and Krois, Joachim}, title = {Self-supervised learning methods for label-efficient dental caries classification}, series = {Diagnostics : open access journal}, volume = {12}, journal = {Diagnostics : open access journal}, number = {5}, publisher = {MDPI}, address = {Basel}, issn = {2075-4418}, doi = {10.3390/diagnostics12051237}, pages = {15}, year = {2022}, abstract = {High annotation costs are a substantial bottleneck in applying deep learning architectures to clinically relevant use cases, substantiating the need for algorithms to learn from unlabeled data. In this work, we propose employing self-supervised methods. To that end, we trained with three self-supervised algorithms on a large corpus of unlabeled dental images, which contained 38K bitewing radiographs (BWRs). We then applied the learned neural network representations on tooth-level dental caries classification, for which we utilized labels extracted from electronic health records (EHRs). Finally, a holdout test-set was established, which consisted of 343 BWRs and was annotated by three dental professionals and approved by a senior dentist. This test-set was used to evaluate the fine-tuned caries classification models. Our experimental results demonstrate the obtained gains by pretraining models using self-supervised algorithms. These include improved caries classification performance (6 p.p. increase in sensitivity) and, most importantly, improved label-efficiency. In other words, the resulting models can be fine-tuned using few labels (annotations). Our results show that using as few as 18 annotations can produce >= 45\% sensitivity, which is comparable to human-level diagnostic performance. This study shows that self-supervision can provide gains in medical image analysis, particularly when obtaining labels is costly and expensive.}, language = {en} } @phdthesis{Takouna2014, author = {Takouna, Ibrahim}, title = {Energy-efficient and performance-aware virtual machine management for cloud data centers}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-72399}, school = {Universit{\"a}t Potsdam}, year = {2014}, abstract = {Virtualisierte Cloud Datenzentren stellen nach Bedarf Ressourcen zur Verf{\"u}gu-ng, erm{\"o}glichen agile Ressourcenbereitstellung und beherbergen heterogene Applikationen mit verschiedenen Anforderungen an Ressourcen. Solche Datenzentren verbrauchen enorme Mengen an Energie, was die Erh{\"o}hung der Betriebskosten, der W{\"a}rme innerhalb der Zentren und des Kohlendioxidausstoßes verursacht. Der Anstieg des Energieverbrauches kann durch ein ineffektives Ressourcenmanagement, das die ineffiziente Ressourcenausnutzung verursacht, entstehen. Die vorliegende Dissertation stellt detaillierte Modelle und neue Verfahren f{\"u}r virtualisiertes Ressourcenmanagement in Cloud Datenzentren vor. Die vorgestellten Verfahren ziehen das Service-Level-Agreement (SLA) und die Heterogenit{\"a}t der Auslastung bez{\"u}glich des Bedarfs an Speicherzugriffen und Kommunikationsmustern von Web- und HPC- (High Performance Computing) Applikationen in Betracht. Um die pr{\"a}sentierten Techniken zu evaluieren, verwenden wir Simulationen und echte Protokollierung der Auslastungen von Web- und HPC- Applikationen. Außerdem vergleichen wir unser Techniken und Verfahren mit anderen aktuellen Verfahren durch die Anwendung von verschiedenen Performance Metriken. Die Hauptbeitr{\"a}ge dieser Dissertation sind Folgendes: Ein Proaktives auf robuster Optimierung basierendes Ressourcenbereitstellungsverfahren. Dieses Verfahren erh{\"o}ht die F{\"a}higkeit der Hostes zur Verf{\"u}g-ungsstellung von mehr VMs. Gleichzeitig aber wird der unn{\"o}tige Energieverbrauch minimiert. Zus{\"a}tzlich mindert diese Technik unerw{\"u}nschte {\"A}nde-rungen im Energiezustand des Servers. Die vorgestellte Technik nutzt einen auf Intervall basierenden Vorhersagealgorithmus zur Implementierung einer robusten Optimierung. Dabei werden unsichere Anforderungen in Betracht gezogen. Ein adaptives und auf Intervall basierendes Verfahren zur Vorhersage des Arbeitsaufkommens mit hohen, in k{\"u}rzer Zeit auftretenden Schwankungen. Die Intervall basierende Vorhersage ist implementiert in der Standard Abweichung Variante und in der Median absoluter Abweichung Variante. Die Intervall-{\"A}nderungen basieren auf einem adaptiven Vertrauensfenster um die Schwankungen des Arbeitsaufkommens zu bew{\"a}ltigen. Eine robuste VM Zusammenlegung f{\"u}r ein effizientes Energie und Performance Management. Dies erm{\"o}glicht die gegenseitige Abh{\"a}ngigkeit zwischen der Energie und der Performance zu minimieren. Unser Verfahren reduziert die Anzahl der VM-Migrationen im Vergleich mit den neu vor kurzem vorgestellten Verfahren. Dies tr{\"a}gt auch zur Reduzierung des durch das Netzwerk verursachten Energieverbrauches. Außerdem reduziert dieses Verfahren SLA-Verletzungen und die Anzahl von {\"A}nderungen an Energiezus-t{\"a}nden. Ein generisches Modell f{\"u}r das Netzwerk eines Datenzentrums um die verz{\"o}-gerte Kommunikation und ihre Auswirkung auf die VM Performance und auf die Netzwerkenergie zu simulieren. Außerdem wird ein generisches Modell f{\"u}r ein Memory-Bus des Servers vorgestellt. Dieses Modell beinhaltet auch Modelle f{\"u}r die Latenzzeit und den Energieverbrauch f{\"u}r verschiedene Memory Frequenzen. Dies erlaubt eine Simulation der Memory Verz{\"o}gerung und ihre Auswirkung auf die VM-Performance und auf den Memory Energieverbrauch. Kommunikation bewusste und Energie effiziente Zusammenlegung f{\"u}r parallele Applikationen um die dynamische Entdeckung von Kommunikationsmustern und das Umplanen von VMs zu erm{\"o}glichen. Das Umplanen von VMs benutzt eine auf den entdeckten Kommunikationsmustern basierende Migration. Eine neue Technik zur Entdeckung von dynamischen Mustern ist implementiert. Sie basiert auf der Signal Verarbeitung des Netzwerks von VMs, anstatt die Informationen des virtuellen Umstellung der Hosts oder der Initiierung der VMs zu nutzen. Das Ergebnis zeigt, dass unsere Methode die durchschnittliche Anwendung des Netzwerks reduziert und aufgrund der Reduzierung der aktiven Umstellungen Energie gespart. Außerdem bietet sie eine bessere VM Performance im Vergleich zu der CPU-basierten Platzierung. Memory bewusste VM Zusammenlegung f{\"u}r unabh{\"a}ngige VMs. Sie nutzt die Vielfalt des VMs Memory Zuganges um die Anwendung vom Memory-Bus der Hosts zu balancieren. Die vorgestellte Technik, Memory-Bus Load Balancing (MLB), verteilt die VMs reaktiv neu im Bezug auf ihre Anwendung vom Memory-Bus. Sie nutzt die VM Migration um die Performance des gesamtem Systems zu verbessern. Außerdem sind die dynamische Spannung, die Frequenz Skalierung des Memory und die MLB Methode kombiniert um ein besseres Energiesparen zu leisten.}, 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} } @inproceedings{SultanowChircuWuestemannetal.2022, author = {Sultanow, Eldar and Chircu, Alina and W{\"u}stemann, Stefanie and Schwan, Andr{\´e} and Lehmann, Andreas and Sept, Andr{\´e} and Szymaski, Oliver and Venkatesan, Sripriya and Ritterbusch, Georg David and Teichmann, Malte Rolf}, title = {Metaverse opportunities for the public sector}, series = {International Conference on Information Systems 2022 : Special Interest Group on Big Data : Proceedings}, booktitle = {International Conference on Information Systems 2022 : Special Interest Group on Big Data : Proceedings}, publisher = {AIS}, address = {Atlanta}, year = {2022}, abstract = {The metaverse is envisioned as a virtual shared space facilitated by emerging technologies such as virtual reality (VR), augmented reality (AR), the Internet of Things (IoT), 5G, artificial intelligence (AI), big data, spatial computing, and digital twins (Allam et al., 2022; Dwivedi et al., 2022; Ravenscraft, 2022; Wiles, 2022). While still a nascent concept, the metaverse has the potential to "transform the physical world, as well as transport or extend physical activities to a virtual world" (Wiles, 2022). Big data technologies will also be essential in managing the enormous amounts of data created in the metaverse (Sun et al., 2022). Metaverse technologies can offer the public sector a host of benefits, such as simplified information exchange, stronger communication with citizens, better access to public services, or benefiting from a new virtual economy. Implementations are underway in several cities around the world (Geraghty et al., 2022). In this paper, we analyze metaverse opportunities for the public sector and explore their application in the context of Germany's Federal Employment Agency. Based on an analysis of academic literature and practical examples, we create a capability map for potential metaverse business capabilities for different areas of the public sector (broadly defined). These include education (virtual training and simulation, digital campuses that offer not just online instruction but a holistic university campus experience, etc.), tourism (virtual travel to remote locations and museums, virtual festival participation, etc.), health (employee training - as for emergency situations, virtual simulations for patient treatment - for example, for depression or anxiety, etc.), military (virtual training to experience operational scenarios without being exposed to a real-world threats, practice strategic decision-making, or gain technical knowledge for operating and repairing equipment, etc.), administrative services (document processing, virtual consultations for citizens, etc.), judiciary (AI decision-making aids, virtual proceedings, etc.), public safety (virtual training for procedural issues, special operations, or unusual situations, etc.), emergency management (training for natural disasters, etc.), and city planning (visualization of future development projects and interactive feedback, traffic management, attraction gamification, etc.), among others. We further identify several metaverse application areas for Germany's Federal Employment Agency. These applications can help it realize the goals of the German government for digital transformation that enables faster, more effective, and innovative government services. They include training of employees, training of customers, and career coaching for customers. These applications can be implemented using interactive learning games with AI agents, virtual representations of the organizational spaces, and avatars interacting with each other in these spaces. Metaverse applications will both use big data (to design the virtual environments) and generate big data (from virtual interactions). Issues related to data availability, quality, storage, processing (and related computing power requirements), interoperability, sharing, privacy and security will need to be addressed in these emerging metaverse applications (Sun et al., 2022). Special attention is needed to understand the potential for power inequities (wealth inequity, algorithmic bias, digital exclusion) due to technologies such as VR (Egliston \& Carter, 2021), harmful surveillance practices (Bibri \& Allam, 2022), and undesirable user behavior or negative psychological impacts (Dwivedi et al., 2022). The results of this exploratory study can inform public sector organizations of emerging metaverse opportunities and enable them to develop plans for action as more of the metaverse technologies become a reality. While the metaverse body of research is still small and research agendas are only now starting to emerge (Dwivedi et al., 2022), this study offers a building block for future development and analysis of metaverse applications.}, language = {en} } @misc{StudenTiberius2020, author = {Studen, Laura and Tiberius, Victor}, title = {Social Media, Quo Vadis?}, series = {Postprints der Universit{\"a}t Potsdam : Wirtschafts- und Sozialwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Wirtschafts- und Sozialwissenschaftliche Reihe}, number = {131}, issn = {1867-5808}, doi = {10.25932/publishup-48293}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-482934}, pages = {24}, year = {2020}, abstract = {Over the past two decades, social media have become a crucial and omnipresent cultural and economic phenomenon, which has seen platforms come and go and advance technologically. In this study, we explore the further development of social media regarding interactive technologies, platform development, relationships to news media, the activities of institutional and organizational users, and effects of social media on the individual and the society over the next five to ten years by conducting an international, two-stage Delphi study. Our results show that enhanced interaction on platforms, including virtual and augmented reality, somatosensory sense, and touch- and movement-based navigation are expected. AIs will interact with other social media users. Inactive user profiles will outnumber active ones. Platform providers will diversify into the WWW, e-commerce, edu-tech, fintechs, the automobile industry, and HR. They will change to a freemium business model and put more effort into combating cybercrime. Social media will become the predominant news distributor, but fake news will still be problematic. Firms will spend greater amounts of their budgets on social media advertising, and schools, politicians, and the medical sector will increase their social media engagement. Social media use will increasingly lead to individuals' psychic issues. Society will benefit from economic growth and new jobs, increased political interest, democratic progress, and education due to social media. However, censorship and the energy consumption of platform operators might rise.}, language = {en} } @article{StudenTiberius2020, author = {Studen, Laura and Tiberius, Victor}, title = {Social Media, Quo Vadis?}, series = {Future Internet}, volume = {12}, journal = {Future Internet}, number = {9}, publisher = {MDPI}, address = {Basel}, issn = {1999-5903}, doi = {10.3390/fi12090146}, pages = {22}, year = {2020}, abstract = {Over the past two decades, social media have become a crucial and omnipresent cultural and economic phenomenon, which has seen platforms come and go and advance technologically. In this study, we explore the further development of social media regarding interactive technologies, platform development, relationships to news media, the activities of institutional and organizational users, and effects of social media on the individual and the society over the next five to ten years by conducting an international, two-stage Delphi study. Our results show that enhanced interaction on platforms, including virtual and augmented reality, somatosensory sense, and touch- and movement-based navigation are expected. AIs will interact with other social media users. Inactive user profiles will outnumber active ones. Platform providers will diversify into the WWW, e-commerce, edu-tech, fintechs, the automobile industry, and HR. They will change to a freemium business model and put more effort into combating cybercrime. Social media will become the predominant news distributor, but fake news will still be problematic. Firms will spend greater amounts of their budgets on social media advertising, and schools, politicians, and the medical sector will increase their social media engagement. Social media use will increasingly lead to individuals' psychic issues. Society will benefit from economic growth and new jobs, increased political interest, democratic progress, and education due to social media. However, censorship and the energy consumption of platform operators might rise.}, language = {en} } @article{Steinroetter2021, author = {Steinr{\"o}tter, Bj{\"o}rn}, title = {Das Konzept einer datenaltruistischen Organisation}, series = {Datenschutz und Datensicherheit}, volume = {45}, journal = {Datenschutz und Datensicherheit}, number = {12}, publisher = {Springer}, address = {Berlin}, issn = {1862-2607}, doi = {10.1007/s11623-021-1539-6}, pages = {794 -- 798}, year = {2021}, abstract = {Dass Technologien wie Machine Learning-Anwendungen oder Big bzw. Smart Data- Verfahren unbedingt Daten in ausreichender Menge und G{\"u}te ben{\"o}tigen, erscheint inzwischen als Binsenweisheit. Vor diesem Hintergrund hat insbesondere der EU-Gesetzgeber f{\"u}r sich zuletzt ein neues Bet{\"a}tigungsfeld entdeckt, indem er versucht, auf unterschiedlichen Wegen Anreize zum Datenteilen zu schaffen, um Innovation zu kreieren. Hierzu z{\"a}hlt auch eine geradezu wohlt{\"o}nend mit ,,Datenaltruismus'' verschlagwortete Konstellation. Der Beitrag stellt die diesbez{\"u}glichen Regulierungserw{\"a}gungen auf supranationaler Ebene dar und nimmt eine erste Analyse vor.}, language = {de} } @article{SteinertStabernack2022, author = {Steinert, Fritjof and Stabernack, Benno}, title = {Architecture of a low latency H.264/AVC video codec for robust ML based image classification how region of interests can minimize the impact of coding artifacts}, series = {Journal of Signal Processing Systems for Signal, Image, and Video Technology}, volume = {94}, journal = {Journal of Signal Processing Systems for Signal, Image, and Video Technology}, number = {7}, publisher = {Springer}, address = {New York}, issn = {1939-8018}, doi = {10.1007/s11265-021-01727-2}, pages = {693 -- 708}, year = {2022}, abstract = {The use of neural networks is considered as the state of the art in the field of image classification. A large number of different networks are available for this purpose, which, appropriately trained, permit a high level of classification accuracy. Typically, these networks are applied to uncompressed image data, since a corresponding training was also carried out using image data of similar high quality. However, if image data contains image errors, the classification accuracy deteriorates drastically. This applies in particular to coding artifacts which occur due to image and video compression. Typical application scenarios for video compression are narrowband transmission channels for which video coding is required but a subsequent classification is to be carried out on the receiver side. In this paper we present a special H.264/Advanced Video Codec (AVC) based video codec that allows certain regions of a picture to be coded with near constant picture quality in order to allow a reliable classification using neural networks, whereas the remaining image will be coded using constant bit rate. We have combined this feature with the ability to run with lowest latency properties, which is usually also required in remote control applications scenarios. The codec has been implemented as a fully hardwired High Definition video capable hardware architecture which is suitable for Field Programmable Gate Arrays.}, language = {en} } @phdthesis{Steinert2014, author = {Steinert, Bastian}, title = {Built-in recovery support for explorative programming}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-71305}, school = {Universit{\"a}t Potsdam}, year = {2014}, abstract = {This work introduces concepts and corresponding tool support to enable a complementary approach in dealing with recovery. Programmers need to recover a development state, or a part thereof, when previously made changes reveal undesired implications. However, when the need arises suddenly and unexpectedly, recovery often involves expensive and tedious work. To avoid tedious work, literature recommends keeping away from unexpected recovery demands by following a structured and disciplined approach, which consists of the application of various best practices including working only on one thing at a time, performing small steps, as well as making proper use of versioning and testing tools. However, the attempt to avoid unexpected recovery is both time-consuming and error-prone. On the one hand, it requires disproportionate effort to minimize the risk of unexpected situations. On the other hand, applying recommended practices selectively, which saves time, can hardly avoid recovery. In addition, the constant need for foresight and self-control has unfavorable implications. It is exhaustive and impedes creative problem solving. This work proposes to make recovery fast and easy and introduces corresponding support called CoExist. Such dedicated support turns situations of unanticipated recovery from tedious experiences into pleasant ones. It makes recovery fast and easy to accomplish, even if explicit commits are unavailable or tests have been ignored for some time. When mistakes and unexpected insights are no longer associated with tedious corrective actions, programmers are encouraged to change source code as a means to reason about it, as opposed to making changes only after structuring and evaluating them mentally. This work further reports on an implementation of the proposed tool support in the Squeak/Smalltalk development environment. The development of the tools has been accompanied by regular performance and usability tests. In addition, this work investigates whether the proposed tools affect programmers' performance. In a controlled lab study, 22 participants improved the design of two different applications. Using a repeated measurement setup, the study examined the effect of providing CoExist on programming performance. The result of analyzing 88 hours of programming suggests that built-in recovery support as provided with CoExist positively has a positive effect on programming performance in explorative programming tasks.}, language = {en} } @book{Stechert2009, author = {Stechert, Peer}, title = {Fachdidaktische Diskussion von Informatiksystemen und der Kompetenzentwicklung im Informatikunterricht}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-024-3}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-37959}, publisher = {Universit{\"a}t Potsdam}, pages = {xiv, 359}, year = {2009}, abstract = {In der vorliegenden Arbeit wird ein Unterrichtsmodell zur Kompetenzentwicklung mit Informatiksystemen f{\"u}r die Sekundarstufe II vorgestellt. Der Bedarf wird u. a. damit begr{\"u}ndet, dass Informatiksysteme zu Beginn des 21. Jahrhunderts allgegenw{\"a}rtig sind (Kapitel 1). F{\"u}r Kompetenzentwicklung mit Informatiksystemen sind diese in ihrer Einheit aus Hardware, Software und Vernetzung anhand ihres nach außen sichtbaren Verhaltens, der inneren Struktur und Implementierungsaspekten zu analysieren. Ausgehend vom Kompetenzbegriff (Kapitel 2) und dem Informatiksystembegriff (Kapitel 3) erfolgt eine Analyse des fachdidaktischen Forschungsstandes zur Kompetenzentwicklung mit Informatiksystemen. Die Ergebnisse lassen sich in die Bereiche (1) Bildungsziele, (2) Unterrichtsinhalte, (3) Lehr-Lernmethodik und (4) Lehr-Lernmedien aufteilen (Kapitel 4). In Kapitel 5 wird die Unterrichtsmodellentwicklung beschrieben. Den Zugang zu Informatiksystemen bildet in der vorliegenden Dissertationsschrift das nach außen sichtbare Verhalten. Es erfolgt eine Fokussierung auf vernetzte fundamentale Ideen der Informatik und Strukturmodelle von Informatiksystemen als Unterrichtsinhalte. Es wird begr{\"u}ndet, dass ausgew{\"a}hlte objektorientierte Entwurfsmuster vernetzte fundamentale Ideen repr{\"a}sentieren. In Abschnitt 5.4 werden dementsprechend Entwurfsmuster als Wissensrepr{\"a}sentation f{\"u}r vernetzte fundamentale Ideen klassifiziert. Das systematische Erkunden des Verhaltens von Informatiksystemen wird im Informatikunterricht bisher kaum thematisiert. Es werden Sch{\"u}lert{\"a}tigkeiten in Anlehnung an Unterrichtsexperimente angegeben, die Sch{\"u}ler unterst{\"u}tzen, Informatiksysteme bewusst und gezielt anzuwenden (Abschnitt 5.5). Bei dieser Lehr-Lernmethodik werden das nach außen sichtbare Verhalten von Informatiksystemen, im Sinne einer Black-Box, und das Wechselspiel von Verhalten und Struktur bei vorliegender Implementierung des Systems als White-Box analysiert. Die Adressierung schrittweise h{\"o}herer kognitiver Niveaustufen wird in die Entwicklung einbezogen. Unterst{\"u}tzend wird f{\"u}r das Unterrichtsmodell lernf{\"o}rderliche Software gestaltet, die vernetzte fundamentale Ideen in Entwurfsmustern und das Experimentieren aufgreift (Abschnitt 5.6). Schwerpunkte bilden im Unterrichtsmodell zwei Arten von lernf{\"o}rderlicher Software: (1) Die Lernsoftware Pattern Park wurde von einer studentischen Projektgruppe entwickelt. In ihr k{\"o}nnen in Entwurfsmustern enthaltene fundamentale Ideen der Informatik {\"u}ber ihren Lebensweltbezug im Szenario eines Freizeitparks analysiert werden. (2) Als weitere Art Lernsoftware werden kleine Programme eingesetzt, deren innere Struktur durch ausgew{\"a}hlte Entwurfsmuster gebildet und deren Verhalten direkt durch die darin enthaltenen fundamentalen Ideen bestimmt wird. Diese Programme k{\"o}nnen durch die Experimente im Unterricht systematisch untersucht werden. Mit dem Ziel, die normative Perspektive um R{\"u}ckkopplung mit der Praxis zu erg{\"a}nzen, werden zwei Erprobungen im Informatikunterricht vorgenommen. Diese liefern Erkenntnisse zur Machbarkeit des Unterrichtsmodells und dessen Akzeptanz durch die Sch{\"u}ler (Kapitel 6 und 8). Exemplarisch umgesetzt werden die Themen Zugriffskontrolle mit dem Proxymuster, Iteration mit dem Iteratormuster und Systemzust{\"a}nde mit dem Zustandsmuster. Der intensive Austausch mit Informatiklehrpersonen in der Kooperationsschule {\"u}ber Informatiksysteme und Kompetenzentwicklung sowie die Durchf{\"u}hrung von zwei Lehrerfortbildungen erg{\"a}nzen die Beobachtungen im unterrichtlichen Geschehen. Die erste Unterrichtserprobung resultiert in einer Weiterentwicklung des Unterrichtsmodells zu Informatiksystemen und Kompetenzentwicklung (Kapitel 7). Darin erfolgt eine Fokussierung auf das nach außen sichtbare Verhalten von Informatiksystemen und eine Verfeinerung der Perspektiven auf innere Struktur und ausgew{\"a}hlte Implementierungsaspekte. Anschließend wird die zweite Unterrichtserprobung durchgef{\"u}hrt und evaluiert (Kapitel 8). Am Schluss der Forschungsarbeit steht ein in empirischen Phasen erprobtes Unterrichtsmodell.}, subject = {Informatik}, language = {de} } @article{StaufferMengeshaSeifertetal.2022, author = {Stauffer, Maxime and Mengesha, Isaak and Seifert, Konrad and Krawczuk, Igor and Fischer, Jens and Serugendo, Giovanna Di Marzo}, title = {A computational turn in policy process studies}, series = {Complexity}, volume = {2022}, journal = {Complexity}, publisher = {Wiley-Hindawi}, address = {London}, issn = {1076-2787}, doi = {10.1155/2022/8210732}, pages = {17}, year = {2022}, abstract = {The past three decades of policy process studies have seen the emergence of a clear intellectual lineage with regard to complexity. Implicitly or explicitly, scholars have employed complexity theory to examine the intricate dynamics of collective action in political contexts. However, the methodological counterparts to complexity theory, such as computational methods, are rarely used and, even if they are, they are often detached from established policy process theory. Building on a critical review of the application of complexity theory to policy process studies, we present and implement a baseline model of policy processes using the logic of coevolving networks. Our model suggests that an actor's influence depends on their environment and on exogenous events facilitating dialogue and consensus-building. Our results validate previous opinion dynamics models and generate novel patterns. Our discussion provides ground for further research and outlines the path for the field to achieve a computational turn.}, language = {en} } @article{SpiekermannKrasnovaHinzetal.2022, author = {Spiekermann, Sarah and Krasnova, Hanna and Hinz, Oliver and Baumann, Annika and Benlian, Alexander and Gimpel, Henner and Heimbach, Irina and Koester, Antonia and Maedche, Alexander and Niehaves, Bjoern and Risius, Marten and Trenz, Manuel}, title = {Values and ethics in information systems}, series = {Business \& information systems engineering}, volume = {64}, journal = {Business \& information systems engineering}, number = {2}, publisher = {Springer Gabler}, address = {Wiesbaden}, issn = {2363-7005}, doi = {10.1007/s12599-021-00734-8}, pages = {247 -- 264}, year = {2022}, language = {en} } @book{SmirnovZamaniFarahaniWeske2011, author = {Smirnov, Sergey and Zamani Farahani, Armin and Weske, Mathias}, title = {State propagation in abstracted business processes}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-130-1}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-51480}, publisher = {Universit{\"a}t Potsdam}, pages = {16}, year = {2011}, abstract = {Business process models are abstractions of concrete operational procedures that occur in the daily business of organizations. To cope with the complexity of these models, business process model abstraction has been introduced recently. Its goal is to derive from a detailed process model several abstract models that provide a high-level understanding of the process. While techniques for constructing abstract models are reported in the literature, little is known about the relationships between process instances and abstract models. In this paper we show how the state of an abstract activity can be calculated from the states of related, detailed process activities as they happen. The approach uses activity state propagation. With state uniqueness and state transition correctness we introduce formal properties that improve the understanding of state propagation. Algorithms to check these properties are devised. Finally, we use behavioral profiles to identify and classify behavioral inconsistencies in abstract process models that might occur, once activity state propagation is used.}, language = {en} } @book{SmirnovWeidlichMendlingetal.2009, author = {Smirnov, Sergey and Weidlich, Matthias and Mendling, Jan and Weske, Mathias}, title = {Action patterns in business process models}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-009-0}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-33586}, publisher = {Universit{\"a}t Potsdam}, pages = {19}, year = {2009}, abstract = {Business process management experiences a large uptake by the industry, and process models play an important role in the analysis and improvement of processes. While an increasing number of staff becomes involved in actual modeling practice, it is crucial to assure model quality and homogeneity along with providing suitable aids for creating models. In this paper we consider the problem of offering recommendations to the user during the act of modeling. Our key contribution is a concept for defining and identifying so-called action patterns - chunks of actions often appearing together in business processes. In particular, we specify action patterns and demonstrate how they can be identified from existing process model repositories using association rule mining techniques. Action patterns can then be used to suggest additional actions for a process model. Our approach is challenged by applying it to the collection of process models from the SAP Reference Model.}, language = {en} } @book{SmirnovReijersNugterenetal.2010, author = {Smirnov, Sergey and Reijers, Hajo A. and Nugteren, Thijs and Weske, Mathias}, title = {Business process model abstraction : theory and practice}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-054-0}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-41782}, publisher = {Universit{\"a}t Potsdam}, pages = {17}, year = {2010}, abstract = {Business process management aims at capturing, understanding, and improving work in organizations. The central artifacts are process models, which serve different purposes. Detailed process models are used to analyze concrete working procedures, while high-level models show, for instance, handovers between departments. To provide different views on process models, business process model abstraction has emerged. While several approaches have been proposed, a number of abstraction use case that are both relevant for industry and scientifically challenging are yet to be addressed. In this paper we systematically develop, classify, and consolidate different use cases for business process model abstraction. The reported work is based on a study with BPM users in the health insurance sector and validated with a BPM consultancy company and a large BPM vendor. The identified fifteen abstraction use cases reflect the industry demand. The related work on business process model abstraction is evaluated against the use cases, which leads to a research agenda.}, language = {en} } @phdthesis{Smirnov2011, author = {Smirnov, Sergey}, title = {Business process model abstraction}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-60258}, school = {Universit{\"a}t Potsdam}, year = {2011}, abstract = {Business process models are used within a range of organizational initiatives, where every stakeholder has a unique perspective on a process and demands the respective model. As a consequence, multiple process models capturing the very same business process coexist. Keeping such models in sync is a challenge within an ever changing business environment: once a process is changed, all its models have to be updated. Due to a large number of models and their complex relations, model maintenance becomes error-prone and expensive. Against this background, business process model abstraction emerged as an operation reducing the number of stored process models and facilitating model management. Business process model abstraction is an operation preserving essential process properties and leaving out insignificant details in order to retain information relevant for a particular purpose. Process model abstraction has been addressed by several researchers. The focus of their studies has been on particular use cases and model transformations supporting these use cases. This thesis systematically approaches the problem of business process model abstraction shaping the outcome into a framework. We investigate the current industry demand in abstraction summarizing it in a catalog of business process model abstraction use cases. The thesis focuses on one prominent use case where the user demands a model with coarse-grained activities and overall process ordering constraints. We develop model transformations that support this use case starting with the transformations based on process model structure analysis. Further, abstraction methods considering the semantics of process model elements are investigated. First, we suggest how semantically related activities can be discovered in process models-a barely researched challenge. The thesis validates the designed abstraction methods against sets of industrial process models and discusses the method implementation aspects. Second, we develop a novel model transformation, which combined with the related activity discovery allows flexible non-hierarchical abstraction. In this way this thesis advocates novel model transformations that facilitate business process model management and provides the foundations for innovative tool support.}, language = {en} } @article{ShekharReimannMayeretal.2021, author = {Shekhar, Sumit and Reimann, Max and Mayer, Maximilian and Semmo, Amir and Pasewaldt, Sebastian and D{\"o}llner, J{\"u}rgen and Trapp, Matthias}, title = {Interactive photo editing on smartphones via intrinsic decomposition}, series = {Computer graphics forum : journal of the European Association for Computer Graphics}, volume = {40}, journal = {Computer graphics forum : journal of the European Association for Computer Graphics}, publisher = {Blackwell}, address = {Oxford}, issn = {0167-7055}, doi = {10.1111/cgf.142650}, pages = {497 -- 510}, year = {2021}, abstract = {Intrinsic decomposition refers to the problem of estimating scene characteristics, such as albedo and shading, when one view or multiple views of a scene are provided. The inverse problem setting, where multiple unknowns are solved given a single known pixel-value, is highly under-constrained. When provided with correlating image and depth data, intrinsic scene decomposition can be facilitated using depth-based priors, which nowadays is easy to acquire with high-end smartphones by utilizing their depth sensors. In this work, we present a system for intrinsic decomposition of RGB-D images on smartphones and the algorithmic as well as design choices therein. Unlike state-of-the-art methods that assume only diffuse reflectance, we consider both diffuse and specular pixels. For this purpose, we present a novel specularity extraction algorithm based on a multi-scale intensity decomposition and chroma inpainting. At this, the diffuse component is further decomposed into albedo and shading components. We use an inertial proximal algorithm for non-convex optimization (iPiano) to ensure albedo sparsity. Our GPU-based visual processing is implemented on iOS via the Metal API and enables interactive performance on an iPhone 11 Pro. Further, a qualitative evaluation shows that we are able to obtain high-quality outputs. Furthermore, our proposed approach for specularity removal outperforms state-of-the-art approaches for real-world images, while our albedo and shading layer decomposition is faster than the prior work at a comparable output quality. Manifold applications such as recoloring, retexturing, relighting, appearance editing, and stylization are shown, each using the intrinsic layers obtained with our method and/or the corresponding depth data.}, 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{Sens2014, author = {Sens, Henriette}, title = {Web-Based map generalization tools put to the test: a jABC workflow}, series = {Process Design for Natural Scientists: an agile model-driven approach}, journal = {Process Design for Natural Scientists: an agile model-driven approach}, number = {500}, publisher = {Springer}, address = {Berlin}, isbn = {978-3-662-45005-5}, issn = {1865-0929}, pages = {175 -- 185}, year = {2014}, abstract = {Geometric generalization is a fundamental concept in the digital mapping process. An increasing amount of spatial data is provided on the web as well as a range of tools to process it. This jABC workflow is used for the automatic testing of web-based generalization services like mapshaper.org by executing its functionality, overlaying both datasets before and after the transformation and displaying them visually in a .tif file. Mostly Web Services and command line tools are used to build an environment where ESRI shapefiles can be uploaded, processed through a chosen generalization service and finally visualized in Irfanview.}, language = {en} } @phdthesis{Semmo2016, author = {Semmo, Amir}, title = {Design and implementation of non-photorealistic rendering techniques for 3D geospatial data}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-99525}, school = {Universit{\"a}t Potsdam}, pages = {XVI, 155}, year = {2016}, abstract = {Geospatial data has become a natural part of a growing number of information systems and services in the economy, society, and people's personal lives. In particular, virtual 3D city and landscape models constitute valuable information sources within a wide variety of applications such as urban planning, navigation, tourist information, and disaster management. Today, these models are often visualized in detail to provide realistic imagery. However, a photorealistic rendering does not automatically lead to high image quality, with respect to an effective information transfer, which requires important or prioritized information to be interactively highlighted in a context-dependent manner. Approaches in non-photorealistic renderings particularly consider a user's task and camera perspective when attempting optimal expression, recognition, and communication of important or prioritized information. However, the design and implementation of non-photorealistic rendering techniques for 3D geospatial data pose a number of challenges, especially when inherently complex geometry, appearance, and thematic data must be processed interactively. Hence, a promising technical foundation is established by the programmable and parallel computing architecture of graphics processing units. This thesis proposes non-photorealistic rendering techniques that enable both the computation and selection of the abstraction level of 3D geospatial model contents according to user interaction and dynamically changing thematic information. To achieve this goal, the techniques integrate with hardware-accelerated rendering pipelines using shader technologies of graphics processing units for real-time image synthesis. The techniques employ principles of artistic rendering, cartographic generalization, and 3D semiotics—unlike photorealistic rendering—to synthesize illustrative renditions of geospatial feature type entities such as water surfaces, buildings, and infrastructure networks. In addition, this thesis contributes a generic system that enables to integrate different graphic styles—photorealistic and non-photorealistic—and provide their seamless transition according to user tasks, camera view, and image resolution. Evaluations of the proposed techniques have demonstrated their significance to the field of geospatial information visualization including topics such as spatial perception, cognition, and mapping. In addition, the applications in illustrative and focus+context visualization have reflected their potential impact on optimizing the information transfer regarding factors such as cognitive load, integration of non-realistic information, visualization of uncertainty, and visualization on small displays.}, language = {en} } @book{SeitzLinckeReinetal.2021, author = {Seitz, Klara and Lincke, Jens and Rein, Patrick and Hirschfeld, Robert}, title = {Language and tool support for 3D crochet patterns}, number = {137}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-505-7}, issn = {1613-5652}, doi = {10.25932/publishup-49253}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-492530}, publisher = {Universit{\"a}t Potsdam}, pages = {vii, 94}, year = {2021}, abstract = {Crochet is a popular handcraft all over the world. While other techniques such as knitting or weaving have received technical support over the years through machines, crochet is still a purely manual craft. Not just the act of crochet itself is manual but also the process of creating instructions for new crochet patterns, which is barely supported by domain specific digital solutions. This leads to unstructured and often also ambiguous and erroneous pattern instructions. In this report, we propose a concept to digitally represent crochet patterns. This format incorporates crochet techniques which allows domain specific support for crochet pattern designers during the pattern creation and instruction writing process. As contributions, we present a thorough domain analysis, the concept of a graph structure used as domain specific language to specify crochet patterns and a prototype of a projectional editor using the graph as representation format of patterns and a diagramming system to visualize them in 2D and 3D. By analyzing the domain, we learned about crochet techniques and pain points of designers in their pattern creation workflow. These insights are the basis on which we defined the pattern representation. In order to evaluate our concept, we built a prototype by which the feasibility of the concept is shown and we tested the software with professional crochet designers who approved of the concept.}, language = {en} } @phdthesis{Seibel2012, author = {Seibel, Andreas}, title = {Traceability and model management with executable and dynamic hierarchical megamodels}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64222}, school = {Universit{\"a}t Potsdam}, year = {2012}, abstract = {Nowadays, model-driven engineering (MDE) promises to ease software development by decreasing the inherent complexity of classical software development. In order to deliver on this promise, MDE increases the level of abstraction and automation, through a consideration of domain-specific models (DSMs) and model operations (e.g. model transformations or code generations). DSMs conform to domain-specific modeling languages (DSMLs), which increase the level of abstraction, and model operations are first-class entities of software development because they increase the level of automation. Nevertheless, MDE has to deal with at least two new dimensions of complexity, which are basically caused by the increased linguistic and technological heterogeneity. The first dimension of complexity is setting up an MDE environment, an activity comprised of the implementation or selection of DSMLs and model operations. Setting up an MDE environment is both time-consuming and error-prone because of the implementation or adaptation of model operations. The second dimension of complexity is concerned with applying MDE for actual software development. Applying MDE is challenging because a collection of DSMs, which conform to potentially heterogeneous DSMLs, are required to completely specify a complex software system. A single DSML can only be used to describe a specific aspect of a software system at a certain level of abstraction and from a certain perspective. Additionally, DSMs are usually not independent but instead have inherent interdependencies, reflecting (partial) similar aspects of a software system at different levels of abstraction or from different perspectives. A subset of these dependencies are applications of various model operations, which are necessary to keep the degree of automation high. This becomes even worse when addressing the first dimension of complexity. Due to continuous changes, all kinds of dependencies, including the applications of model operations, must also be managed continuously. This comprises maintaining the existence of these dependencies and the appropriate (re-)application of model operations. The contribution of this thesis is an approach that combines traceability and model management to address the aforementioned challenges of configuring and applying MDE for software development. The approach is considered as a traceability approach because it supports capturing and automatically maintaining dependencies between DSMs. The approach is considered as a model management approach because it supports managing the automated (re-)application of heterogeneous model operations. In addition, the approach is considered as a comprehensive model management. Since the decomposition of model operations is encouraged to alleviate the first dimension of complexity, the subsequent composition of model operations is required to counteract their fragmentation. A significant portion of this thesis concerns itself with providing a method for the specification of decoupled yet still highly cohesive complex compositions of heterogeneous model operations. The approach supports two different kinds of compositions - data-flow compositions and context compositions. Data-flow composition is used to define a network of heterogeneous model operations coupled by sharing input and output DSMs alone. Context composition is related to a concept used in declarative model transformation approaches to compose individual model transformation rules (units) at any level of detail. In this thesis, context composition provides the ability to use a collection of dependencies as context for the composition of other dependencies, including model operations. In addition, the actual implementation of model operations, which are going to be composed, do not need to implement any composition concerns. The approach is realized by means of a formalism called an executable and dynamic hierarchical megamodel, based on the original idea of megamodels. This formalism supports specifying compositions of dependencies (traceability and model operations). On top of this formalism, traceability is realized by means of a localization concept, and model management by means of an execution concept.}, language = {en} } @misc{SeewannVerwiebeBuderetal.2022, author = {Seewann, Lena and Verwiebe, Roland and Buder, Claudia and Fritsch, Nina-Sophie}, title = {"Broadcast your gender."}, series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Wirtschafts- und Sozialwissenschaftliche Reihe}, journal = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Wirtschafts- und Sozialwissenschaftliche Reihe}, number = {152}, issn = {1867-5808}, doi = {10.25932/publishup-56628}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-566287}, pages = {16}, year = {2022}, abstract = {Social media platforms provide a large array of behavioral data relevant to social scientific research. However, key information such as sociodemographic characteristics of agents are often missing. This paper aims to compare four methods of classifying social attributes from text. Specifically, we are interested in estimating the gender of German social media creators. By using the example of a random sample of 200 YouTube channels, we compare several classification methods, namely (1) a survey among university staff, (2) a name dictionary method with the World Gender Name Dictionary as a reference list, (3) an algorithmic approach using the website gender-api.com, and (4) a Multinomial Na{\"i}ve Bayes (MNB) machine learning technique. These different methods identify gender attributes based on YouTube channel names and descriptions in German but are adaptable to other languages. Our contribution will evaluate the share of identifiable channels, accuracy and meaningfulness of classification, as well as limits and benefits of each approach. We aim to address methodological challenges connected to classifying gender attributes for YouTube channels as well as related to reinforcing stereotypes and ethical implications.}, language = {en} } @article{SeewannVerwiebeBuderetal.2022, author = {Seewann, Lena and Verwiebe, Roland and Buder, Claudia and Fritsch, Nina-Sophie}, title = {"Broadcast your gender."}, series = {Frontiers in Big Data}, journal = {Frontiers in Big Data}, number = {5}, publisher = {Frontiers}, address = {Lausanne, Schweiz}, issn = {2624-909X}, doi = {10.3389/fdata.2022.908636}, pages = {16}, year = {2022}, abstract = {Social media platforms provide a large array of behavioral data relevant to social scientific research. However, key information such as sociodemographic characteristics of agents are often missing. This paper aims to compare four methods of classifying social attributes from text. Specifically, we are interested in estimating the gender of German social media creators. By using the example of a random sample of 200 YouTube channels, we compare several classification methods, namely (1) a survey among university staff, (2) a name dictionary method with the World Gender Name Dictionary as a reference list, (3) an algorithmic approach using the website gender-api.com, and (4) a Multinomial Na{\"i}ve Bayes (MNB) machine learning technique. These different methods identify gender attributes based on YouTube channel names and descriptions in German but are adaptable to other languages. Our contribution will evaluate the share of identifiable channels, accuracy and meaningfulness of classification, as well as limits and benefits of each approach. We aim to address methodological challenges connected to classifying gender attributes for YouTube channels as well as related to reinforcing stereotypes and ethical implications.}, language = {en} } @inproceedings{SeegererRomeikeTillmannetal.2018, author = {Seegerer, Stefan and Romeike, Ralf and Tillmann, Alexander and Kr{\"o}mker, Detlef and Horn, Florian and Gattinger, Thorsten and Weicker, Karsten and Schmitz, Dennis and Moldt, Daniel and R{\"o}pke, Ren{\´e} and Larisch, Kathrin and Schroeder, Ulrik and Keverp{\"u}tz, Claudia and K{\"u}ppers, Bastian and Striewe, Michael and Kramer, Matthias and Grillenberger, Andreas and Frede, Christiane and Knobelsdorf, Maria and Greven, Christoph}, title = {Hochschuldidaktik der Informatik HDI 2018}, series = {Commentarii informaticae didacticae (CID)}, booktitle = {Commentarii informaticae didacticae (CID)}, number = {12}, editor = {Bergner, Nadine and R{\"o}pke, Ren{\´e} and Schroeder, Ulrik and Kr{\"o}mker, Detlef}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-435-7}, issn = {1868-0844}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-413542}, pages = {161}, year = {2018}, abstract = {Die 8. Fachtagung f{\"u}r Hochschuldidaktik der Informatik (HDI) fand im September 2018 zusammen mit der Deutschen E-Learning Fachtagung Informatik (DeLFI) unter dem gemeinsamen Motto „Digitalisierungswahnsinn? - Wege der Bildungstransformationen" in Frankfurt statt. Dabei widmet sich die HDI allen Fragen der informatischen Bildung im Hochschulbereich. Schwerpunkte bildeten in diesem Jahr u. a.: - Analyse der Inhalte und anzustrebenden Kompetenzen in Informatikveranstaltungen - Programmieren lernen \& Einstieg in Softwareentwicklung - Spezialthemen: Data Science, Theoretische Informatik und Wissenschaftliches Arbeiten Die Fachtagung widmet sich ausgew{\"a}hlten Fragestellungen dieser Themenkomplexe, die durch Vortr{\"a}ge ausgewiesener Experten und durch eingereichte Beitr{\"a}ge intensiv behandelt werden.}, language = {de} } @article{Schuett2014, author = {Sch{\"u}tt, Christine}, title = {Identification of differentially expressed genes}, series = {Process design for natural scientists: an agile model-driven approach}, journal = {Process design for natural scientists: an agile model-driven approach}, number = {500}, publisher = {Springer}, address = {Berlin}, isbn = {978-3-662-45005-5}, issn = {1865-0929}, pages = {127 -- 139}, year = {2014}, abstract = {With the jABC it is possible to realize workflows for numerous questions in different fields. The goal of this project was to create a workflow for the identification of differentially expressed genes. This is of special interest in biology, for it gives the opportunity to get a better insight in cellular changes due to exogenous stress, diseases and so on. With the knowledge that can be derived from the differentially expressed genes in diseased tissues, it becomes possible to find new targets for treatment.}, language = {en} } @article{SchaeferStede2021, author = {Sch{\"a}fer, Robin and Stede, Manfred}, title = {Argument mining on twitter}, series = {Information technology : it ; Methoden und innovative Anwendungen der Informatik und Informationstechnik ; Organ der Fachbereiche 3 und 4 der GI e.V. und des Fachbereichs 6 der ITG}, volume = {63}, journal = {Information technology : it ; Methoden und innovative Anwendungen der Informatik und Informationstechnik ; Organ der Fachbereiche 3 und 4 der GI e.V. und des Fachbereichs 6 der ITG}, number = {1}, publisher = {De Gruyter}, address = {Berlin}, issn = {1611-2776}, doi = {10.1515/itit-2020-0053}, pages = {45 -- 58}, year = {2021}, abstract = {In the last decade, the field of argument mining has grown notably. However, only relatively few studies have investigated argumentation in social media and specifically on Twitter. Here, we provide the, to our knowledge, first critical in-depth survey of the state of the art in tweet-based argument mining. We discuss approaches to modelling the structure of arguments in the context of tweet corpus annotation, and we review current progress in the task of detecting argument components and their relations in tweets. We also survey the intersection of argument mining and stance detection, before we conclude with an outlook.}, language = {en} } @book{SchwarzerWeissSaoumiKitteletal.2023, author = {Schwarzer, Ingo and Weiß-Saoumi, Said and Kittel, Roland and Friedrich, Tobias and Kaynak, Koraltan and Durak, Cemil and Isbarn, Andreas and Diestel, J{\"o}rg and Knittel, Jens and Franz, Marquart and Morra, Carlos and Stahnke, Susanne and Braband, Jens and Dittmann, Johannes and Griebel, Stephan and Krampf, Andreas and Link, Martin and M{\"u}ller, Matthias and Radestock, Jens and Strub, Leo and Bleeke, Kai and Jehl, Leander and Kapitza, R{\"u}diger and Messadi, Ines and Schmidt, Stefan and Schwarz-R{\"u}sch, Signe and Pirl, Lukas and Schmid, Robert and Friedenberger, Dirk and Beilharz, Jossekin Jakob and Boockmeyer, Arne and Polze, Andreas and R{\"o}hrig, Ralf and Sch{\"a}be, Hendrik and Thiermann, Ricky}, title = {RailChain}, number = {152}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-550-7}, issn = {1613-5652}, doi = {10.25932/publishup-57740}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-577409}, publisher = {Universit{\"a}t Potsdam}, pages = {140}, year = {2023}, abstract = {The RailChain project designed, implemented, and experimentally evaluated a juridical recorder that is based on a distributed consensus protocol. That juridical blockchain recorder has been realized as distributed ledger on board the advanced TrainLab (ICE-TD 605 017) of Deutsche Bahn. For the project, a consortium consisting of DB Systel, Siemens, Siemens Mobility, the Hasso Plattner Institute for Digital Engineering, Technische Universit{\"a}t Braunschweig, T{\"U}V Rheinland InterTraffic, and Spherity has been formed. These partners not only concentrated competencies in railway operation, computer science, regulation, and approval, but also combined experiences from industry, research from academia, and enthusiasm from startups. Distributed ledger technologies (DLTs) define distributed databases and express a digital protocol for transactions between business partners without the need for a trusted intermediary. The implementation of a blockchain with real-time requirements for the local network of a railway system (e.g., interlocking or train) allows to log data in the distributed system verifiably in real-time. For this, railway-specific assumptions can be leveraged to make modifications to standard blockchains protocols. EULYNX and OCORA (Open CCS On-board Reference Architecture) are parts of a future European reference architecture for control command and signalling (CCS, Reference CCS Architecture - RCA). Both architectural concepts outline heterogeneous IT systems with components from multiple manufacturers. Such systems introduce novel challenges for the approved and safety-relevant CCS of railways which were considered neither for road-side nor for on-board systems so far. Logging implementations, such as the common juridical recorder on vehicles, can no longer be realized as a central component of a single manufacturer. All centralized approaches are in question. The research project RailChain is funded by the mFUND program and gives practical evidence that distributed consensus protocols are a proper means to immutably (for legal purposes) store state information of many system components from multiple manufacturers. The results of RailChain have been published, prototypically implemented, and experimentally evaluated in large-scale field tests on the advanced TrainLab. At the same time, the project showed how RailChain can be integrated into the road-side and on-board architecture given by OCORA and EULYNX. Logged data can now be analysed sooner and also their trustworthiness is being increased. This enables, e.g., auditable predictive maintenance, because it is ensured that data is authentic and unmodified at any point in time.}, language = {en} } @book{SchwalbKruegerPlattner2013, author = {Schwalb, David and Kr{\"u}ger, Jens and Plattner, Hasso}, title = {Cache conscious column organization in in-memory column stores}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-228-5}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-63890}, publisher = {Universit{\"a}t Potsdam}, pages = {v, 84}, year = {2013}, abstract = {Cost models are an essential part of database systems, as they are the basis of query performance optimization. Based on predictions made by cost models, the fastest query execution plan can be chosen and executed or algorithms can be tuned and optimised. In-memory databases shifts the focus from disk to main memory accesses and CPU costs, compared to disk based systems where input and output costs dominate the overall costs and other processing costs are often neglected. However, modelling memory accesses is fundamentally different and common models do not apply anymore. This work presents a detailed parameter evaluation for the plan operators scan with equality selection, scan with range selection, positional lookup and insert in in-memory column stores. Based on this evaluation, a cost model based on cache misses for estimating the runtime of the considered plan operators using different data structures is developed. Considered are uncompressed columns, bit compressed and dictionary encoded columns with sorted and unsorted dictionaries. Furthermore, tree indices on the columns and dictionaries are discussed. Finally, partitioned columns consisting of one partition with a sorted and one with an unsorted dictionary are investigated. New values are inserted in the unsorted dictionary partition and moved periodically by a merge process to the sorted partition. An efficient attribute merge algorithm is described, supporting the update performance required to run enterprise applications on read-optimised databases. Further, a memory traffic based cost model for the merge process is provided.}, language = {en} }