@phdthesis{Hesse2022, author = {Hesse, Guenter}, title = {A benchmark for enterprise stream processing architectures}, doi = {10.25932/publishup-56600}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-566000}, school = {Universit{\"a}t Potsdam}, pages = {ix, 148}, year = {2022}, abstract = {Data stream processing systems (DSPSs) are a key enabler to integrate continuously generated data, such as sensor measurements, into enterprise applications. DSPSs allow to steadily analyze information from data streams, e.g., to monitor manufacturing processes and enable fast reactions to anomalous behavior. Moreover, DSPSs continuously filter, sample, and aggregate incoming streams of data, which reduces the data size, and thus data storage costs. The growing volumes of generated data have increased the demand for high-performance DSPSs, leading to a higher interest in these systems and to the development of new DSPSs. While having more DSPSs is favorable for users as it allows choosing the system that satisfies their requirements the most, it also introduces the challenge of identifying the most suitable DSPS regarding current needs as well as future demands. Having a solution to this challenge is important because replacements of DSPSs require the costly re-writing of applications if no abstraction layer is used for application development. However, quantifying performance differences between DSPSs is a difficult task. Existing benchmarks fail to integrate all core functionalities of DSPSs and lack tool support, which hinders objective result comparisons. Moreover, no current benchmark covers the combination of streaming data with existing structured business data, which is particularly relevant for companies. This thesis proposes a performance benchmark for enterprise stream processing called ESPBench. With enterprise stream processing, we refer to the combination of streaming and structured business data. Our benchmark design represents real-world scenarios and allows for an objective result comparison as well as scaling of data. The defined benchmark query set covers all core functionalities of DSPSs. The benchmark toolkit automates the entire benchmark process and provides important features, such as query result validation and a configurable data ingestion rate. To validate ESPBench and to ease the use of the benchmark, we propose an example implementation of the ESPBench queries leveraging the Apache Beam software development kit (SDK). The Apache Beam SDK is an abstraction layer designed for developing stream processing applications that is applied in academia as well as enterprise contexts. It allows to run the defined applications on any of the supported DSPSs. The performance impact of Apache Beam is studied in this dissertation as well. The results show that there is a significant influence that differs among DSPSs and stream processing applications. For validating ESPBench, we use the example implementation of the ESPBench queries developed using the Apache Beam SDK. We benchmark the implemented queries executed on three modern DSPSs: Apache Flink, Apache Spark Streaming, and Hazelcast Jet. The results of the study prove the functioning of ESPBench and its toolkit. ESPBench is capable of quantifying performance characteristics of DSPSs and of unveiling differences among systems. The benchmark proposed in this thesis covers all requirements to be applied in enterprise stream processing settings, and thus represents an improvement over the current state-of-the-art.}, language = {en} } @misc{GalkeGerstenkornScherp2018, author = {Galke, Lukas and Gerstenkorn, Gunnar and Scherp, Ansgar}, title = {A case atudy of closed-domain response suggestion with limited training data}, series = {Database and Expert Systems Applications : DEXA 2018 Iinternational workshops}, volume = {903}, journal = {Database and Expert Systems Applications : DEXA 2018 Iinternational workshops}, publisher = {Springer}, address = {Berlin}, isbn = {978-3-319-99133-7}, issn = {1865-0929}, doi = {10.1007/978-3-319-99133-7_18}, pages = {218 -- 229}, year = {2018}, abstract = {We analyze the problem of response suggestion in a closed domain along a real-world scenario of a digital library. We present a text-processing pipeline to generate question-answer pairs from chat transcripts. On this limited amount of training data, we compare retrieval-based, conditioned-generation, and dedicated representation learning approaches for response suggestion. Our results show that retrieval-based methods that strive to find similar, known contexts are preferable over parametric approaches from the conditioned-generation family, when the training data is limited. We, however, identify a specific representation learning approach that is competitive to the retrieval-based approaches despite the training data limitation.}, language = {en} } @article{WuttkeLiLietal.2019, author = {Wuttke, Matthias and Li, Yong and Li, Man and Sieber, Karsten B. and Feitosa, Mary F. and Gorski, Mathias and Tin, Adrienne and Wang, Lihua and Chu, Audrey Y. and Hoppmann, Anselm and Kirsten, Holger and Giri, Ayush and Chai, Jin-Fang and Sveinbjornsson, Gardar and Tayo, Bamidele O. and Nutile, Teresa and Fuchsberger, Christian and Marten, Jonathan and Cocca, Massimiliano and Ghasemi, Sahar and Xu, Yizhe and Horn, Katrin and Noce, Damia and Van der Most, Peter J. and Sedaghat, Sanaz and Yu, Zhi and Akiyama, Masato and Afaq, Saima and Ahluwalia, Tarunveer Singh and Almgren, Peter and Amin, Najaf and Arnlov, Johan and Bakker, Stephan J. L. and Bansal, Nisha and Baptista, Daniela and Bergmann, Sven and Biggs, Mary L. and Biino, Ginevra and Boehnke, Michael and Boerwinkle, Eric and Boissel, Mathilde and B{\"o}ttinger, Erwin and Boutin, Thibaud S. and Brenner, Hermann and Brumat, Marco and Burkhardt, Ralph and Butterworth, Adam S. and Campana, Eric and Campbell, Archie and Campbell, Harry and Canouil, Mickael and Carroll, Robert J. and Catamo, Eulalia and Chambers, John C. and Chee, Miao-Ling and Chee, Miao-Li and Chen, Xu and Cheng, Ching-Yu and Cheng, Yurong and Christensen, Kaare and Cifkova, Renata and Ciullo, Marina and Concas, Maria Pina and Cook, James P. and Coresh, Josef and Corre, Tanguy and Sala, Cinzia Felicita and Cusi, Daniele and Danesh, John and Daw, E. Warwick and De Borst, Martin H. and De Grandi, Alessandro and De Mutsert, Renee and De Vries, Aiko P. J. and Degenhardt, Frauke and Delgado, Graciela and Demirkan, Ayse and Di Angelantonio, Emanuele and Dittrich, Katalin and Divers, Jasmin and Dorajoo, Rajkumar and Eckardt, Kai-Uwe and Ehret, Georg and Elliott, Paul and Endlich, Karlhans and Evans, Michele K. and Felix, Janine F. and Foo, Valencia Hui Xian and Franco, Oscar H. and Franke, Andre and Freedman, Barry I. and Freitag-Wolf, Sandra and Friedlander, Yechiel and Froguel, Philippe and Gansevoort, Ron T. and Gao, He and Gasparini, Paolo and Gaziano, J. Michael and Giedraitis, Vilmantas and Gieger, Christian and Girotto, Giorgia and Giulianini, Franco and Gogele, Martin and Gordon, Scott D. and Gudbjartsson, Daniel F. and Gudnason, Vilmundur and Haller, Toomas and Hamet, Pavel and Harris, Tamara B. and Hartman, Catharina A. and Hayward, Caroline and Hellwege, Jacklyn N. and Heng, Chew-Kiat and Hicks, Andrew A. and Hofer, Edith and Huang, Wei and Hutri-Kahonen, Nina and Hwang, Shih-Jen and Ikram, M. Arfan and Indridason, Olafur S. and Ingelsson, Erik and Ising, Marcus and Jaddoe, Vincent W. V. and Jakobsdottir, Johanna and Jonas, Jost B. and Joshi, Peter K. and Josyula, Navya Shilpa and Jung, Bettina and Kahonen, Mika and Kamatani, Yoichiro and Kammerer, Candace M. and Kanai, Masahiro and Kastarinen, Mika and Kerr, Shona M. and Khor, Chiea-Chuen and Kiess, Wieland and Kleber, Marcus E. and Koenig, Wolfgang and Kooner, Jaspal S. and Korner, Antje and Kovacs, Peter and Kraja, Aldi T. and Krajcoviechova, Alena and Kramer, Holly and Kramer, Bernhard K. and Kronenberg, Florian and Kubo, Michiaki and Kuhnel, Brigitte and Kuokkanen, Mikko and Kuusisto, Johanna and La Bianca, Martina and Laakso, Markku and Lange, Leslie A. and Langefeld, Carl D. and Lee, Jeannette Jen-Mai and Lehne, Benjamin and Lehtimaki, Terho and Lieb, Wolfgang and Lim, Su-Chi and Lind, Lars and Lindgren, Cecilia M. and Liu, Jun and Liu, Jianjun and Loeffler, Markus and Loos, Ruth J. F. and Lucae, Susanne and Lukas, Mary Ann and Lyytikainen, Leo-Pekka and Magi, Reedik and Magnusson, Patrik K. E. and Mahajan, Anubha and Martin, Nicholas G. and Martins, Jade and Marz, Winfried and Mascalzoni, Deborah and Matsuda, Koichi and Meisinger, Christa and Meitinger, Thomas and Melander, Olle and Metspalu, Andres and Mikaelsdottir, Evgenia K. and Milaneschi, Yuri and Miliku, Kozeta and Mishra, Pashupati P. and Program, V. A. Million Veteran and Mohlke, Karen L. and Mononen, Nina and Montgomery, Grant W. and Mook-Kanamori, Dennis O. and Mychaleckyj, Josyf C. and Nadkarni, Girish N. and Nalls, Mike A. and Nauck, Matthias and Nikus, Kjell and Ning, Boting and Nolte, Ilja M. and Noordam, Raymond and Olafsson, Isleifur and Oldehinkel, Albertine J. and Orho-Melander, Marju and Ouwehand, Willem H. and Padmanabhan, Sandosh and Palmer, Nicholette D. and Palsson, Runolfur and Penninx, Brenda W. J. H. and Perls, Thomas and Perola, Markus and Pirastu, Mario and Pirastu, Nicola and Pistis, Giorgio and Podgornaia, Anna I. and Polasek, Ozren and Ponte, Belen and Porteous, David J. and Poulain, Tanja and Pramstaller, Peter P. and Preuss, Michael H. and Prins, Bram P. and Province, Michael A. and Rabelink, Ton J. and Raffield, Laura M. and Raitakari, Olli T. and Reilly, Dermot F. and Rettig, Rainer and Rheinberger, Myriam and Rice, Kenneth M. and Ridker, Paul M. and Rivadeneira, Fernando and Rizzi, Federica and Roberts, David J. and Robino, Antonietta and Rossing, Peter and Rudan, Igor and Rueedi, Rico and Ruggiero, Daniela and Ryan, Kathleen A. and Saba, Yasaman and Sabanayagam, Charumathi and Salomaa, Veikko and Salvi, Erika and Saum, Kai-Uwe and Schmidt, Helena and Schmidt, Reinhold and Ben Schottker, and Schulz, Christina-Alexandra and Schupf, Nicole and Shaffer, Christian M. and Shi, Yuan and Smith, Albert V. and Smith, Blair H. and Soranzo, Nicole and Spracklen, Cassandra N. and Strauch, Konstantin and Stringham, Heather M. and Stumvoll, Michael and Svensson, Per O. and Szymczak, Silke and Tai, E-Shyong and Tajuddin, Salman M. and Tan, Nicholas Y. Q. and Taylor, Kent D. and Teren, Andrej and Tham, Yih-Chung and Thiery, Joachim and Thio, Chris H. L. and Thomsen, Hauke and Thorleifsson, Gudmar and Toniolo, Daniela and Tonjes, Anke and Tremblay, Johanne and Tzoulaki, Ioanna and Uitterlinden, Andre G. and Vaccargiu, Simona and Van Dam, Rob M. and Van der Harst, Pim and Van Duijn, Cornelia M. and Edward, Digna R. Velez and Verweij, Niek and Vogelezang, Suzanne and Volker, Uwe and Vollenweider, Peter and Waeber, Gerard and Waldenberger, Melanie and Wallentin, Lars and Wang, Ya Xing and Wang, Chaolong and Waterworth, Dawn M. and Bin Wei, Wen and White, Harvey and Whitfield, John B. and Wild, Sarah H. and Wilson, James F. and Wojczynski, Mary K. and Wong, Charlene and Wong, Tien-Yin and Xu, Liang and Yang, Qiong and Yasuda, Masayuki and Yerges-Armstrong, Laura M. and Zhang, Weihua and Zonderman, Alan B. and Rotter, Jerome I. and Bochud, Murielle and Psaty, Bruce M. and Vitart, Veronique and Wilson, James G. and Dehghan, Abbas and Parsa, Afshin and Chasman, Daniel I. and Ho, Kevin and Morris, Andrew P. and Devuyst, Olivier and Akilesh, Shreeram and Pendergrass, Sarah A. and Sim, Xueling and Boger, Carsten A. and Okada, Yukinori and Edwards, Todd L. and Snieder, Harold and Stefansson, Kari and Hung, Adriana M. and Heid, Iris M. and Scholz, Markus and Teumer, Alexander and Kottgen, Anna and Pattaro, Cristian}, title = {A catalog of genetic loci associated with kidney function from analyses of a million individuals}, series = {Nature genetics}, volume = {51}, journal = {Nature genetics}, number = {6}, publisher = {Nature Publ. Group}, address = {New York}, organization = {Lifelines COHort Study}, issn = {1061-4036}, doi = {10.1038/s41588-019-0407-x}, pages = {957 -- +}, year = {2019}, abstract = {Chronic kidney disease (CKD) is responsible for a public health burden with multi-systemic complications. Through transancestry meta-analysis of genome-wide association studies of estimated glomerular filtration rate (eGFR) and independent replication (n = 1,046,070), we identified 264 associated loci (166 new). Of these,147 were likely to be relevant for kidney function on the basis of associations with the alternative kidney function marker blood urea nitrogen (n = 416,178). Pathway and enrichment analyses, including mouse models with renal phenotypes, support the kidney as the main target organ. A genetic risk score for lower eGFR was associated with clinically diagnosed CKD in 452,264 independent individuals. Colocalization analyses of associations with eGFR among 783,978 European-ancestry individuals and gene expression across 46 human tissues, including tubulo-interstitial and glomerular kidney compartments, identified 17 genes differentially expressed in kidney. Fine-mapping highlighted missense driver variants in 11 genes and kidney-specific regulatory variants. These results provide a comprehensive priority list of molecular targets for translational research.}, language = {en} } @misc{HalfpapSchlosser2019, author = {Halfpap, Stefan and Schlosser, Rainer}, title = {A Comparison of Allocation Algorithms for Partially Replicated Databases}, series = {2019 IEEE 35th International Conference on Data Engineering (ICDE)}, journal = {2019 IEEE 35th International Conference on Data Engineering (ICDE)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-7474-1}, issn = {1084-4627}, doi = {10.1109/ICDE.2019.00226}, pages = {2008 -- 2011}, year = {2019}, abstract = {Increasing demand for analytical processing capabilities can be managed by replication approaches. However, to evenly balance the replicas' workload shares while at the same time minimizing the data replication factor is a highly challenging allocation problem. As optimal solutions are only applicable for small problem instances, effective heuristics are indispensable. In this paper, we test and compare state-of-the-art allocation algorithms for partial replication. By visualizing and exploring their (heuristic) solutions for different benchmark workloads, we are able to derive structural insights and to detect an algorithm's strengths as well as its potential for improvement. Further, our application enables end-to-end evaluations of different allocations to verify their theoretical performance.}, language = {en} } @misc{TorkuraSukmanaKayemetal.2018, author = {Torkura, Kennedy A. and Sukmana, Muhammad Ihsan Haikal and Kayem, Anne V. D. M. and Cheng, Feng and Meinel, Christoph}, title = {A cyber risk based moving target defense mechanism for microservice architectures}, series = {IEEE Intl Conf on Parallel \& Distributed Processing with Applications, Ubiquitous Computing \& Communications, Big Data \& Cloud Computing, Social Computing \& Networking, Sustainable Computing \& Communications (ISPA/IUCC/BDCloud/SocialCom/SustainCom)}, journal = {IEEE Intl Conf on Parallel \& Distributed Processing with Applications, Ubiquitous Computing \& Communications, Big Data \& Cloud Computing, Social Computing \& Networking, Sustainable Computing \& Communications (ISPA/IUCC/BDCloud/SocialCom/SustainCom)}, publisher = {Institute of Electrical and Electronics Engineers}, address = {Los Alamitos}, isbn = {978-1-7281-1141-4}, issn = {2158-9178}, doi = {10.1109/BDCloud.2018.00137}, pages = {932 -- 939}, year = {2018}, abstract = {Microservice Architectures (MSA) structure applications as a collection of loosely coupled services that implement business capabilities. The key advantages of MSA include inherent support for continuous deployment of large complex applications, agility and enhanced productivity. However, studies indicate that most MSA are homogeneous, and introduce shared vulnerabilites, thus vulnerable to multi-step attacks, which are economics-of-scale incentives to attackers. In this paper, we address the issue of shared vulnerabilities in microservices with a novel solution based on the concept of Moving Target Defenses (MTD). Our mechanism works by performing risk analysis against microservices to detect and prioritize vulnerabilities. Thereafter, security risk-oriented software diversification is employed, guided by a defined diversification index. The diversification is performed at runtime, leveraging both model and template based automatic code generation techniques to automatically transform programming languages and container images of the microservices. Consequently, the microservices attack surfaces are altered thereby introducing uncertainty for attackers while reducing the attackability of the microservices. Our experiments demonstrate the efficiency of our solution, with an average success rate of over 70\% attack surface randomization.}, language = {en} } @phdthesis{Krentz2019, author = {Krentz, Konrad-Felix}, title = {A Denial-of-Sleep-Resilient Medium Access Control Layer for IEEE 802.15.4 Networks}, doi = {10.25932/publishup-43930}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-439301}, school = {Universit{\"a}t Potsdam}, pages = {xiv, 187}, year = {2019}, abstract = {With the emergence of the Internet of things (IoT), plenty of battery-powered and energy-harvesting devices are being deployed to fulfill sensing and actuation tasks in a variety of application areas, such as smart homes, precision agriculture, smart cities, and industrial automation. In this context, a critical issue is that of denial-of-sleep attacks. Such attacks temporarily or permanently deprive battery-powered, energy-harvesting, or otherwise energy-constrained devices of entering energy-saving sleep modes, thereby draining their charge. At the very least, a successful denial-of-sleep attack causes a long outage of the victim device. Moreover, to put battery-powered devices back into operation, their batteries have to be replaced. This is tedious and may even be infeasible, e.g., if a battery-powered device is deployed at an inaccessible location. While the research community came up with numerous defenses against denial-of-sleep attacks, most present-day IoT protocols include no denial-of-sleep defenses at all, presumably due to a lack of awareness and unsolved integration problems. After all, despite there are many denial-of-sleep defenses, effective defenses against certain kinds of denial-of-sleep attacks are yet to be found. The overall contribution of this dissertation is to propose a denial-of-sleep-resilient medium access control (MAC) layer for IoT devices that communicate over IEEE 802.15.4 links. Internally, our MAC layer comprises two main components. The first main component is a denial-of-sleep-resilient protocol for establishing session keys among neighboring IEEE 802.15.4 nodes. The established session keys serve the dual purpose of implementing (i) basic wireless security and (ii) complementary denial-of-sleep defenses that belong to the second main component. The second main component is a denial-of-sleep-resilient MAC protocol. Notably, this MAC protocol not only incorporates novel denial-of-sleep defenses, but also state-of-the-art mechanisms for achieving low energy consumption, high throughput, and high delivery ratios. Altogether, our MAC layer resists, or at least greatly mitigates, all denial-of-sleep attacks against it we are aware of. Furthermore, our MAC layer is self-contained and thus can act as a drop-in replacement for IEEE 802.15.4-compliant MAC layers. In fact, we implemented our MAC layer in the Contiki-NG operating system, where it seamlessly integrates into an existing protocol stack.}, language = {en} } @article{IhdePufahlVoelkeretal.2022, author = {Ihde, Sven and Pufahl, Luise and V{\"o}lker, Maximilian and Goel, Asvin and Weske, Mathias}, title = {A framework for modeling and executing task}, series = {Computing : archives for informatics and numerical computation}, volume = {104}, journal = {Computing : archives for informatics and numerical computation}, publisher = {Springer}, address = {Wien}, issn = {0010-485X}, doi = {10.1007/s00607-022-01093-2}, pages = {2405 -- 2429}, year = {2022}, abstract = {As resources are valuable assets, organizations have to decide which resources to allocate to business process tasks in a way that the process is executed not only effectively but also efficiently. Traditional role-based resource allocation leads to effective process executions, since each task is performed by a resource that has the required skills and competencies to do so. However, the resulting allocations are typically not as efficient as they could be, since optimization techniques have yet to find their way in traditional business process management scenarios. On the other hand, operations research provides a rich set of analytical methods for supporting problem-specific decisions on resource allocation. This paper provides a novel framework for creating transparency on existing tasks and resources, supporting individualized allocations for each activity in a process, and the possibility to integrate problem-specific analytical methods of the operations research domain. To validate the framework, the paper reports on the design and prototypical implementation of a software architecture, which extends a traditional process engine with a dedicated resource management component. This component allows us to define specific resource allocation problems at design time, and it also facilitates optimized resource allocation at run time. The framework is evaluated using a real-world parcel delivery process. The evaluation shows that the quality of the allocation results increase significantly with a technique from operations research in contrast to the traditional applied rule-based approach.}, language = {en} } @misc{GonzalezLopezPufahl2019, author = {Gonzalez-Lopez, Fernanda and Pufahl, Luise}, title = {A Landscape for Case Models}, series = {Enterprise, Business-Process and Information Systems Modeling}, volume = {352}, journal = {Enterprise, Business-Process and Information Systems Modeling}, publisher = {Springer}, address = {Berlin}, isbn = {978-3-030-20618-5}, issn = {1865-1348}, doi = {10.1007/978-3-030-20618-5_6}, pages = {87 -- 102}, year = {2019}, abstract = {Case Management is a paradigm to support knowledge-intensive processes. The different approaches developed for modeling these types of processes tend to result in scattered models due to the low abstraction level at which the inherently complex processes are therein represented. Thus, readability and understandability is more challenging than that of traditional process models. By reviewing existing proposals in the field of process overviews and case models, this paper extends a case modeling language - the fragment-based Case Management (fCM) language - with the goal of modeling knowledge-intensive processes from a higher abstraction level - to generate a so-called fCM landscape. This proposal is empirically evaluated via an online experiment. Results indicate that interpreting an fCM landscape might be more effective and efficient than interpreting an informationally equivalent case model.}, language = {en} } @book{SchneiderLambersOrejas2019, author = {Schneider, Sven and Lambers, Leen and Orejas, Fernando}, title = {A logic-based incremental approach to graph repair}, number = {126}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-462-3}, issn = {1613-5652}, doi = {10.25932/publishup-42751}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-427517}, publisher = {Universit{\"a}t Potsdam}, pages = {34}, year = {2019}, abstract = {Graph repair, restoring consistency of a graph, plays a prominent role in several areas of computer science and beyond: For example, in model-driven engineering, the abstract syntax of models is usually encoded using graphs. Flexible edit operations temporarily create inconsistent graphs not representing a valid model, thus requiring graph repair. Similarly, in graph databases—managing the storage and manipulation of graph data—updates may cause that a given database does not satisfy some integrity constraints, requiring also graph repair. We present a logic-based incremental approach to graph repair, generating a sound and complete (upon termination) overview of least-changing repairs. In our context, we formalize consistency by so-called graph conditions being equivalent to first-order logic on graphs. We present two kind of repair algorithms: State-based repair restores consistency independent of the graph update history, whereas deltabased (or incremental) repair takes this history explicitly into account. Technically, our algorithms rely on an existing model generation algorithm for graph conditions implemented in AutoGraph. Moreover, the delta-based approach uses the new concept of satisfaction (ST) trees for encoding if and how a graph satisfies a graph condition. We then demonstrate how to manipulate these STs incrementally with respect to a graph update.}, language = {en} } @article{dePaulaMarxWolfetal.2022, author = {de Paula, Danielly and Marx, Carolin and Wolf, Ella and Dremel, Christian and Cormican, Kathryn and Uebernickel, Falk}, title = {A managerial mental model to drive innovation in the context of digital transformation}, series = {Industry and innovation}, journal = {Industry and innovation}, publisher = {Routledge, Taylor \& Francis Group}, address = {Abingdon}, issn = {1366-2716}, doi = {10.1080/13662716.2022.2072711}, pages = {24}, year = {2022}, abstract = {Industry 4.0 is transforming how businesses innovate and, as a result, companies are spearheading the movement towards 'Digital Transformation'. While some scholars advocate the use of design thinking to identify new innovative behaviours, cognition experts emphasise the importance of top managers in supporting employees to develop these behaviours. However, there is a dearth of research in this domain and companies are struggling to implement the required behaviours. To address this gap, this study aims to identify and prioritise behavioural strategies conducive to design thinking to inform the creation of a managerial mental model. We identify 20 behavioural strategies from 45 interviewees with practitioners and educators and combine them with the concepts of 'paradigm-mindset-mental model' from cognition theory. The paper contributes to the body of knowledge by identifying and prioritising specific behavioural strategies to form a novel set of survival conditions aligned to the new industrial paradigm of Industry 4.0.}, language = {en} } @article{StaubitzSerthThomasetal.2023, author = {Staubitz, Thomas and Serth, Sebastian and Thomas, Max and Ebner, Martin and Koschutnig-Ebner, Markus and Rampelt, Florian and von Stetten, Alexander and Wittke, Andreas}, title = {A metastandard for the international exchange of MOOCs}, series = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, journal = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, editor = {Meinel, Christoph and Schweiger, Stefanie and Staubitz, Thomas and Conrad, Robert and Alario Hoyos, Carlos and Ebner, Martin and Sancassani, Susanna and Żur, Agnieszka and Friedl, Christian and Halawa, Sherif and Gamage, Dilrukshi and Scott, Jeffrey and Kristine Jonson Carlon, May and Deville, Yves and Gaebel, Michael and Delgado Kloos, Carlos and von Schmieden, Karen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-62415}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-624154}, pages = {147 -- 161}, year = {2023}, abstract = {The MOOChub is a joined web-based catalog of all relevant German and Austrian MOOC platforms that lists well over 750 Massive Open Online Courses (MOOCs). Automatically building such a catalog requires that all partners describe and publicly offer the metadata of their courses in the same way. The paper at hand presents the genesis of the idea to establish a common metadata standard and the story of its subsequent development. The result of this effort is, first, an open-licensed de-facto-standard, which is based on existing commonly used standards and second, a first prototypical platform that is using this standard: the MOOChub, which lists all courses of the involved partners. This catalog is searchable and provides a more comprehensive overview of basically all MOOCs that are offered by German and Austrian MOOC platforms. Finally, the upcoming developments to further optimize the catalog and the metadata standard are reported.}, language = {en} } @article{PerachAlexandron2021, author = {Perach, Shai and Alexandron, Giora}, title = {A MOOC-Based Computer Science Program for Middle School}, series = {EMOOCs 2021}, volume = {2021}, journal = {EMOOCs 2021}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51713}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-517133}, pages = {111 -- 127}, year = {2021}, abstract = {In an attempt to pave the way for more extensive Computer Science Education (CSE) coverage in K-12, this research developed and made a preliminary evaluation of a blended-learning Introduction to CS program based on an academic MOOC. Using an academic MOOC that is pedagogically effective and engaging, such a program may provide teachers with disciplinary scaffolds and allow them to focus their attention on enhancing students' learning experience and nurturing critical 21st-century skills such as self-regulated learning. As we demonstrate, this enabled us to introduce an academic level course to middle-school students. In this research, we developed the principals and initial version of such a program, targeting ninth-graders in science-track classes who learn CS as part of their standard curriculum. We found that the middle-schoolers who participated in the program achieved academic results on par with undergraduate students taking this MOOC for academic credit. Participating students also developed a more accurate perception of the essence of CS as a scientific discipline. The unplanned school closure due to the COVID19 pandemic outbreak challenged the research but underlined the advantages of such a MOOCbased blended learning program above classic pedagogy in times of global or local crises that lead to school closure. While most of the science track classes seem to stop learning CS almost entirely, and the end-of-year MoE exam was discarded, the program's classes smoothly moved to remote learning mode, and students continued to study at a pace similar to that experienced before the school shut down.}, language = {en} } @misc{GieseHenklerHirsch2017, author = {Giese, Holger and Henkler, Stefan and Hirsch, Martin}, title = {A multi-paradigm approach supporting the modular execution of reconfigurable hybrid systems}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-402896}, pages = {34}, year = {2017}, abstract = {Advanced mechatronic systems have to integrate existing technologies from mechanical, electrical and software engineering. They must be able to adapt their structure and behavior at runtime by reconfiguration to react flexibly to changes in the environment. Therefore, a tight integration of structural and behavioral models of the different domains is required. This integration results in complex reconfigurable hybrid systems, the execution logic of which cannot be addressed directly with existing standard modeling, simulation, and code-generation techniques. We present in this paper how our component-based approach for reconfigurable mechatronic systems, M ECHATRONIC UML, efficiently handles the complex interplay of discrete behavior and continuous behavior in a modular manner. In addition, its extension to even more flexible reconfiguration cases is presented.}, language = {en} } @article{NavarroOrejasPinoetal.2021, author = {Navarro, Marisa and Orejas, Fernando and Pino, Elvira and Lambers, Leen}, title = {A navigational logic for reasoning about graph properties}, series = {Journal of logical and algebraic methods in programming}, volume = {118}, journal = {Journal of logical and algebraic methods in programming}, publisher = {Elsevier Science}, address = {Amsterdam [u.a.]}, issn = {2352-2208}, doi = {10.1016/j.jlamp.2020.100616}, pages = {33}, year = {2021}, abstract = {Graphs play an important role in many areas of Computer Science. In particular, our work is motivated by model-driven software development and by graph databases. For this reason, it is very important to have the means to express and to reason about the properties that a given graph may satisfy. With this aim, in this paper we present a visual logic that allows us to describe graph properties, including navigational properties, i.e., properties about the paths in a graph. The logic is equipped with a deductive tableau method that we have proved to be sound and complete.}, language = {en} } @article{KayemMeinelWolthusen2018, author = {Kayem, Anne Voluntas dei Massah and Meinel, Christoph and Wolthusen, Stephen D.}, title = {A resilient smart micro-grid architecture for resource constrained environments}, series = {Smart Micro-Grid Systems Security and Privacy}, volume = {71}, journal = {Smart Micro-Grid Systems Security and Privacy}, publisher = {Springer}, address = {Dordrecht}, isbn = {978-3-319-91427-5}, doi = {10.1007/978-3-319-91427-5_5}, pages = {71 -- 101}, year = {2018}, abstract = {Resource constrained smart micro-grid architectures describe a class of smart micro-grid architectures that handle communications operations over a lossy network and depend on a distributed collection of power generation and storage units. Disadvantaged communities with no or intermittent access to national power networks can benefit from such a micro-grid model by using low cost communication devices to coordinate the power generation, consumption, and storage. Furthermore, this solution is both cost-effective and environmentally-friendly. One model for such micro-grids, is for users to agree to coordinate a power sharing scheme in which individual generator owners sell excess unused power to users wanting access to power. Since the micro-grid relies on distributed renewable energy generation sources which are variable and only partly predictable, coordinating micro-grid operations with distributed algorithms is necessity for grid stability. Grid stability is crucial in retaining user trust in the dependability of the micro-grid, and user participation in the power sharing scheme, because user withdrawals can cause the grid to breakdown which is undesirable. In this chapter, we present a distributed architecture for fair power distribution and billing on microgrids. The architecture is designed to operate efficiently over a lossy communication network, which is an advantage for disadvantaged communities. We build on the architecture to discuss grid coordination notably how tasks such as metering, power resource allocation, forecasting, and scheduling can be handled. All four tasks are managed by a feedback control loop that monitors the performance and behaviour of the micro-grid, and based on historical data makes decisions to ensure the smooth operation of the grid. Finally, since lossy networks are undependable, differentiating system failures from adversarial manipulations is an important consideration for grid stability. We therefore provide a characterisation of potential adversarial models and discuss possible mitigation measures.}, language = {en} } @article{ShlakaOuahibBerrada2023, author = {Shlaka, Souhad and Ouahib, Sara and Berrada, Khalid}, title = {A retrospective feedback of MOOCS in Morocco}, series = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, journal = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, editor = {Meinel, Christoph and Schweiger, Stefanie and Staubitz, Thomas and Conrad, Robert and Alario Hoyos, Carlos and Ebner, Martin and Sancassani, Susanna and Żur, Agnieszka and Friedl, Christian and Halawa, Sherif and Gamage, Dilrukshi and Scott, Jeffrey and Kristine Jonson Carlon, May and Deville, Yves and Gaebel, Michael and Delgado Kloos, Carlos and von Schmieden, Karen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-62482}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-624826}, pages = {317 -- 327}, year = {2023}, abstract = {The integration of MOOCs into the Moroccan Higher Education (MHE) took place in 2013 by developing different partnerships and projects at national and international levels. As elsewhere, the Covid-19 crisis has played an important role in accelerating distance education in MHE. However, based on our experience as both university professors and specialists in educational engineering, the effective execution of the digital transition has not yet been implemented. Thus, in this article, we present a retrospective feedback of MOOCs in Morocco, focusing on the policies taken by the government to better support the digital transition in general and MOOCs in particular. We are therefore seeking to establish an optimal scenario for the promotion of MOOCs, which emphasizes the policies to be considered, and which recalls the importance of conducting a delicate articulation taking into account four levels, namely environmental, institutional, organizational and individual. We conclude with recommendations that are inspired by the Moroccan academic contex that focus on the major role that MOOCs plays for university students and on maintaining lifelong learning.}, language = {en} } @misc{DischerRichterDoellner2018, author = {Discher, S{\"o}ren and Richter, Rico and D{\"o}llner, J{\"u}rgen Roland Friedrich}, title = {A scalable webGL-based approach for visualizing massive 3D point clouds using semantics-dependent rendering techniques}, series = {Web3D 2018: The 23rd International ACM Conference on 3D Web Technology}, journal = {Web3D 2018: The 23rd International ACM Conference on 3D Web Technology}, editor = {Spencer, SN}, publisher = {Association for Computing Machinery}, address = {New York}, isbn = {978-1-4503-5800-2}, doi = {10.1145/3208806.3208816}, pages = {1 -- 9}, year = {2018}, abstract = {3D point cloud technology facilitates the automated and highly detailed digital acquisition of real-world environments such as assets, sites, cities, and countries; the acquired 3D point clouds represent an essential category of geodata used in a variety of geoinformation applications and systems. In this paper, we present a web-based system for the interactive and collaborative exploration and inspection of arbitrary large 3D point clouds. Our approach is based on standard WebGL on the client side and is able to render 3D point clouds with billions of points. It uses spatial data structures and level-of-detail representations to manage the 3D point cloud data and to deploy out-of-core and web-based rendering concepts. By providing functionality for both, thin-client and thick-client applications, the system scales for client devices that are vastly different in computing capabilities. Different 3D point-based rendering techniques and post-processing effects are provided to enable task-specific and data-specific filtering and highlighting, e.g., based on per-point surface categories or temporal information. A set of interaction techniques allows users to collaboratively work with the data, e.g., by measuring distances and areas, by annotating, or by selecting and extracting data subsets. Additional value is provided by the system's ability to display additional, context-providing geodata alongside 3D point clouds and to integrate task-specific processing and analysis operations. We have evaluated the presented techniques and the prototype system with different data sets from aerial, mobile, and terrestrial acquisition campaigns with up to 120 billion points to show their practicality and feasibility.}, language = {en} } @phdthesis{Buschmann2018, author = {Buschmann, Stefan}, title = {A software framework for GPU-based geo-temporal visualization techniques}, doi = {10.25932/publishup-44340}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-443406}, school = {Universit{\"a}t Potsdam}, pages = {viii, 99}, year = {2018}, abstract = {R{\"a}umlich-zeitliche Daten sind Daten, welche sowohl einen Raum- als auch einen Zeitbezug aufweisen. So k{\"o}nnen beispielsweise Zeitreihen von Geodaten, thematische Karten die sich {\"u}ber die Zeit ver{\"a}ndern, oder Bewegungsaufzeichnungen von sich bewegenden Objekten als r{\"a}umlich-zeitliche Daten aufgefasst werden. In der heutigen automatisierten Welt gibt es eine wachsende Anzahl von Datenquellen, die best{\"a}ndig r{\"a}umlich-zeitliche Daten generieren. Hierzu geh{\"o}ren beispielsweise Verkehrs{\"u}berwachungssysteme, die Bewegungsdaten von Menschen oder Fahrzeugen aufzeichnen, Fernerkundungssysteme, welche regelm{\"a}ßig unsere Umgebung scannen und digitale Abbilder wie z.B. Stadt- und Landschaftsmodelle erzeugen, sowie Sensornetzwerke in unterschiedlichsten Anwendungsgebieten, wie z.B. der Logistik, der Verhaltensforschung von Tieren, oder der Klimaforschung. Zur Analyse r{\"a}umlich-zeitlicher Daten werden neben der automatischen Analyse mittels statistischer Methoden und Data-Mining auch explorative Methoden angewendet, welche auf der interaktiven Visualisierung der Daten beruhen. Diese Methode der Analyse basiert darauf, dass Anwender in Form interaktiver Visualisierung die Daten explorieren k{\"o}nnen, wodurch die menschliche Wahrnehmung sowie das Wissen der User genutzt werden, um Muster zu erkennen und dadurch einen Einblick in die Daten zu erlangen. Diese Arbeit beschreibt ein Software-Framework f{\"u}r die Visualisierung r{\"a}umlich-zeitlicher Daten, welches GPU-basierte Techniken beinhaltet, um eine interaktive Visualisierung und Exploration großer r{\"a}umlich-zeitlicher Datens{\"a}tze zu erm{\"o}glichen. Die entwickelten Techniken umfassen Datenhaltung, Prozessierung und Rendering und erm{\"o}glichen es, große Datenmengen in Echtzeit zu prozessieren und zu visualisieren. Die Hauptbeitr{\"a}ge der Arbeit umfassen: - Konzept und Implementierung einer GPU-zentrierten Visualisierungspipeline. Die beschriebenen Techniken basieren auf dem Konzept einer GPU-zentrierten Visualisierungspipeline, in welcher alle Stufen -- Prozessierung,Mapping, Rendering -- auf der GPU ausgef{\"u}hrt werden. Bei diesem Konzept werden die r{\"a}umlich-zeitlichen Daten direkt im GPU-Speicher abgelegt. W{\"a}hrend des Rendering-Prozesses werden dann mittels Shader-Programmen die Daten prozessiert, gefiltert, ein Mapping auf visuelle Attribute vorgenommen, und schließlich die Geometrien f{\"u}r die Visualisierung erzeugt. Datenprozessierung, Filtering und Mapping k{\"o}nnen daher in Echtzeit ausgef{\"u}hrt werden. Dies erm{\"o}glicht es Usern, die Mapping-Parameter sowie den gesamten Visualisierungsprozess interaktiv zu steuern und zu kontrollieren. - Interaktive Visualisierung attributierter 3D-Trajektorien. Es wurde eine Visualisierungsmethode f{\"u}r die interaktive Exploration einer großen Anzahl von 3D Bewegungstrajektorien entwickelt. Die Trajektorien werden dabei innerhalb einer virtuellen geographischen Umgebung in Form von einfachen Geometrien, wie Linien, B{\"a}ndern, Kugeln oder R{\"o}hren dargestellt. Durch interaktives Mapping k{\"o}nnen Attributwerte der Trajektorien oder einzelner Messpunkte auf visuelle Eigenschaften abgebildet werden. Hierzu stehen Form, H{\"o}he, Gr{\"o}ße, Farbe, Textur, sowie Animation zur Verf{\"u}gung. Mithilfe dieses dynamischen Mappings wurden außerdem verschiedene Visualisierungsmethoden implementiert, wie z.B. eine Focus+Context-Visualisierung von Trajektorien mithilfe von interaktiven Dichtekarten, sowie einer Space-Time-Cube-Visualisierung zur Darstellung des zeitlichen Ablaufs einzelner Bewegungen. - Interaktive Visualisierung geographischer Netzwerke. Es wurde eine Visualisierungsmethode zur interaktiven Exploration geo-referenzierter Netzwerke entwickelt, welche die Visualisierung von Netzwerken mit einer großen Anzahl von Knoten und Kanten erm{\"o}glicht. Um die Analyse von Netzwerken verschiedener Gr{\"o}ßen und in unterschiedlichen Kontexten zu erm{\"o}glichen, stehen mehrere virtuelle geographische Umgebungen zur Verf{\"u}gung, wie bspw. ein virtueller 3D-Globus, als auch 2D-Karten mit unterschiedlichen geographischen Projektionen. Zur interaktiven Analyse dieser Netzwerke stehen interaktive Tools wie Filterung, Mapping und Selektion zur Verf{\"u}gung. Des weiteren wurden Visualisierungsmethoden f{\"u}r verschiedene Arten von Netzwerken, wie z.B. 3D-Netzwerke und zeitlich ver{\"a}nderliche Netzwerke, implementiert. Zur Demonstration des Konzeptes wurden interaktive Tools f{\"u}r zwei unterschiedliche Anwendungsf{\"a}lle entwickelt. Das erste beinhaltet die Visualisierung attributierter 3D-Trajektorien, welche die Bewegungen von Flugzeugen um einen Flughafen beschreiben. Es erm{\"o}glicht Nutzern, die Trajektorien von ankommenden und startenden Flugzeugen {\"u}ber den Zeitraum eines Monats interaktiv zu explorieren und zu analysieren. Durch Verwendung der interaktiven Visualisierungsmethoden f{\"u}r 3D-Trajektorien und interaktiven Dichtekarten k{\"o}nnen Einblicke in die Daten gewonnen werden, wie beispielsweise h{\"a}ufig genutzte Flugkorridore, typische sowie untypische Bewegungsmuster, oder ungew{\"o}hnliche Vorkommnisse wie Fehlanfl{\"u}ge. Der zweite Anwendungsfall beinhaltet die Visualisierung von Klimanetzwerken, welche geographischen Netzwerken in der Klimaforschung darstellen. Klimanetzwerke repr{\"a}sentieren die Dynamiken im Klimasystem durch eine Netzwerkstruktur, die die statistische Beziehungen zwischen Orten beschreiben. Das entwickelte Tool erm{\"o}glicht es Analysten, diese großen Netzwerke interaktiv zu explorieren und dadurch die Struktur des Netzwerks zu analysieren und mit den geographischen Daten in Beziehung zu setzen. Interaktive Filterung und Selektion erm{\"o}glichen es, Muster in den Daten zu identifizieren, und so bspw. Cluster in der Netzwerkstruktur oder Str{\"o}mungsmuster zu erkennen.}, language = {en} } @article{KrestelChikkamathHeweletal.2021, author = {Krestel, Ralf and Chikkamath, Renukswamy and Hewel, Christoph and Risch, Julian}, title = {A survey on deep learning for patent analysis}, series = {World patent information}, volume = {65}, journal = {World patent information}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0172-2190}, doi = {10.1016/j.wpi.2021.102035}, pages = {13}, year = {2021}, abstract = {Patent document collections are an immense source of knowledge for research and innovation communities worldwide. The rapid growth of the number of patent documents poses an enormous challenge for retrieving and analyzing information from this source in an effective manner. Based on deep learning methods for natural language processing, novel approaches have been developed in the field of patent analysis. The goal of these approaches is to reduce costs by automating tasks that previously only domain experts could solve. In this article, we provide a comprehensive survey of the application of deep learning for patent analysis. We summarize the state-of-the-art techniques and describe how they are applied to various tasks in the patent domain. In a detailed discussion, we categorize 40 papers based on the dataset, the representation, and the deep learning architecture that were used, as well as the patent analysis task that was targeted. With our survey, we aim to foster future research at the intersection of patent analysis and deep learning and we conclude by listing promising paths for future work.}, language = {en} } @misc{Richly2019, author = {Richly, Keven}, title = {A survey on trajectory data management for hybrid transactional and analytical workloads}, series = {IEEE International Conference on Big Data (Big Data)}, journal = {IEEE International Conference on Big Data (Big Data)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-5035-6}, issn = {2639-1589}, doi = {10.1109/BigData.2018.8622394}, pages = {562 -- 569}, year = {2019}, abstract = {Rapid advances in location-acquisition technologies have led to large amounts of trajectory data. This data is the foundation for a broad spectrum of services driven and improved by trajectory data mining. However, for hybrid transactional and analytical workloads, the storing and processing of rapidly accumulated trajectory data is a non-trivial task. In this paper, we present a detailed survey about state-of-the-art trajectory data management systems. To determine the relevant aspects and requirements for such systems, we developed a trajectory data mining framework, which summarizes the different steps in the trajectory data mining process. Based on the derived requirements, we analyze different concepts to store, compress, index, and process spatio-temporal data. There are various trajectory management systems, which are optimized for scalability, data footprint reduction, elasticity, or query performance. To get a comprehensive overview, we describe and compare different exciting systems. Additionally, the observed similarities in the general structure of different systems are consolidated in a general blueprint of trajectory management systems.}, language = {en} } @phdthesis{Kraus2021, author = {Kraus, Sara Milena}, title = {A Systems Medicine approach for heart valve diseases}, doi = {10.25932/publishup-52226}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-522266}, school = {Universit{\"a}t Potsdam}, pages = {xi, 186}, year = {2021}, abstract = {In Systems Medicine, in addition to high-throughput molecular data (*omics), the wealth of clinical characterization plays a major role in the overall understanding of a disease. Unique problems and challenges arise from the heterogeneity of data and require new solutions to software and analysis methods. The SMART and EurValve studies establish a Systems Medicine approach to valvular heart disease -- the primary cause of subsequent heart failure. With the aim to ascertain a holistic understanding, different *omics as well as the clinical picture of patients with aortic stenosis (AS) and mitral regurgitation (MR) are collected. Our task within the SMART consortium was to develop an IT platform for Systems Medicine as a basis for data storage, processing, and analysis as a prerequisite for collaborative research. Based on this platform, this thesis deals on the one hand with the transfer of the used Systems Biology methods to their use in the Systems Medicine context and on the other hand with the clinical and biomolecular differences of the two heart valve diseases. To advance differential expression/abundance (DE/DA) analysis software for use in Systems Medicine, we state 21 general software requirements and features of automated DE/DA software, including a novel concept for the simple formulation of experimental designs that can represent complex hypotheses, such as comparison of multiple experimental groups, and demonstrate our handling of the wealth of clinical data in two research applications DEAME and Eatomics. In user interviews, we show that novice users are empowered to formulate and test their multiple DE hypotheses based on clinical phenotype. Furthermore, we describe insights into users' general impression and expectation of the software's performance and show their intention to continue using the software for their work in the future. Both research applications cover most of the features of existing tools or even extend them, especially with respect to complex experimental designs. Eatomics is freely available to the research community as a user-friendly R Shiny application. Eatomics continued to help drive the collaborative analysis and interpretation of the proteomic profile of 75 human left myocardial tissue samples from the SMART and EurValve studies. Here, we investigate molecular changes within the two most common types of valvular heart disease: aortic valve stenosis (AS) and mitral valve regurgitation (MR). Through DE/DA analyses, we explore shared and disease-specific protein alterations, particularly signatures that could only be found in the sex-stratified analysis. In addition, we relate changes in the myocardial proteome to parameters from clinical imaging. We find comparable cardiac hypertrophy but differences in ventricular size, the extent of fibrosis, and cardiac function. We find that AS and MR show many shared remodeling effects, the most prominent of which is an increase in the extracellular matrix and a decrease in metabolism. Both effects are stronger in AS. In muscle and cytoskeletal adaptations, we see a greater increase in mechanotransduction in AS and an increase in cortical cytoskeleton in MR. The decrease in proteostasis proteins is mainly attributable to the signature of female patients with AS. We also find relevant therapeutic targets. In addition to the new findings, our work confirms several concepts from animal and heart failure studies by providing the largest collection of human tissue from in vivo collected biopsies to date. Our dataset contributing a resource for isoform-specific protein expression in two of the most common valvular heart diseases. Apart from the general proteomic landscape, we demonstrate the added value of the dataset by showing proteomic and transcriptomic evidence for increased expression of the SARS-CoV-2- receptor at pressure load but not at volume load in the left ventricle and also provide the basis of a newly developed metabolic model of the heart.}, language = {en} } @article{ScheibelTrappLimbergeretal.2020, author = {Scheibel, Willy and Trapp, Matthias and Limberger, Daniel and D{\"o}llner, J{\"u}rgen Roland Friedrich}, title = {A taxonomy of treemap visualization techniques}, series = {Science and Technology Publications}, journal = {Science and Technology Publications}, publisher = {Springer}, address = {Berlin}, pages = {8}, year = {2020}, abstract = {A treemap is a visualization that has been specifically designed to facilitate the exploration of tree-structured data and, more general, hierarchically structured data. The family of visualization techniques that use a visual metaphor for parent-child relationships based "on the property of containment" (Johnson, 1993) is commonly referred to as treemaps. However, as the number of variations of treemaps grows, it becomes increasingly important to distinguish clearly between techniques and their specific characteristics. This paper proposes to discern between Space-filling Treemap TS, Containment Treemap TC, Implicit Edge Representation Tree TIE, and Mapped Tree TMT for classification of hierarchy visualization techniques and highlights their respective properties. This taxonomy is created as a hyponymy, i.e., its classes have an is-a relationship to one another: TS TC TIE TMT. With this proposal, we intend to stimulate a discussion on a more unambiguous classification of treemaps and, furthermore, broaden what is understood by the concept of treemap itself.}, language = {en} } @misc{ScheibelTrappLimbergeretal.2020, author = {Scheibel, Willy and Trapp, Matthias and Limberger, Daniel and D{\"o}llner, J{\"u}rgen Roland Friedrich}, title = {A taxonomy of treemap visualization techniques}, series = {Postprints der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, journal = {Postprints der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, number = {8}, doi = {10.25932/publishup-52469}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-524693}, pages = {10}, year = {2020}, abstract = {A treemap is a visualization that has been specifically designed to facilitate the exploration of tree-structured data and, more general, hierarchically structured data. The family of visualization techniques that use a visual metaphor for parent-child relationships based "on the property of containment" (Johnson, 1993) is commonly referred to as treemaps. However, as the number of variations of treemaps grows, it becomes increasingly important to distinguish clearly between techniques and their specific characteristics. This paper proposes to discern between Space-filling Treemap TS, Containment Treemap TC, Implicit Edge Representation Tree TIE, and Mapped Tree TMT for classification of hierarchy visualization techniques and highlights their respective properties. This taxonomy is created as a hyponymy, i.e., its classes have an is-a relationship to one another: TS TC TIE TMT. With this proposal, we intend to stimulate a discussion on a more unambiguous classification of treemaps and, furthermore, broaden what is understood by the concept of treemap itself.}, language = {en} } @article{NohrHaugsbakken2023, author = {Nohr, Magnus and Haugsbakken, Halvdan}, title = {A taxonomy of video genres as a scaffolding strategy for video making in education}, series = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, journal = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, editor = {Meinel, Christoph and Schweiger, Stefanie and Staubitz, Thomas and Conrad, Robert and Alario Hoyos, Carlos and Ebner, Martin and Sancassani, Susanna and Żur, Agnieszka and Friedl, Christian and Halawa, Sherif and Gamage, Dilrukshi and Scott, Jeffrey and Kristine Jonson Carlon, May and Deville, Yves and Gaebel, Michael and Delgado Kloos, Carlos and von Schmieden, Karen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-62429}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-624294}, pages = {201 -- 220}, year = {2023}, abstract = {This research paper aims to introduce a novel practitioner-oriented and research-based taxonomy of video genres. This taxonomy can serve as a scaffolding strategy to support educators throughout the entire educational system in creating videos for pedagogical purposes. A taxonomy of video genres is essential as videos are highly valued resources among learners. Although the use of videos in education has been extensively researched and well-documented in systematic research reviews, gaps remain in the literature. Predominantly, researchers employ sophisticated quantitative methods and similar approaches to measure the performance of videos. This trend has led to the emergence of a strong learning analytics research tradition with its embedded literature. This body of research includes analysis of performance of videos in online courses such as Massive Open Online Courses (MOOCs). Surprisingly, this same literature is limited in terms of research outlining approaches to designing and creating educational videos, which applies to both video-based learning and online courses. This issue results in a knowledge gap, highlighting the need for developing pedagogical tools and strategies for video making. These can be found in frameworks, guidelines, and taxonomies, which can serve as scaffolding strategies. In contrast, there appears to be very few frameworks available for designing and creating videos for pedagogica purposes, apart from a few well-known frameworks. In this regard, this research paper proposes a novel taxonomy of video genres that educators can utilize when creating videos intended for use in either video-based learning environments or online courses. To create this taxonomy, a large number of videos from online courses were collected and analyzed using a mixed-method research design approach.}, language = {en} } @misc{PerscheidFaberKrausetal.2018, author = {Perscheid, Cindy and Faber, Lukas and Kraus, Milena and Arndt, Paul and Janke, Michael and Rehfeldt, Sebastian and Schubotz, Antje and Slosarek, Tamara and Uflacker, Matthias}, title = {A tissue-aware gene selection approach for analyzing multi-tissue gene expression data}, series = {2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)}, journal = {2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-5488-0}, issn = {2156-1125}, doi = {10.1109/BIBM.2018.8621189}, pages = {2159 -- 2166}, year = {2018}, abstract = {High-throughput RNA sequencing (RNAseq) produces large data sets containing expression levels of thousands of genes. The analysis of RNAseq data leads to a better understanding of gene functions and interactions, which eventually helps to study diseases like cancer and develop effective treatments. Large-scale RNAseq expression studies on cancer comprise samples from multiple cancer types and aim to identify their distinct molecular characteristics. Analyzing samples from different cancer types implies analyzing samples from different tissue origin. Such multi-tissue RNAseq data sets require a meaningful analysis that accounts for the inherent tissue-related bias: The identified characteristics must not originate from the differences in tissue types, but from the actual differences in cancer types. However, current analysis procedures do not incorporate that aspect. As a result, we propose to integrate a tissue-awareness into the analysis of multi-tissue RNAseq data. We introduce an extension for gene selection that provides a tissue-wise context for every gene and can be flexibly combined with any existing gene selection approach. We suggest to expand conventional evaluation by additional metrics that are sensitive to the tissue-related bias. Evaluations show that especially low complexity gene selection approaches profit from introducing tissue-awareness.}, language = {en} } @phdthesis{Katzmann2023, author = {Katzmann, Maximilian}, title = {About the analysis of algorithms on networks with underlying hyperbolic geometry}, doi = {10.25932/publishup-58296}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-582965}, school = {Universit{\"a}t Potsdam}, pages = {xi, 191}, year = {2023}, abstract = {Many complex systems that we encounter in the world can be formalized using networks. Consequently, they have been in the focus of computer science for decades, where algorithms are developed to understand and utilize these systems. Surprisingly, our theoretical understanding of these algorithms and their behavior in practice often diverge significantly. In fact, they tend to perform much better on real-world networks than one would expect when considering the theoretical worst-case bounds. One way of capturing this discrepancy is the average-case analysis, where the idea is to acknowledge the differences between practical and worst-case instances by focusing on networks whose properties match those of real graphs. Recent observations indicate that good representations of real-world networks are obtained by assuming that a network has an underlying hyperbolic geometry. In this thesis, we demonstrate that the connection between networks and hyperbolic space can be utilized as a powerful tool for average-case analysis. To this end, we first introduce strongly hyperbolic unit disk graphs and identify the famous hyperbolic random graph model as a special case of them. We then consider four problems where recent empirical results highlight a gap between theory and practice and use hyperbolic graph models to explain these phenomena theoretically. First, we develop a routing scheme, used to forward information in a network, and analyze its efficiency on strongly hyperbolic unit disk graphs. For the special case of hyperbolic random graphs, our algorithm beats existing performance lower bounds. Afterwards, we use the hyperbolic random graph model to theoretically explain empirical observations about the performance of the bidirectional breadth-first search. Finally, we develop algorithms for computing optimal and nearly optimal vertex covers (problems known to be NP-hard) and show that, on hyperbolic random graphs, they run in polynomial and quasi-linear time, respectively. Our theoretical analyses reveal interesting properties of hyperbolic random graphs and our empirical studies present evidence that these properties, as well as our algorithmic improvements translate back into practice.}, language = {en} } @techreport{DoellnerFriedrichArnrichetal.2022, author = {D{\"o}llner, J{\"u}rgen Roland Friedrich and Friedrich, Tobias and Arnrich, Bert and Hirschfeld, Robert and Lippert, Christoph and Meinel, Christoph}, title = {Abschlussbericht KI-Labor ITSE}, doi = {10.25932/publishup-57860}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-578604}, pages = {60}, year = {2022}, abstract = {Der Abschlussbericht beschreibt Aufgaben und Ergebnisse des KI-Labors "ITSE". Gegenstand des KI-Labors bildeten Methodik, Technik und Ausbildung in der IT-Systemtechnik zur Analyse, Planung und Konstruktion KI-basierter, komplexer IT-Systeme.}, language = {de} } @article{YousfiBatoulisWeske2019, author = {Yousfi, Alaaeddine and Batoulis, Kimon and Weske, Mathias}, title = {Achieving Business Process Improvement via Ubiquitous Decision-Aware Business Processes}, series = {ACM Transactions on Internet Technology}, volume = {19}, journal = {ACM Transactions on Internet Technology}, number = {1}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {1533-5399}, doi = {10.1145/3298986}, pages = {19}, year = {2019}, abstract = {Business process improvement is an endless challenge for many organizations. As long as there is a process, it must he improved. Nowadays, improvement initiatives are driven by professionals. This is no longer practical because people cannot perceive the enormous data of current business environments. Here, we introduce ubiquitous decision-aware business processes. They pervade the physical space, analyze the ever-changing environments, and make decisions accordingly. We explain how they can be built and used for improvement. Our approach can be a valuable improvement option to alleviate the workload of participants by helping focus on the crucial rather than the menial tasks.}, language = {en} } @article{LimanowskiLopesKecketal.2020, author = {Limanowski, Jakub and Lopes, Pedro and Keck, Janis and Baudisch, Patrick and Friston, Karl and Blankenburg, Felix}, title = {Action-dependent processing of touch in the human parietal operculum and posterior insula}, series = {Cerebral Cortex}, volume = {30}, journal = {Cerebral Cortex}, number = {2}, publisher = {Oxford University Press}, address = {Oxford}, issn = {1047-3211}, doi = {10.1093/cercor/bhz111}, pages = {607 -- 617}, year = {2020}, abstract = {Somatosensory input generated by one's actions (i.e., self-initiated body movements) is generally attenuated. Conversely, externally caused somatosensory input is enhanced, for example, during active touch and the haptic exploration of objects. Here, we used functional magnetic resonance imaging (fMRI) to ask how the brain accomplishes this delicate weighting of self-generated versus externally caused somatosensory components. Finger movements were either self-generated by our participants or induced by functional electrical stimulation (FES) of the same muscles. During half of the trials, electrotactile impulses were administered when the (actively or passively) moving finger reached a predefined flexion threshold. fMRI revealed an interaction effect in the contralateral posterior insular cortex (pIC), which responded more strongly to touch during self-generated than during FES-induced movements. A network analysis via dynamic causal modeling revealed that connectivity from the secondary somatosensory cortex via the pIC to the supplementary motor area was generally attenuated during self-generated relative to FES-induced movements-yet specifically enhanced by touch received during self-generated, but not FES-induced movements. Together, these results suggest a crucial role of the parietal operculum and the posterior insula in differentiating self-generated from externally caused somatosensory information received from one's moving limb.}, language = {en} } @phdthesis{Gruetze2018, author = {Gr{\"u}tze, Toni}, title = {Adding value to text with user-generated content}, school = {Universit{\"a}t Potsdam}, pages = {ii, 114}, year = {2018}, abstract = {In recent years, the ever-growing amount of documents on the Web as well as in closed systems for private or business contexts led to a considerable increase of valuable textual information about topics, events, and entities. It is a truism that the majority of information (i.e., business-relevant data) is only available in unstructured textual form. The text mining research field comprises various practice areas that have the common goal of harvesting high-quality information from textual data. These information help addressing users' information needs. In this thesis, we utilize the knowledge represented in user-generated content (UGC) originating from various social media services to improve text mining results. These social media platforms provide a plethora of information with varying focuses. In many cases, an essential feature of such platforms is to share relevant content with a peer group. Thus, the data exchanged in these communities tend to be focused on the interests of the user base. The popularity of social media services is growing continuously and the inherent knowledge is available to be utilized. We show that this knowledge can be used for three different tasks. Initially, we demonstrate that when searching persons with ambiguous names, the information from Wikipedia can be bootstrapped to group web search results according to the individuals occurring in the documents. We introduce two models and different means to handle persons missing in the UGC source. We show that the proposed approaches outperform traditional algorithms for search result clustering. Secondly, we discuss how the categorization of texts according to continuously changing community-generated folksonomies helps users to identify new information related to their interests. We specifically target temporal changes in the UGC and show how they influence the quality of different tag recommendation approaches. Finally, we introduce an algorithm to attempt the entity linking problem, a necessity for harvesting entity knowledge from large text collections. The goal is the linkage of mentions within the documents with their real-world entities. A major focus lies on the efficient derivation of coherent links. For each of the contributions, we provide a wide range of experiments on various text corpora as well as different sources of UGC. The evaluation shows the added value that the usage of these sources provides and confirms the appropriateness of leveraging user-generated content to serve different information needs.}, language = {en} } @misc{Matthies2019, author = {Matthies, Christoph}, title = {Agile process improvement in retrospectives}, series = {41st International Conference on Software Engineering: Companion Proceedings (ICSE-Companion)}, journal = {41st International Conference on Software Engineering: Companion Proceedings (ICSE-Companion)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-7281-1764-5}, issn = {2574-1934}, doi = {10.1109/ICSE-Companion.2019.00063}, pages = {150 -- 152}, year = {2019}, abstract = {Working in iterations and repeatedly improving team workflows based on collected feedback is fundamental to agile software development processes. Scrum, the most popular agile method, provides dedicated retrospective meetings to reflect on the last development iteration and to decide on process improvement actions. However, agile methods do not prescribe how these improvement actions should be identified, managed or tracked in detail. The approaches to detect and remove problems in software development processes are therefore often based on intuition and prior experiences and perceptions of team members. Previous research in this area has focused on approaches to elicit a team's improvement opportunities as well as measurements regarding the work performed in an iteration, e.g. Scrum burn-down charts. Little research deals with the quality and nature of identified problems or how progress towards removing issues is measured. In this research, we investigate how agile development teams in the professional software industry organize their feedback and process improvement approaches. In particular, we focus on the structure and content of improvement and reflection meetings, i.e. retrospectives, and their outcomes. Researching how the vital mechanism of process improvement is implemented in practice in modern software development leads to a more complete picture of agile process improvement.}, language = {en} } @article{HaugsbakkenHagelia2023, author = {Haugsbakken, Halvdan and Hagelia, Marianne}, title = {An asynchronous cooperative leaning design in a Small Private Online Course (SPOC)}, series = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, journal = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, editor = {Meinel, Christoph and Schweiger, Stefanie and Staubitz, Thomas and Conrad, Robert and Alario Hoyos, Carlos and Ebner, Martin and Sancassani, Susanna and Żur, Agnieszka and Friedl, Christian and Halawa, Sherif and Gamage, Dilrukshi and Scott, Jeffrey and Kristine Jonson Carlon, May and Deville, Yves and Gaebel, Michael and Delgado Kloos, Carlos and von Schmieden, Karen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-62210}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-622107}, pages = {67 -- 76}, year = {2023}, abstract = {This short paper sets out to propose a novel and interesting learning design that facilitates for cooperative learning in which students do not conduct traditional group work in an asynchronous online education setting. This learning design will be explored in a Small Private Online Course (SPOC) among teachers and school managers at a teacher education. Such an approach can be made possible by applying specific criteria commonly used to define collaborative learning. Collaboration can be defined, among other things, as a structured way of working among students that includes elements of co-laboring. The cooperative learning design involves adapting various traditional collaborative learning approaches for use in an online learning environment. A critical component of this learning design is that students work on a self-defined case project related to their professional practices. Through an iterative process, students will receive ongoing feedback and formative assessments from instructors and follow students at specific points, meaning that co-constructing of knowledge and learning takes place as the SPOC progresses. This learning design can contribute to better learning experiences and outcomes for students, and be a valuable contribution to current research discussions on learning design in Massive Open Online Courses (MOOCs).}, language = {en} } @misc{ArandaSchoelzelMendezetal.2018, author = {Aranda, Juan and Sch{\"o}lzel, Mario and Mendez, Diego and Carrillo, Henry}, title = {An energy consumption model for multiModal wireless sensor networks based on wake-up radio receivers}, series = {2018 IEEE Colombian Conference on Communications and Computing (COLCOM)}, journal = {2018 IEEE Colombian Conference on Communications and Computing (COLCOM)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-6820-7}, doi = {10.1109/ColComCon.2018.8466728}, pages = {6}, year = {2018}, abstract = {Energy consumption is a major concern in Wireless Sensor Networks. A significant waste of energy occurs due to the idle listening and overhearing problems, which are typically avoided by turning off the radio, while no transmission is ongoing. The classical approach for allowing the reception of messages in such situations is to use a low-duty-cycle protocol, and to turn on the radio periodically, which reduces the idle listening problem, but requires timers and usually unnecessary wakeups. A better solution is to turn on the radio only on demand by using a Wake-up Radio Receiver (WuRx). In this paper, an energy model is presented to estimate the energy saving in various multi-hop network topologies under several use cases, when a WuRx is used instead of a classical low-duty-cycling protocol. The presented model also allows for estimating the benefit of various WuRx properties like using addressing or not.}, language = {en} } @article{ConciaDistlerLawetal.2023, author = {Concia, Francesca and Distler, Petr and Law, Gareth and Macerata, Elena and Mariani, Mario and Mossini, Eros and Negrin, Maddalena and Štrok, Marko}, title = {An experience in developing models to use MOOCs in teaching and to advocate OERs}, series = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, journal = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, editor = {Meinel, Christoph and Schweiger, Stefanie and Staubitz, Thomas and Conrad, Robert and Alario Hoyos, Carlos and Ebner, Martin and Sancassani, Susanna and Żur, Agnieszka and Friedl, Christian and Halawa, Sherif and Gamage, Dilrukshi and Scott, Jeffrey and Kristine Jonson Carlon, May and Deville, Yves and Gaebel, Michael and Delgado Kloos, Carlos and von Schmieden, Karen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-62460}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-624609}, pages = {239 -- 254}, year = {2023}, abstract = {Loss of expertise in the fields of Nuclear- and Radio-Chemistry (NRC) is problematic at a scientific and social level. This has been addressed by developing a MOOC, in order to let students in scientific matters discover all the benefits of NRC to society and improving their awareness of this discipline. The MOOC "Essential Radiochemistry for Society" includes current societal challenges related to health, clean and sustainable energy for safety and quality of food and agriculture. NRC teachers belonging to CINCH network were invited to use the MOOC in their teaching, according to various usage models: on the basis of these different experiences, some usage patterns were designed, describing context characteristics (number and age of students, course), activities' scheduling and organization, results and students' feedback, with the aim of encouraging the use of MOOCs in university teaching, as an opportunity for both lecturers and students. These models were the basis of a "toolkit for teachers". By experiencing digital teaching resources created by different lecturers, CINCH teachers took a first meaningful step towards understanding the worth of Open Educational Resources (OER) and the importance of their creation, adoption and sharing for knowledge progress. In this paper, the entire path from MOOC concept to MOOC different usage models, to awareness-raising regarding OER is traced in conceptual stages.}, language = {en} } @book{BaltzerHradilakPfennigschmidtetal.2021, author = {Baltzer, Wanda and Hradilak, Theresa and Pfennigschmidt, Lara and Prestin, Luc Maurice and Spranger, Moritz and Stadlinger, Simon and Wendt, Leo and Lincke, Jens and Rein, Patrick and Church, Luke and Hirschfeld, Robert}, title = {An individual-centered approach to visualize people's opinions and demographic information}, number = {136}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-504-0}, issn = {1613-5652}, doi = {10.25932/publishup-49145}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-491457}, publisher = {Universit{\"a}t Potsdam}, pages = {326}, year = {2021}, abstract = {The noble way to substantiate decisions that affect many people is to ask these people for their opinions. For governments that run whole countries, this means asking all citizens for their views to consider their situations and needs. Organizations such as Africa's Voices Foundation, who want to facilitate communication between decision-makers and citizens of a country, have difficulty mediating between these groups. To enable understanding, statements need to be summarized and visualized. Accomplishing these goals in a way that does justice to the citizens' voices and situations proves challenging. Standard charts do not help this cause as they fail to create empathy for the people behind their graphical abstractions. Furthermore, these charts do not create trust in the data they are representing as there is no way to see or navigate back to the underlying code and the original data. To fulfill these functions, visualizations would highly benefit from interactions to explore the displayed data, which standard charts often only limitedly provide. To help improve the understanding of people's voices, we developed and categorized 80 ideas for new visualizations, new interactions, and better connections between different charts, which we present in this report. From those ideas, we implemented 10 prototypes and two systems that integrate different visualizations. We show that this integration allows consistent appearance and behavior of visualizations. The visualizations all share the same main concept: representing each individual with a single dot. To realize this idea, we discuss technologies that efficiently allow the rendering of a large number of these dots. With these visualizations, direct interactions with representations of individuals are achievable by clicking on them or by dragging a selection around them. This direct interaction is only possible with a bidirectional connection from the visualization to the data it displays. We discuss different strategies for bidirectional mappings and the trade-offs involved. Having unified behavior across visualizations enhances exploration. For our prototypes, that includes grouping, filtering, highlighting, and coloring of dots. Our prototyping work was enabled by the development environment Lively4. We explain which parts of Lively4 facilitated our prototyping process. Finally, we evaluate our approach to domain problems and our developed visualization concepts. Our work provides inspiration and a starting point for visualization development in this domain. Our visualizations can improve communication between citizens and their government and motivate empathetic decisions. Our approach, combining low-level entities to create visualizations, provides value to an explorative and empathetic workflow. We show that the design space for visualizing this kind of data has a lot of potential and that it is possible to combine qualitative and quantitative approaches to data analysis.}, language = {en} } @misc{PatalasMaliszewskaKrebs2018, author = {Patalas-Maliszewska, Justyna and Krebs, Irene}, title = {An Information System Supporting the Eliciting of Expert Knowledge for Successful IT Projects}, series = {Information and Software Technologies, ICIST 2018}, volume = {920}, journal = {Information and Software Technologies, ICIST 2018}, publisher = {Springer}, address = {Berlin}, isbn = {978-3-319-99972-2}, issn = {1865-0929}, doi = {10.1007/978-3-319-99972-2_1}, pages = {3 -- 13}, year = {2018}, abstract = {In order to guarantee the success of an IT project, it is necessary for a company to possess expert knowledge. The difficulty arises when experts no longer work for the company and it then becomes necessary to use their knowledge, in order to realise an IT project. In this paper, the ExKnowIT information system which supports the eliciting of expert knowledge for successful IT projects, is presented and consists of the following modules: (1) the identification of experts for successful IT projects, (2) the eliciting of expert knowledge on completed IT projects, (3) the expert knowledge base on completed IT projects, (4) the Group Method for Data Handling (GMDH) algorithm, (5) new knowledge in support of decisions regarding the selection of a manager for a new IT project. The added value of our system is that these three approaches, namely, the elicitation of expert knowledge, the success of an IT project and the discovery of new knowledge, gleaned from the expert knowledge base, otherwise known as the decision model, complement each other.}, language = {en} } @article{KunftKatsifodimosSchelteretal.2019, author = {Kunft, Andreas and Katsifodimos, Asterios and Schelter, Sebastian and Bress, Sebastian and Rabl, Tilmann and Markl, Volker}, title = {An Intermediate Representation for Optimizing Machine Learning Pipelines}, series = {Proceedings of the VLDB Endowment}, volume = {12}, journal = {Proceedings of the VLDB Endowment}, number = {11}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {2150-8097}, doi = {10.14778/3342263.3342633}, pages = {1553 -- 1567}, year = {2019}, abstract = {Machine learning (ML) pipelines for model training and validation typically include preprocessing, such as data cleaning and feature engineering, prior to training an ML model. Preprocessing combines relational algebra and user-defined functions (UDFs), while model training uses iterations and linear algebra. Current systems are tailored to either of the two. As a consequence, preprocessing and ML steps are optimized in isolation. To enable holistic optimization of ML training pipelines, we present Lara, a declarative domain-specific language for collections and matrices. Lara's inter-mediate representation (IR) reflects on the complete program, i.e., UDFs, control flow, and both data types. Two views on the IR enable diverse optimizations. Monads enable operator pushdown and fusion across type and loop boundaries. Combinators provide the semantics of domain-specific operators and optimize data access and cross-validation of ML algorithms. Our experiments on preprocessing pipelines and selected ML algorithms show the effects of our proposed optimizations on dense and sparse data, which achieve speedups of up to an order of magnitude.}, language = {en} } @phdthesis{Wolf2021, author = {Wolf, Johannes}, title = {Analysis and visualization of transport infrastructure based on large-scale geospatial mobile mapping data}, doi = {10.25932/publishup-53612}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-536129}, school = {Universit{\"a}t Potsdam}, pages = {vi, 121}, year = {2021}, abstract = {3D point clouds are a universal and discrete digital representation of three-dimensional objects and environments. For geospatial applications, 3D point clouds have become a fundamental type of raw data acquired and generated using various methods and techniques. In particular, 3D point clouds serve as raw data for creating digital twins of the built environment. This thesis concentrates on the research and development of concepts, methods, and techniques for preprocessing, semantically enriching, analyzing, and visualizing 3D point clouds for applications around transport infrastructure. It introduces a collection of preprocessing techniques that aim to harmonize raw 3D point cloud data, such as point density reduction and scan profile detection. Metrics such as, e.g., local density, verticality, and planarity are calculated for later use. One of the key contributions tackles the problem of analyzing and deriving semantic information in 3D point clouds. Three different approaches are investigated: a geometric analysis, a machine learning approach operating on synthetically generated 2D images, and a machine learning approach operating on 3D point clouds without intermediate representation. In the first application case, 2D image classification is applied and evaluated for mobile mapping data focusing on road networks to derive road marking vector data. The second application case investigates how 3D point clouds can be merged with ground-penetrating radar data for a combined visualization and to automatically identify atypical areas in the data. For example, the approach detects pavement regions with developing potholes. The third application case explores the combination of a 3D environment based on 3D point clouds with panoramic imagery to improve visual representation and the detection of 3D objects such as traffic signs. The presented methods were implemented and tested based on software frameworks for 3D point clouds and 3D visualization. In particular, modules for metric computation, classification procedures, and visualization techniques were integrated into a modular pipeline-based C++ research framework for geospatial data processing, extended by Python machine learning scripts. All visualization and analysis techniques scale to large real-world datasets such as road networks of entire cities or railroad networks. The thesis shows that some use cases allow taking advantage of established image vision methods to analyze images rendered from mobile mapping data efficiently. The two presented semantic classification methods working directly on 3D point clouds are use case independent and show similar overall accuracy when compared to each other. While the geometry-based method requires less computation time, the machine learning-based method supports arbitrary semantic classes but requires training the network with ground truth data. Both methods can be used in combination to gradually build this ground truth with manual corrections via a respective annotation tool. This thesis contributes results for IT system engineering of applications, systems, and services that require spatial digital twins of transport infrastructure such as road networks and railroad networks based on 3D point clouds as raw data. It demonstrates the feasibility of fully automated data flows that map captured 3D point clouds to semantically classified models. This provides a key component for seamlessly integrated spatial digital twins in IT solutions that require up-to-date, object-based, and semantically enriched information about the built environment.}, language = {en} } @phdthesis{Ussath2017, author = {Ussath, Martin Georg}, title = {Analytical approaches for advanced attacks}, school = {Universit{\"a}t Potsdam}, pages = {169}, year = {2017}, language = {en} } @article{BuschmannTrappDoellner2016, author = {Buschmann, Stefan and Trapp, Matthias and D{\"o}llner, J{\"u}rgen Roland Friedrich}, title = {Animated visualization of spatial-temporal trajectory data for air-traffic analysis}, series = {The Visual Computer}, volume = {32}, journal = {The Visual Computer}, publisher = {Springer}, address = {New York}, issn = {0178-2789}, doi = {10.1007/s00371-015-1185-9}, pages = {371 -- 381}, year = {2016}, abstract = {With increasing numbers of flights worldwide and a continuing rise in airport traffic, air-traffic management is faced with a number of challenges. These include monitoring, reporting, planning, and problem analysis of past and current air traffic, e.g., to identify hotspots, minimize delays, or to optimize sector assignments to air-traffic controllers. To cope with these challenges, cyber worlds can be used for interactive visual analysis and analytical reasoning based on aircraft trajectory data. However, with growing data size and complexity, visualization requires high computational efficiency to process that data within real-time constraints. This paper presents a technique for real-time animated visualization of massive trajectory data. It enables (1) interactive spatio-temporal filtering, (2) generic mapping of trajectory attributes to geometric representations and appearance, and (3) real-time rendering within 3D virtual environments such as virtual 3D airport or 3D city models. Different visualization metaphors can be efficiently built upon this technique such as temporal focus+context, density maps, or overview+detail methods. As a general-purpose visualization technique, it can be applied to general 3D and 3+1D trajectory data, e.g., traffic movement data, geo-referenced networks, or spatio-temporal data, and it supports related visual analytics and data mining tasks within cyber worlds.}, language = {en} } @misc{BinTareafBergerHennigetal.2018, author = {Bin Tareaf, Raad and Berger, Philipp and Hennig, Patrick and Meinel, Christoph}, title = {ASEDS}, series = {IEEE 20th International Conference on High Performance Computing and Communications; IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/SmartCity/DSS))}, journal = {IEEE 20th International Conference on High Performance Computing and Communications; IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/SmartCity/DSS))}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-6614-2}, doi = {10.1109/HPCC/SmartCity/DSS.2018.00143}, pages = {860 -- 866}, year = {2018}, abstract = {The Massive adoption of social media has provided new ways for individuals to express their opinion and emotion online. In 2016, Facebook introduced a new reactions feature that allows users to express their psychological emotions regarding published contents using so-called Facebook reactions. In this paper, a framework for predicting the distribution of Facebook post reactions is presented. For this purpose, we collected an enormous amount of Facebook posts associated with their reactions labels using the proposed scalable Facebook crawler. The training process utilizes 3 million labeled posts for more than 64,000 unique Facebook pages from diverse categories. The evaluation on standard benchmarks using the proposed features shows promising results compared to previous research. The final model is able to predict the reaction distribution on Facebook posts with a recall score of 0.90 for "Joy" emotion.}, language = {en} } @misc{UllrichEnkeTeichmannetal.2019, author = {Ullrich, Andre and Enke, Judith and Teichmann, Malte and Kress, Antonio and Gronau, Norbert}, title = {Audit - and then what?}, series = {Procedia Manufacturing}, volume = {31}, journal = {Procedia Manufacturing}, publisher = {Elsevier}, address = {Amsterdam}, issn = {2351-9789}, doi = {10.1016/j.promfg.2019.03.025}, pages = {162 -- 168}, year = {2019}, abstract = {Current trends such as digital transformation, Internet of Things, or Industry 4.0 are challenging the majority of learning factories. Regardless of whether a conventional learning factory, a model factory, or a digital learning factory, traditional approaches such as the monotonous execution of specific instructions don't suffice the learner's needs, market requirements as well as especially current technological developments. Contemporary teaching environments need a clear strategy, a road to follow for being able to successfully cope with the changes and develop towards digitized learning factories. This demand driven necessity of transformation leads to another obstacle: Assessing the status quo and developing and implementing adequate action plans. Within this paper, details of a maturity-based audit of the hybrid learning factory in the Research and Application Centre Industry 4.0 and a thereof derived roadmap for the digitization of a learning factory are presented.}, language = {en} } @article{SchlosserWaltherBoissieretal.2019, author = {Schlosser, Rainer and Walther, Carsten and Boissier, Martin and Uflacker, Matthias}, title = {Automated repricing and ordering strategies in competitive markets}, series = {AI communications : AICOM ; the European journal on artificial intelligence}, volume = {32}, journal = {AI communications : AICOM ; the European journal on artificial intelligence}, number = {1}, publisher = {IOS Press}, address = {Amsterdam}, issn = {0921-7126}, doi = {10.3233/AIC-180603}, pages = {15 -- 29}, year = {2019}, abstract = {Merchants on modern e-commerce platforms face a highly competitive environment. They compete against each other using automated dynamic pricing and ordering strategies. Successfully managing both inventory levels as well as offer prices is a challenging task as (i) demand is uncertain, (ii) competitors strategically interact, and (iii) optimized pricing and ordering decisions are mutually dependent. We show how to derive optimized data-driven pricing and ordering strategies which are based on demand learning techniques and efficient dynamic optimization models. We verify the superior performance of our self-adaptive strategies by comparing them to different rule-based as well as data-driven strategies in duopoly and oligopoly settings. Further, to study and to optimize joint dynamic ordering and pricing strategies on online marketplaces, we built an interactive simulation platform. To be both flexible and scalable, the platform has a microservice-based architecture and allows handling dozens of competing merchants and streams of consumers with configurable characteristics.}, language = {en} } @article{DyckGieseLambers2019, author = {Dyck, Johannes and Giese, Holger and Lambers, Leen}, title = {Automatic verification of behavior preservation at the transformation level for relational model transformation}, series = {Software and systems modeling}, volume = {18}, journal = {Software and systems modeling}, number = {5}, publisher = {Springer}, address = {Heidelberg}, issn = {1619-1366}, doi = {10.1007/s10270-018-00706-9}, pages = {2937 -- 2972}, year = {2019}, abstract = {The correctness of model transformations is a crucial element for model-driven engineering of high-quality software. In particular, behavior preservation is an important correctness property avoiding the introduction of semantic errors during the model-driven engineering process. Behavior preservation verification techniques show some kind of behavioral equivalence or refinement between source and target model of the transformation. Automatic tool support is available for verifying behavior preservation at the instance level, i.e., for a given source and target model specified by the model transformation. However, until now there is no sound and automatic verification approach available at the transformation level, i.e., for all source and target models. In this article, we extend our results presented in earlier work (Giese and Lambers, in: Ehrig et al (eds) Graph transformations, Springer, Berlin, 2012) and outline a new transformation-level approach for the sound and automatic verification of behavior preservation captured by bisimulation resp.simulation for outplace model transformations specified by triple graph grammars and semantic definitions given by graph transformation rules. In particular, we first show how behavior preservation can be modeled in a symbolic manner at the transformation level and then describe that transformation-level verification of behavior preservation can be reduced to invariant checking of suitable conditions for graph transformations. We demonstrate that the resulting checking problem can be addressed by our own invariant checker for an example of a transformation between sequence charts and communicating automata.}, language = {en} } @misc{GawronChengMeinel2018, author = {Gawron, Marian and Cheng, Feng and Meinel, Christoph}, title = {Automatic vulnerability classification using machine learning}, series = {Risks and Security of Internet and Systems}, journal = {Risks and Security of Internet and Systems}, publisher = {Springer}, address = {Cham}, isbn = {978-3-319-76687-4}, issn = {0302-9743}, doi = {10.1007/978-3-319-76687-4_1}, pages = {3 -- 17}, year = {2018}, abstract = {The classification of vulnerabilities is a fundamental step to derive formal attributes that allow a deeper analysis. Therefore, it is required that this classification has to be performed timely and accurate. Since the current situation demands a manual interaction in the classification process, the timely processing becomes a serious issue. Thus, we propose an automated alternative to the manual classification, because the amount of identified vulnerabilities per day cannot be processed manually anymore. We implemented two different approaches that are able to automatically classify vulnerabilities based on the vulnerability description. We evaluated our approaches, which use Neural Networks and the Naive Bayes methods respectively, on the base of publicly known vulnerabilities.}, language = {en} } @article{PufahlWeske2019, author = {Pufahl, Luise and Weske, Mathias}, title = {Batch activity: enhancing business process modeling and enactment with batch processing}, series = {Computing}, volume = {101}, journal = {Computing}, number = {12}, publisher = {Springer}, address = {Wien}, issn = {0010-485X}, doi = {10.1007/s00607-019-00717-4}, pages = {1909 -- 1933}, year = {2019}, abstract = {Organizations strive for efficiency in their business processes by process improvement and automation. Business process management (BPM) supports these efforts by capturing business processes in process models serving as blueprint for a number of process instances. In BPM, process instances are typically considered running independently of each other. However, batch processing-the collectively execution of several instances at specific process activities-is a common phenomenon in operational processes to reduce cost or time. Currently, batch processing is organized manually or hard-coded in software. For allowing stakeholders to explicitly represent their batch configurations in process models and their automatic execution, this paper provides a concept for batch activities and describes the corresponding execution semantics. The batch activity concept is evaluated in a two-step approach: a prototypical implementation in an existing BPM System proves its feasibility. Additionally, batch activities are applied to different use cases in a simulated environment. Its application implies cost-savings when a suitable batch configuration is selected. The batch activity concept contributes to practice by allowing the specification of batch work in process models and their automatic execution, and to research by extending the existing process modeling concepts.}, language = {en} } @misc{RepkeKrestelEddingetal.2018, author = {Repke, Tim and Krestel, Ralf and Edding, Jakob and Hartmann, Moritz and Hering, Jonas and Kipping, Dennis and Schmidt, Hendrik and Scordialo, Nico and Zenner, Alexander}, title = {Beacon in the Dark}, series = {Proceedings of the 27th ACM International Conference on Information and Knowledge Management}, journal = {Proceedings of the 27th ACM International Conference on Information and Knowledge Management}, publisher = {Association for Computing Machinery}, address = {New York}, isbn = {978-1-4503-6014-2}, doi = {10.1145/3269206.3269231}, pages = {1871 -- 1874}, year = {2018}, abstract = {The large amount of heterogeneous data in these email corpora renders experts' investigations by hand infeasible. Auditors or journalists, e.g., who are looking for irregular or inappropriate content or suspicious patterns, are in desperate need for computer-aided exploration tools to support their investigations. We present our Beacon system for the exploration of such corpora at different levels of detail. A distributed processing pipeline combines text mining methods and social network analysis to augment the already semi-structured nature of emails. The user interface ties into the resulting cleaned and enriched dataset. For the interface design we identify three objectives expert users have: gain an initial overview of the data to identify leads to investigate, understand the context of the information at hand, and have meaningful filters to iteratively focus onto a subset of emails. To this end we make use of interactive visualisations based on rearranged and aggregated extracted information to reveal salient patterns.}, language = {en} } @phdthesis{Meinig2019, author = {Meinig, Michael}, title = {Bedrohungsanalyse f{\"u}r milit{\"a}rische Informationstechnik}, doi = {10.25932/publishup-44160}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-441608}, school = {Universit{\"a}t Potsdam}, pages = {X, 137}, year = {2019}, abstract = {Risiken f{\"u}r Cyberressourcen k{\"o}nnen durch unbeabsichtigte oder absichtliche Bedrohungen entstehen. Dazu geh{\"o}ren Insider-Bedrohungen von unzufriedenen oder nachl{\"a}ssigen Mitarbeitern und Partnern, eskalierende und aufkommende Bedrohungen aus aller Welt, die stetige Weiterentwicklung der Angriffstechnologien und die Entstehung neuer und zerst{\"o}rerischer Angriffe. Informationstechnik spielt mittlerweile in allen Bereichen des Lebens eine entscheidende Rolle, u. a. auch im Bereich des Milit{\"a}rs. Ein ineffektiver Schutz von Cyberressourcen kann hier Sicherheitsvorf{\"a}lle und Cyberattacken erleichtern, welche die kritischen Vorg{\"a}nge st{\"o}ren, zu unangemessenem Zugriff, Offenlegung, {\"A}nderung oder Zerst{\"o}rung sensibler Informationen f{\"u}hren und somit die nationale Sicherheit, das wirtschaftliche Wohlergehen sowie die {\"o}ffentliche Gesundheit und Sicherheit gef{\"a}hrden. Oftmals ist allerdings nicht klar, welche Bedrohungen konkret vorhanden sind und welche der kritischen Systemressourcen besonders gef{\"a}hrdet ist. In dieser Dissertation werden verschiedene Analyseverfahren f{\"u}r Bedrohungen in milit{\"a}rischer Informationstechnik vorgeschlagen und in realen Umgebungen getestet. Dies bezieht sich auf Infrastrukturen, IT-Systeme, Netze und Anwendungen, welche Verschlusssachen (VS)/Staatsgeheimnisse verarbeiten, wie zum Beispiel bei milit{\"a}rischen oder Regierungsorganisationen. Die Besonderheit an diesen Organisationen ist das Konzept der Informationsr{\"a}ume, in denen verschiedene Datenelemente, wie z. B. Papierdokumente und Computerdateien, entsprechend ihrer Sicherheitsempfindlichkeit eingestuft werden, z. B. „STRENG GEHEIM", „GEHEIM", „VS-VERTRAULICH", „VS-NUR-F{\"U}R-DEN-DIENSTGEBRAUCH" oder „OFFEN". Die Besonderheit dieser Arbeit ist der Zugang zu eingestuften Informationen aus verschiedenen Informationsr{\"a}umen und der Prozess der Freigabe dieser. Jede in der Arbeit entstandene Ver{\"o}ffentlichung wurde mit Angeh{\"o}rigen in der Organisation besprochen, gegengelesen und freigegeben, so dass keine eingestuften Informationen an die {\"O}ffentlichkeit gelangen. Die Dissertation beschreibt zun{\"a}chst Bedrohungsklassifikationsschemen und Angreiferstrategien, um daraus ein ganzheitliches, strategiebasiertes Bedrohungsmodell f{\"u}r Organisationen abzuleiten. Im weiteren Verlauf wird die Erstellung und Analyse eines Sicherheitsdatenflussdiagramms definiert, welches genutzt wird, um in eingestuften Informationsr{\"a}umen operationelle Netzknoten zu identifizieren, die aufgrund der Bedrohungen besonders gef{\"a}hrdet sind. Die spezielle, neuartige Darstellung erm{\"o}glicht es, erlaubte und verbotene Informationsfl{\"u}sse innerhalb und zwischen diesen Informationsr{\"a}umen zu verstehen. Aufbauend auf der Bedrohungsanalyse werden im weiteren Verlauf die Nachrichtenfl{\"u}sse der operationellen Netzknoten auf Verst{\"o}ße gegen Sicherheitsrichtlinien analysiert und die Ergebnisse mit Hilfe des Sicherheitsdatenflussdiagramms anonymisiert dargestellt. Durch Anonymisierung der Sicherheitsdatenflussdiagramme ist ein Austausch mit externen Experten zur Diskussion von Sicherheitsproblematiken m{\"o}glich. Der dritte Teil der Arbeit zeigt, wie umfangreiche Protokolldaten der Nachrichtenfl{\"u}sse dahingehend untersucht werden k{\"o}nnen, ob eine Reduzierung der Menge an Daten m{\"o}glich ist. Dazu wird die Theorie der groben Mengen aus der Unsicherheitstheorie genutzt. Dieser Ansatz wird in einer Fallstudie, auch unter Ber{\"u}cksichtigung von m{\"o}glichen auftretenden Anomalien getestet und ermittelt, welche Attribute in Protokolldaten am ehesten redundant sind.}, language = {de} } @article{ŞahinEgloffsteinBotheetal.2021, author = {Şahin, Muhittin and Egloffstein, Marc and Bothe, Max and Rohloff, Tobias and Schenk, Nathanael and Schwerer, Florian and Ifenthaler, Dirk}, title = {Behavioral Patterns in Enterprise MOOCs at openSAP}, series = {EMOOCs 2021}, volume = {2021}, journal = {EMOOCs 2021}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51735}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-517350}, pages = {281 -- 288}, year = {2021}, language = {en} } @misc{MatthiesTeusnerHesse2018, author = {Matthies, Christoph and Teusner, Ralf and Hesse, G{\"u}nter}, title = {Beyond Surveys}, series = {2018 IEEE Frontiers in Education (FIE) Conference}, journal = {2018 IEEE Frontiers in Education (FIE) Conference}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-1174-6}, issn = {0190-5848}, pages = {9}, year = {2018}, language = {en} } @book{MeinelGayvoronskayaSchnjakin2018, author = {Meinel, Christoph and Gayvoronskaya, Tatiana and Schnjakin, Maxim}, title = {Blockchain}, number = {124}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-441-8}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-414525}, publisher = {Universit{\"a}t Potsdam}, pages = {102}, year = {2018}, abstract = {The term blockchain has recently become a buzzword, but only few know what exactly lies behind this approach. According to a survey, issued in the first quarter of 2017, the term is only known by 35 percent of German medium-sized enterprise representatives. However, the blockchain technology is very interesting for the mass media because of its rapid development and global capturing of different markets. For example, many see blockchain technology either as an all-purpose weapon— which only a few have access to—or as a hacker technology for secret deals in the darknet. The innovation of blockchain technology is found in its successful combination of already existing approaches: such as decentralized networks, cryptography, and consensus models. This innovative concept makes it possible to exchange values in a decentralized system. At the same time, there is no requirement for trust between its nodes (e.g. users). With this study the Hasso Plattner Institute would like to help readers form their own opinion about blockchain technology, and to distinguish between truly innovative properties and hype. The authors of the present study analyze the positive and negative properties of the blockchain architecture and suggest possible solutions, which can contribute to the efficient use of the technology. We recommend that every company define a clear target for the intended application, which is achievable with a reasonable cost-benefit ration, before deciding on this technology. Both the possibilities and the limitations of blockchain technology need to be considered. The relevant steps that must be taken in this respect are summarized /summed up for the reader in this study. Furthermore, this study elaborates on urgent problems such as the scalability of the blockchain, appropriate consensus algorithm and security, including various types of possible attacks and their countermeasures. New blockchains, for example, run the risk of reducing security, as changes to existing technology can lead to lacks in the security and failures. After discussing the innovative properties and problems of the blockchain technology, its implementation is discussed. There are a lot of implementation opportunities for companies available who are interested in the blockchain realization. The numerous applications have either their own blockchain as a basis or use existing and widespread blockchain systems. Various consortia and projects offer "blockchain-as-a-service{\"a}nd help other companies to develop, test and deploy their own applications. This study gives a detailed overview of diverse relevant applications and projects in the field of blockchain technology. As this technology is still a relatively young and fast developing approach, it still lacks uniform standards to allow the cooperation of different systems and to which all developers can adhere. Currently, developers are orienting themselves to Bitcoin, Ethereum and Hyperledger systems, which serve as the basis for many other blockchain applications. The goal is to give readers a clear and comprehensive overview of blockchain technology and its capabilities.}, language = {en} } @article{RichlySchlosserBoissier2022, author = {Richly, Keven and Schlosser, Rainer and Boissier, Martin}, title = {Budget-conscious fine-grained configuration optimization for spatio-temporal applications}, series = {Proceedings of the VLDB Endowment}, volume = {15}, journal = {Proceedings of the VLDB Endowment}, number = {13}, publisher = {Association for Computing Machinery (ACM)}, address = {[New York]}, issn = {2150-8097}, doi = {10.14778/3565838.3565858}, pages = {4079 -- 4092}, year = {2022}, abstract = {Based on the performance requirements of modern spatio-temporal data mining applications, in-memory database systems are often used to store and process the data. To efficiently utilize the scarce DRAM capacities, modern database systems support various tuning possibilities to reduce the memory footprint (e.g., data compression) or increase performance (e.g., additional indexes). However, the selection of cost and performance balancing configurations is challenging due to the vast number of possible setups consisting of mutually dependent individual decisions. In this paper, we introduce a novel approach to jointly optimize the compression, sorting, indexing, and tiering configuration for spatio-temporal workloads. Further, we consider horizontal data partitioning, which enables the independent application of different tuning options on a fine-grained level. We propose different linear programming (LP) models addressing cost dependencies at different levels of accuracy to compute optimized tuning configurations for a given workload and memory budgets. To yield maintainable and robust configurations, we extend our LP-based approach to incorporate reconfiguration costs as well as a worst-case optimization for potential workload scenarios. Further, we demonstrate on a real-world dataset that our models allow to significantly reduce the memory footprint with equal performance or increase the performance with equal memory size compared to existing tuning heuristics.}, language = {en} } @article{MoeringdeMutiis2019, author = {M{\"o}ring, Sebastian and de Mutiis, Marco}, title = {Camera Ludica}, series = {Intermedia games - Games inter media : Video games and intermediality}, journal = {Intermedia games - Games inter media : Video games and intermediality}, publisher = {Bloomsbury academic}, address = {New York}, isbn = {978-1-5013-3051-3}, pages = {69 -- 93}, year = {2019}, language = {en} } @misc{BrinkmannHeine2019, author = {Brinkmann, Maik and Heine, Moreen}, title = {Can Blockchain Leverage for New Public Governance?}, series = {Proceedings of the 12th International Conference on Theory and Practice of Electronic Governance}, journal = {Proceedings of the 12th International Conference on Theory and Practice of Electronic Governance}, publisher = {Association for Computing Machinery}, address = {New York}, isbn = {978-1-4503-6644-1}, doi = {10.1145/3326365.3326409}, pages = {338 -- 341}, year = {2019}, abstract = {New Public Governance (NPG) as a paradigm for collaborative forms of public service delivery and Blockchain governance are trending topics for researchers and practitioners alike. Thus far, each topic has, on the whole, been discussed separately. This paper presents the preliminary results of ongoing research which aims to shed light on the more concrete benefits of Blockchain for the purpose of NPG. For the first time, a conceptual analysis is conducted on process level to spot benefits and limitations of Blockchain-based governance. Per process element, Blockchain key characteristics are mapped to functional aspects of NPG from a governance perspective. The preliminary results show that Blockchain offers valuable support for governments seeking methods to effectively coordinate co-producing networks. However, the extent of benefits of Blockchain varies across the process elements. It becomes evident that there is a need for off-chain processes. It is, therefore, argued in favour of intensifying research on off-chain governance processes to better understand the implications for and influences on on-chain governance.}, language = {en} } @article{NeuboeckLinschinger2023, author = {Neub{\"o}ck, Kristina and Linschinger, Nadine}, title = {Central elements of knowledge and competence development with MOOCs}, series = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, journal = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, editor = {Meinel, Christoph and Schweiger, Stefanie and Staubitz, Thomas and Conrad, Robert and Alario Hoyos, Carlos and Ebner, Martin and Sancassani, Susanna and Żur, Agnieszka and Friedl, Christian and Halawa, Sherif and Gamage, Dilrukshi and Scott, Jeffrey and Kristine Jonson Carlon, May and Deville, Yves and Gaebel, Michael and Delgado Kloos, Carlos and von Schmieden, Karen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-62466}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-624668}, pages = {255 -- 262}, year = {2023}, abstract = {To implement OERs at HEIs sustainably, not just technical infrastructure is required, but also well-trained staff. The University of Graz is in charge of an OER training program for university staff as part of the collaborative project Open Education Austria Advanced (OEAA) with the aim of ensuring long-term competence growth in the use and creation of OERs. The program consists of a MOOC and a guided blended learning format that was evaluated to find out which accompanying teaching and learning concepts can best facilitate targeted competence development. The evaluation of the program shows that learning videos, self-study assignments and synchronous sessions are most useful for the learning process. The results indicate that the creation of OERs is a complex process that can be undergone more effectively in the guided program.}, language = {en} } @article{LorenzBockSchulteOstermann2023, author = {Lorenz, Anja and Bock, Stefanie and Schulte-Ostermann, Juleka}, title = {Challenges and proposals for introducing digital certificates in higher education infrastructures}, series = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, journal = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, editor = {Meinel, Christoph and Schweiger, Stefanie and Staubitz, Thomas and Conrad, Robert and Alario Hoyos, Carlos and Ebner, Martin and Sancassani, Susanna and Żur, Agnieszka and Friedl, Christian and Halawa, Sherif and Gamage, Dilrukshi and Scott, Jeffrey and Kristine Jonson Carlon, May and Deville, Yves and Gaebel, Michael and Delgado Kloos, Carlos and von Schmieden, Karen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-62470}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-624701}, pages = {263 -- 270}, year = {2023}, abstract = {Questions about the recognition of MOOCs within and outside higher education were already being raised in the early 2010s. Today, recognition decisions are still made more or less on a case-by-case basis. However, digital certification approaches are now emerging that could automate recognition processes. The technical development of the required machinereadable documents and infrastructures is already well advanced in some cases. The DigiCerts consortium has developed a solution based on a collective blockchain. There are ongoing and open discussions regarding the particular technology, but the institutional implementation of digital certificates raises further questions. A number of workshops have been held at the Institute for Interactive Systems at Technische Hochschule L{\"u}beck, which have identified the need for new responsibilities for issuing certificates. It has also become clear that all members of higher education institutions need to develop skills in the use of digital certificates.}, language = {en} } @article{SchlosserChenavazDimitrov2021, author = {Schlosser, Rainer and Chenavaz, R{\´e}gis Y. and Dimitrov, Stanko}, title = {Circular economy}, series = {International journal of production economics}, volume = {236}, journal = {International journal of production economics}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0925-5273}, doi = {10.1016/j.ijpe.2021.108117}, pages = {13}, year = {2021}, abstract = {In a circular economy, the use of recycled resources in production is a key performance indicator for management. Yet, academic studies are still unable to inform managers on appropriate recycling and pricing policies. We develop an optimal control model integrating a firm's recycling rate, which can use both virgin and recycled resources in the production process. Our model accounts for recycling influence both at the supply- and demandsides. The positive effect of a firm's use of recycled resources diminishes over time but may increase through investments. Using general formulations for demand and cost, we analytically examine joint dynamic pricing and recycling investment policies in order to determine their optimal interplay over time. We provide numerical experiments to assess the existence of a steady-state and to calculate sensitivity analyses with respect to various model parameters. The analysis shows how to dynamically adapt jointly optimized controls to reach sustainability in the production process. Our results pave the way to sounder sustainable practices for firms operating within a circular economy.}, language = {en} } @phdthesis{AlhosseiniAlmodarresiYasin2024, author = {Alhosseini Almodarresi Yasin, Seyed Ali}, title = {Classification, prediction and evaluation of graph neural networks on online social media platforms}, doi = {10.25932/publishup-62642}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-626421}, school = {Universit{\"a}t Potsdam}, pages = {xviii, 78}, year = {2024}, abstract = {The vast amount of data generated on social media platforms have made them a valuable source of information for businesses, governments and researchers. Social media data can provide insights into user behavior, preferences, and opinions. In this work, we address two important challenges in social media analytics. Predicting user engagement with online content has become a critical task for content creators to increase user engagement and reach larger audiences. Traditional user engagement prediction approaches rely solely on features derived from the user and content. However, a new class of deep learning methods based on graphs captures not only the content features but also the graph structure of social media networks. This thesis proposes a novel Graph Neural Network (GNN) approach to predict user interaction with tweets. The proposed approach combines the features of users, tweets and their engagement graphs. The tweet text features are extracted using pre-trained embeddings from language models, and a GNN layer is used to embed the user in a vector space. The GNN model then combines the features and graph structure to predict user engagement. The proposed approach achieves an accuracy value of 94.22\% in classifying user interactions, including likes, retweets, replies, and quotes. Another major challenge in social media analysis is detecting and classifying social bot accounts. Social bots are automated accounts used to manipulate public opinion by spreading misinformation or generating fake interactions. Detecting social bots is critical to prevent their negative impact on public opinion and trust in social media. In this thesis, we classify social bots on Twitter by applying Graph Neural Networks. The proposed approach uses a combination of both the features of a node and an aggregation of the features of a node's neighborhood to classify social bot accounts. Our final results indicate a 6\% improvement in the area under the curve score in the final predictions through the utilization of GNN. Overall, our work highlights the importance of social media data and the potential of new methods such as GNNs to predict user engagement and detect social bots. These methods have important implications for improving the quality and reliability of information on social media platforms and mitigating the negative impact of social bots on public opinion and discourse.}, language = {en} } @article{TopaliChountaOrtegaArranzetal.2021, author = {Topali, Paraskevi and Chounta, Irene-Angelica and Ortega-Arranz, Alejandro and Villagr{\´a}-Sobrino, Sara L. and Mart{\´i}nez-Mon{\´e}s, Alejandra}, title = {CoFeeMOOC-v.2}, series = {EMOOCs 2021}, volume = {2021}, journal = {EMOOCs 2021}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51724}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-517241}, pages = {209 -- 217}, year = {2021}, abstract = {Providing adequate support to MOOC participants is often a challenging task due to massiveness of the learners' population and the asynchronous communication among peers and MOOC practitioners. This workshop aims at discussing common learners' problems reported in the literature and reflect on designing adequate feedback interventions with the use of learning data. Our aim is three-fold: a) to pinpoint MOOC aspects that impact the planning of feedback, b) to explore the use of learning data in designing feedback strategies, and c) to propose design guidelines for developing and delivering scaffolding interventions for personalized feedback in MOOCs. To do so, we will carry out hands-on activities that aim to involve participants in interpreting learning data and using them to design adaptive feedback. This workshop appeals to researchers, practitioners and MOOC stakeholders who aim to providing contextualized scaffolding. We envision that this workshop will provide insights for bridging the gap between pedagogical theory and practice when it comes to feedback interventions in MOOCs.}, language = {en} } @misc{StaubitzMeinel2018, author = {Staubitz, Thomas and Meinel, Christoph}, title = {Collaborative Learning in MOOCs - Approaches and Experiments}, series = {2018 IEEE Frontiers in Education (FIE) Conference}, journal = {2018 IEEE Frontiers in Education (FIE) Conference}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-1174-6}, issn = {0190-5848}, pages = {9}, year = {2018}, abstract = {This Research-to-Practice paper examines the practical application of various forms of collaborative learning in MOOCs. Since 2012, about 60 MOOCs in the wider context of Information Technology and Computer Science have been conducted on our self-developed MOOC platform. The platform is also used by several customers, who either run their own platform instances or use our white label platform. We, as well as some of our partners, have experimented with different approaches in collaborative learning in these courses. Based on the results of early experiments, surveys amongst our participants, and requests by our business partners we have integrated several options to offer forms of collaborative learning to the system. The results of our experiments are directly fed back to the platform development, allowing to fine tune existing and to add new tools where necessary. In the paper at hand, we discuss the benefits and disadvantages of decisions in the design of a MOOC with regard to the various forms of collaborative learning. While the focus of the paper at hand is on forms of large group collaboration, two types of small group collaboration on our platforms are briefly introduced.}, language = {en} } @phdthesis{Quinzan2023, author = {Quinzan, Francesco}, title = {Combinatorial problems and scalability in artificial intelligence}, doi = {10.25932/publishup-61111}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-611114}, school = {Universit{\"a}t Potsdam}, pages = {xi, 141}, year = {2023}, abstract = {Modern datasets often exhibit diverse, feature-rich, unstructured data, and they are massive in size. This is the case of social networks, human genome, and e-commerce databases. As Artificial Intelligence (AI) systems are increasingly used to detect pattern in data and predict future outcome, there are growing concerns on their ability to process large amounts of data. Motivated by these concerns, we study the problem of designing AI systems that are scalable to very large and heterogeneous data-sets. Many AI systems require to solve combinatorial optimization problems in their course of action. These optimization problems are typically NP-hard, and they may exhibit additional side constraints. However, the underlying objective functions often exhibit additional properties. These properties can be exploited to design suitable optimization algorithms. One of these properties is the well-studied notion of submodularity, which captures diminishing returns. Submodularity is often found in real-world applications. Furthermore, many relevant applications exhibit generalizations of this property. In this thesis, we propose new scalable optimization algorithms for combinatorial problems with diminishing returns. Specifically, we focus on three problems, the Maximum Entropy Sampling problem, Video Summarization, and Feature Selection. For each problem, we propose new algorithms that work at scale. These algorithms are based on a variety of techniques, such as forward step-wise selection and adaptive sampling. Our proposed algorithms yield strong approximation guarantees, and the perform well experimentally. We first study the Maximum Entropy Sampling problem. This problem consists of selecting a subset of random variables from a larger set, that maximize the entropy. By using diminishing return properties, we develop a simple forward step-wise selection optimization algorithm for this problem. Then, we study the problem of selecting a subset of frames, that represent a given video. Again, this problem corresponds to a submodular maximization problem. We provide a new adaptive sampling algorithm for this problem, suitable to handle the complex side constraints imposed by the application. We conclude by studying Feature Selection. In this case, the underlying objective functions generalize the notion of submodularity. We provide a new adaptive sequencing algorithm for this problem, based on the Orthogonal Matching Pursuit paradigm. Overall, we study practically relevant combinatorial problems, and we propose new algorithms to solve them. We demonstrate that these algorithms are suitable to handle massive datasets. However, our analysis is not problem-specific, and our results can be applied to other domains, if diminishing return properties hold. We hope that the flexibility of our framework inspires further research into scalability in AI.}, language = {en} } @article{CaselDreierFernauetal.2020, author = {Casel, Katrin and Dreier, Jan and Fernau, Henning and Gobbert, Moritz and Kuinke, Philipp and Villaamil, Fernando S{\´a}nchez and Schmid, Markus L. and van Leeuwen, Erik Jan}, title = {Complexity of independency and cliquy trees}, series = {Discrete applied mathematics}, volume = {272}, journal = {Discrete applied mathematics}, publisher = {Elsevier}, address = {Amsterdam [u.a.]}, issn = {0166-218X}, doi = {10.1016/j.dam.2018.08.011}, pages = {2 -- 15}, year = {2020}, abstract = {An independency (cliquy) tree of an n-vertex graph G is a spanning tree of G in which the set of leaves induces an independent set (clique). We study the problems of minimizing or maximizing the number of leaves of such trees, and fully characterize their parameterized complexity. We show that all four variants of deciding if an independency/cliquy tree with at least/most l leaves exists parameterized by l are either Para-NP- or W[1]-hard. We prove that minimizing the number of leaves of a cliquy tree parameterized by the number of internal vertices is Para-NP-hard too. However, we show that minimizing the number of leaves of an independency tree parameterized by the number k of internal vertices has an O*(4(k))-time algorithm and a 2k vertex kernel. Moreover, we prove that maximizing the number of leaves of an independency/cliquy tree parameterized by the number k of internal vertices both have an O*(18(k))-time algorithm and an O(k 2(k)) vertex kernel, but no polynomial kernel unless the polynomial hierarchy collapses to the third level. Finally, we present an O(3(n) . f(n))-time algorithm to find a spanning tree where the leaf set has a property that can be decided in f (n) time and has minimum or maximum size.}, language = {en} } @book{MaximovaSchneiderGiese2020, author = {Maximova, Maria and Schneider, Sven and Giese, Holger}, title = {Compositional analysis of probabilistic timed graph transformation systems}, number = {133}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-501-9}, issn = {1613-5652}, doi = {10.25932/publishup-49013}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-490131}, publisher = {Universit{\"a}t Potsdam}, pages = {53}, year = {2020}, abstract = {The analysis of behavioral models is of high importance for cyber-physical systems, as the systems often encompass complex behavior based on e.g. concurrent components with mutual exclusion or probabilistic failures on demand. The rule-based formalism of probabilistic timed graph transformation systems is a suitable choice when the models representing states of the system can be understood as graphs and timed and probabilistic behavior is important. However, model checking PTGTSs is limited to systems with rather small state spaces. We present an approach for the analysis of large scale systems modeled as probabilistic timed graph transformation systems by systematically decomposing their state spaces into manageable fragments. To obtain qualitative and quantitative analysis results for a large scale system, we verify that results obtained for its fragments serve as overapproximations for the corresponding results of the large scale system. Hence, our approach allows for the detection of violations of qualitative and quantitative safety properties for the large scale system under analysis. We consider a running example in which we model shuttles driving on tracks of a large scale topology and for which we verify that shuttles never collide and are unlikely to execute emergency brakes. In our evaluation, we apply an implementation of our approach to the running example.}, language = {en} } @article{Perscheid2021, author = {Perscheid, Cindy}, title = {Comprior}, series = {BMC Bioinformatics}, volume = {22}, journal = {BMC Bioinformatics}, publisher = {Springer Nature}, address = {London}, issn = {1471-2105}, doi = {10.1186/s12859-021-04308-z}, pages = {1 -- 15}, year = {2021}, abstract = {Background Reproducible benchmarking is important for assessing the effectiveness of novel feature selection approaches applied on gene expression data, especially for prior knowledge approaches that incorporate biological information from online knowledge bases. However, no full-fledged benchmarking system exists that is extensible, provides built-in feature selection approaches, and a comprehensive result assessment encompassing classification performance, robustness, and biological relevance. Moreover, the particular needs of prior knowledge feature selection approaches, i.e. uniform access to knowledge bases, are not addressed. As a consequence, prior knowledge approaches are not evaluated amongst each other, leaving open questions regarding their effectiveness. Results We present the Comprior benchmark tool, which facilitates the rapid development and effortless benchmarking of feature selection approaches, with a special focus on prior knowledge approaches. Comprior is extensible by custom approaches, offers built-in standard feature selection approaches, enables uniform access to multiple knowledge bases, and provides a customizable evaluation infrastructure to compare multiple feature selection approaches regarding their classification performance, robustness, runtime, and biological relevance. Conclusion Comprior allows reproducible benchmarking especially of prior knowledge approaches, which facilitates their applicability and for the first time enables a comprehensive assessment of their effectiveness}, language = {en} } @misc{Perscheid2021, author = {Perscheid, Cindy}, title = {Comprior: facilitating the implementation and automated benchmarking of prior knowledge-based feature selection approaches on gene expression data sets}, series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, journal = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-54894}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-548943}, pages = {1 -- 15}, year = {2021}, abstract = {Background Reproducible benchmarking is important for assessing the effectiveness of novel feature selection approaches applied on gene expression data, especially for prior knowledge approaches that incorporate biological information from online knowledge bases. However, no full-fledged benchmarking system exists that is extensible, provides built-in feature selection approaches, and a comprehensive result assessment encompassing classification performance, robustness, and biological relevance. Moreover, the particular needs of prior knowledge feature selection approaches, i.e. uniform access to knowledge bases, are not addressed. As a consequence, prior knowledge approaches are not evaluated amongst each other, leaving open questions regarding their effectiveness. Results We present the Comprior benchmark tool, which facilitates the rapid development and effortless benchmarking of feature selection approaches, with a special focus on prior knowledge approaches. Comprior is extensible by custom approaches, offers built-in standard feature selection approaches, enables uniform access to multiple knowledge bases, and provides a customizable evaluation infrastructure to compare multiple feature selection approaches regarding their classification performance, robustness, runtime, and biological relevance. Conclusion Comprior allows reproducible benchmarking especially of prior knowledge approaches, which facilitates their applicability and for the first time enables a comprehensive assessment of their effectiveness}, language = {en} } @misc{RazzaqKaminskiRomeroetal.2018, author = {Razzaq, Misbah and Kaminski, Roland and Romero, Javier and Schaub, Torsten H. and Bourdon, Jeremie and Guziolowski, Carito}, title = {Computing diverse boolean networks from phosphoproteomic time series data}, series = {Computational Methods in Systems Biology}, volume = {11095}, journal = {Computational Methods in Systems Biology}, publisher = {Springer}, address = {Berlin}, isbn = {978-3-319-99429-1}, issn = {0302-9743}, doi = {10.1007/978-3-319-99429-1_4}, pages = {59 -- 74}, year = {2018}, abstract = {Logical modeling has been widely used to understand and expand the knowledge about protein interactions among different pathways. Realizing this, the caspo-ts system has been proposed recently to learn logical models from time series data. It uses Answer Set Programming to enumerate Boolean Networks (BNs) given prior knowledge networks and phosphoproteomic time series data. In the resulting sequence of solutions, similar BNs are typically clustered together. This can be problematic for large scale problems where we cannot explore the whole solution space in reasonable time. Our approach extends the caspo-ts system to cope with the important use case of finding diverse solutions of a problem with a large number of solutions. We first present the algorithm for finding diverse solutions and then we demonstrate the results of the proposed approach on two different benchmark scenarios in systems biology: (1) an artificial dataset to model TCR signaling and (2) the HPN-DREAM challenge dataset to model breast cancer cell lines.}, language = {en} } @phdthesis{Limberger2024, author = {Limberger, Daniel}, title = {Concepts and techniques for 3D-embedded treemaps and their application to software visualization}, doi = {10.25932/publishup-63201}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-632014}, school = {Universit{\"a}t Potsdam}, pages = {xi, 118}, year = {2024}, abstract = {This thesis addresses concepts and techniques for interactive visualization of hierarchical data using treemaps. It explores (1) how treemaps can be embedded in 3D space to improve their information content and expressiveness, (2) how the readability of treemaps can be improved using level-of-detail and degree-of-interest techniques, and (3) how to design and implement a software framework for the real-time web-based rendering of treemaps embedded in 3D. With a particular emphasis on their application, use cases from software analytics are taken to test and evaluate the presented concepts and techniques. Concerning the first challenge, this thesis shows that a 3D attribute space offers enhanced possibilities for the visual mapping of data compared to classical 2D treemaps. In particular, embedding in 3D allows for improved implementation of visual variables (e.g., by sketchiness and color weaving), provision of new visual variables (e.g., by physically based materials and in situ templates), and integration of visual metaphors (e.g., by reference surfaces and renderings of natural phenomena) into the three-dimensional representation of treemaps. For the second challenge—the readability of an information visualization—the work shows that the generally higher visual clutter and increased cognitive load typically associated with three-dimensional information representations can be kept low in treemap-based representations of both small and large hierarchical datasets. By introducing an adaptive level-of-detail technique, we cannot only declutter the visualization results, thereby reducing cognitive load and mitigating occlusion problems, but also summarize and highlight relevant data. Furthermore, this approach facilitates automatic labeling, supports the emphasis on data outliers, and allows visual variables to be adjusted via degree-of-interest measures. The third challenge is addressed by developing a real-time rendering framework with WebGL and accumulative multi-frame rendering. The framework removes hardware constraints and graphics API requirements, reduces interaction response times, and simplifies high-quality rendering. At the same time, the implementation effort for a web-based deployment of treemaps is kept reasonable. The presented visualization concepts and techniques are applied and evaluated for use cases in software analysis. In this domain, data about software systems, especially about the state and evolution of the source code, does not have a descriptive appearance or natural geometric mapping, making information visualization a key technology here. In particular, software source code can be visualized with treemap-based approaches because of its inherently hierarchical structure. With treemaps embedded in 3D, we can create interactive software maps that visually map, software metrics, software developer activities, or information about the evolution of software systems alongside their hierarchical module structure. Discussions on remaining challenges and opportunities for future research for 3D-embedded treemaps and their applications conclude the thesis.}, language = {en} } @phdthesis{Richter2018, author = {Richter, Rico}, title = {Concepts and techniques for processing and rendering of massive 3D point clouds}, doi = {10.25932/publishup-42330}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-423304}, school = {Universit{\"a}t Potsdam}, pages = {v, 131}, year = {2018}, abstract = {Remote sensing technology, such as airborne, mobile, or terrestrial laser scanning, and photogrammetric techniques, are fundamental approaches for efficient, automatic creation of digital representations of spatial environments. For example, they allow us to generate 3D point clouds of landscapes, cities, infrastructure networks, and sites. As essential and universal category of geodata, 3D point clouds are used and processed by a growing number of applications, services, and systems such as in the domains of urban planning, landscape architecture, environmental monitoring, disaster management, virtual geographic environments as well as for spatial analysis and simulation. While the acquisition processes for 3D point clouds become more and more reliable and widely-used, applications and systems are faced with more and more 3D point cloud data. In addition, 3D point clouds, by their very nature, are raw data, i.e., they do not contain any structural or semantics information. Many processing strategies common to GIS such as deriving polygon-based 3D models generally do not scale for billions of points. GIS typically reduce data density and precision of 3D point clouds to cope with the sheer amount of data, but that results in a significant loss of valuable information at the same time. This thesis proposes concepts and techniques designed to efficiently store and process massive 3D point clouds. To this end, object-class segmentation approaches are presented to attribute semantics to 3D point clouds, used, for example, to identify building, vegetation, and ground structures and, thus, to enable processing, analyzing, and visualizing 3D point clouds in a more effective and efficient way. Similarly, change detection and updating strategies for 3D point clouds are introduced that allow for reducing storage requirements and incrementally updating 3D point cloud databases. In addition, this thesis presents out-of-core, real-time rendering techniques used to interactively explore 3D point clouds and related analysis results. All techniques have been implemented based on specialized spatial data structures, out-of-core algorithms, and GPU-based processing schemas to cope with massive 3D point clouds having billions of points. All proposed techniques have been evaluated and demonstrated their applicability to the field of geospatial applications and systems, in particular for tasks such as classification, processing, and visualization. Case studies for 3D point clouds of entire cities with up to 80 billion points show that the presented approaches open up new ways to manage and apply large-scale, dense, and time-variant 3D point clouds as required by a rapidly growing number of applications and systems.}, language = {en} } @misc{CombiOliboniWeskeetal.2018, author = {Combi, Carlo and Oliboni, Barbara and Weske, Mathias and Zerbato, Francesca}, title = {Conceptual modeling of processes and data}, series = {Conceptual Modeling, ER 2018}, volume = {11157}, journal = {Conceptual Modeling, ER 2018}, editor = {Trujillo, JC Davis}, publisher = {Springer}, address = {Cham}, isbn = {978-3-030-00847-5}, issn = {0302-9743}, doi = {10.1007/978-3-030-00847-5_18}, pages = {236 -- 250}, year = {2018}, abstract = {Business processes constantly generate, manipulate, and consume data that are managed by organizational databases. Despite being central to process modeling and execution, the link between processes and data is often handled by developers when the process is implemented, thus leaving the connection unexplored during the conceptual design. In this paper, we introduce, formalize, and evaluate a novel conceptual view that bridges the gap between process and data models, and show some kinds of interesting insights that can be derived from this novel proposal.}, language = {en} } @article{BeirneNicGiollaMhichilBrownetal.2021, author = {Beirne, Elaine and Nic Giolla Mhich{\´i}l, Mair{\´e}ad and Brown, Mark and Mac Lochlainn, Conch{\´u}r}, title = {Confidence Counts}, series = {EMOOCs 2021}, volume = {2021}, journal = {EMOOCs 2021}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51722}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-517220}, pages = {201 -- 208}, year = {2021}, abstract = {The increasing reliance on online learning in higher education has been further expedited by the on-going Covid-19 pandemic. Students need to be supported as they adapt to this new learning environment. Research has established that learners with positive online learning self-efficacy beliefs are more likely to persevere and achieve their higher education goals when learning online. In this paper, we explore how MOOC design can contribute to the four sources of self-efficacy beliefs posited by Bandura [4]. Specifically, we will explore, drawing on learner reflections, whether design elements of the MOOC, The Digital Edge: Essentials for the Online Learner, provided participants with the necessary mastery experiences, vicarious experiences, verbal persuasion, and affective regulation opportunities, to evaluate and develop their online learning self-efficacy beliefs. Findings from a content analysis of discussion forum posts show that learners referenced three of the four information sources when reflecting on their experience of the MOOC. This paper illustrates the potential of MOOCs as a pedagogical tool for enhancing online learning self-efficacy among students.}, language = {en} } @article{GalkaMoontahaSiniatchkin2020, author = {Galka, Andreas and Moontaha, Sidratul and Siniatchkin, Michael}, title = {Constrained expectation maximisation algorithm for estimating ARMA models in state space representation}, series = {EURASIP journal on advances in signal processing}, volume = {2020}, journal = {EURASIP journal on advances in signal processing}, number = {1}, publisher = {Springer}, address = {Heidelberg}, issn = {1687-6180}, doi = {10.1186/s13634-020-00678-3}, pages = {37}, year = {2020}, abstract = {This paper discusses the fitting of linear state space models to given multivariate time series in the presence of constraints imposed on the four main parameter matrices of these models. Constraints arise partly from the assumption that the models have a block-diagonal structure, with each block corresponding to an ARMA process, that allows the reconstruction of independent source components from linear mixtures, and partly from the need to keep models identifiable. The first stage of parameter fitting is performed by the expectation maximisation (EM) algorithm. Due to the identifiability constraint, a subset of the diagonal elements of the dynamical noise covariance matrix needs to be constrained to fixed values (usually unity). For this kind of constraints, so far, no closed-form update rules were available. We present new update rules for this situation, both for updating the dynamical noise covariance matrix directly and for updating a matrix square-root of this matrix. The practical applicability of the proposed algorithm is demonstrated by a low-dimensional simulation example. The behaviour of the EM algorithm, as observed in this example, illustrates the well-known fact that in practical applications, the EM algorithm should be combined with a different algorithm for numerical optimisation, such as a quasi-Newton algorithm.}, language = {en} } @article{SoechtingTrapp2020, author = {S{\"o}chting, Maximilian and Trapp, Matthias}, title = {Controlling image-stylization techniques using eye tracking}, series = {Science and Technology Publications}, journal = {Science and Technology Publications}, publisher = {Springer}, address = {Berlin}, issn = {2184-4321}, pages = {10}, year = {2020}, abstract = {With the spread of smart phones capable of taking high-resolution photos and the development of high-speed mobile data infrastructure, digital visual media is becoming one of the most important forms of modern communication. With this development, however, also comes a devaluation of images as a media form with the focus becoming the frequency at which visual content is generated instead of the quality of the content. In this work, an interactive system using image-abstraction techniques and an eye tracking sensor is presented, which allows users to experience diverting and dynamic artworks that react to their eye movement. The underlying modular architecture enables a variety of different interaction techniques that share common design principles, making the interface as intuitive as possible. The resulting experience allows users to experience a game-like interaction in which they aim for a reward, the artwork, while being held under constraints, e.g., not blinking. The co nscious eye movements that are required by some interaction techniques hint an interesting, possible future extension for this work into the field of relaxation exercises and concentration training.}, language = {en} } @misc{SoechtingTrapp2020, author = {S{\"o}chting, Maximilian and Trapp, Matthias}, title = {Controlling image-stylization techniques using eye tracking}, series = {Postprints der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, journal = {Postprints der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, number = {7}, doi = {10.25932/publishup-52471}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-524717}, pages = {12}, year = {2020}, abstract = {With the spread of smart phones capable of taking high-resolution photos and the development of high-speed mobile data infrastructure, digital visual media is becoming one of the most important forms of modern communication. With this development, however, also comes a devaluation of images as a media form with the focus becoming the frequency at which visual content is generated instead of the quality of the content. In this work, an interactive system using image-abstraction techniques and an eye tracking sensor is presented, which allows users to experience diverting and dynamic artworks that react to their eye movement. The underlying modular architecture enables a variety of different interaction techniques that share common design principles, making the interface as intuitive as possible. The resulting experience allows users to experience a game-like interaction in which they aim for a reward, the artwork, while being held under constraints, e.g., not blinking. The co nscious eye movements that are required by some interaction techniques hint an interesting, possible future extension for this work into the field of relaxation exercises and concentration training.}, language = {en} } @misc{PerlichMeinel2018, author = {Perlich, Anja and Meinel, Christoph}, title = {Cooperative Note-Taking in Psychotherapy Sessions}, series = {2018 IEEE 20th International Conference on e-Health Networking, Applications and Services (Healthcom)}, journal = {2018 IEEE 20th International Conference on e-Health Networking, Applications and Services (Healthcom)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-4294-8}, pages = {6}, year = {2018}, abstract = {In the course of patient treatments, psychotherapists aim to meet the challenges of being both a trusted, knowledgeable conversation partner and a diligent documentalist. We are developing the digital whiteboard system Tele-Board MED (TBM), which allows the therapist to take digital notes during the session together with the patient. This study investigates what therapists are experiencing when they document with TBM in patient sessions for the first time and whether this documentation saves them time when writing official clinical documents. As the core of this study, we conducted four anamnesis session dialogues with behavior psychotherapists and volunteers acting in the role of patients. Following a mixed-method approach, the data collection and analysis involved self-reported emotion samples, user experience curves and questionnaires. We found that even in the very first patient session with TBM, therapists come to feel comfortable, develop a positive feeling and can concentrate on the patient. Regarding administrative documentation tasks, we found with the TBM report generation feature the therapists save 60\% of the time they normally spend on writing case reports to the health insurance.}, 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} } @article{BelaidRabusKrestel2021, author = {Belaid, Mohamed Karim and Rabus, Maximilian and Krestel, Ralf}, title = {CrashNet}, series = {Data mining and knowledge discovery}, volume = {35}, journal = {Data mining and knowledge discovery}, number = {4}, publisher = {Springer}, address = {Dordrecht}, issn = {1384-5810}, doi = {10.1007/s10618-021-00761-9}, pages = {1688 -- 1709}, year = {2021}, abstract = {Destructive car crash tests are an elaborate, time-consuming, and expensive necessity of the automotive development process. Today, finite element method (FEM) simulations are used to reduce costs by simulating car crashes computationally. We propose CrashNet, an encoder-decoder deep neural network architecture that reduces costs further and models specific outcomes of car crashes very accurately. We achieve this by formulating car crash events as time series prediction enriched with a set of scalar features. Traditional sequence-to-sequence models are usually composed of convolutional neural network (CNN) and CNN transpose layers. We propose to concatenate those with an MLP capable of learning how to inject the given scalars into the output time series. In addition, we replace the CNN transpose with 2D CNN transpose layers in order to force the model to process the hidden state of the set of scalars as one time series. The proposed CrashNet model can be trained efficiently and is able to process scalars and time series as input in order to infer the results of crash tests. CrashNet produces results faster and at a lower cost compared to destructive tests and FEM simulations. Moreover, it represents a novel approach in the car safety management domain.}, language = {en} } @misc{BruechnerRenzKlingbeil2019, author = {Bruechner, Dominik and Renz, Jan and Klingbeil, Mandy}, title = {Creating a Framework for User-Centered Development and Improvement of Digital Education}, series = {Scale}, journal = {Scale}, publisher = {Association for Computing Machinery}, address = {New York}, isbn = {978-1-4503-6804-9}, doi = {10.1145/3330430.3333644}, pages = {4}, year = {2019}, abstract = {We investigate how the technology acceptance and learning experience of the digital education platform HPI Schul-Cloud (HPI School Cloud) for German secondary school teachers can be improved by proposing a user-centered research and development framework. We highlight the importance of developing digital learning technologies in a user-centered way to take differences in the requirements of educators and students into account. We suggest applying qualitative and quantitative methods to build a solid understanding of a learning platform's users, their needs, requirements, and their context of use. After concept development and idea generation of features and areas of opportunity based on the user research, we emphasize on the application of a multi-attribute utility analysis decision-making framework to prioritize ideas rationally, taking results of user research into account. Afterward, we recommend applying the principle build-learn-iterate to build prototypes in different resolutions while learning from user tests and improving the selected opportunities. Last but not least, we propose an approach for continuous short- and long-term user experience controlling and monitoring, extending existing web- and learning analytics metrics.}, language = {en} } @article{ThienenWeinsteinMeinel2023, author = {Thienen, Julia von and Weinstein, Theresa Julia and Meinel, Christoph}, title = {Creative metacognition in design thinking}, series = {Frontiers in psychology}, volume = {14}, journal = {Frontiers in psychology}, publisher = {Frontiers Research Foundation}, address = {Lausanne}, issn = {1664-1078}, doi = {10.3389/fpsyg.2023.1157001}, pages = {20}, year = {2023}, abstract = {Design thinking is a well-established practical and educational approach to fostering high-level creativity and innovation, which has been refined since the 1950s with the participation of experts like Joy Paul Guilford and Abraham Maslow. Through real-world projects, trainees learn to optimize their creative outcomes by developing and practicing creative cognition and metacognition. This paper provides a holistic perspective on creativity, enabling the formulation of a comprehensive theoretical framework of creative metacognition. It focuses on the design thinking approach to creativity and explores the role of metacognition in four areas of creativity expertise: Products, Processes, People, and Places. The analysis includes task-outcome relationships (product metacognition), the monitoring of strategy effectiveness (process metacognition), an understanding of individual or group strengths and weaknesses (people metacognition), and an examination of the mutual impact between environments and creativity (place metacognition). It also reviews measures taken in design thinking education, including a distribution of cognition and metacognition, to support students in their development of creative mastery. On these grounds, we propose extended methods for measuring creative metacognition with the goal of enhancing comprehensive assessments of the phenomenon. Proposed methodological advancements include accuracy sub-scales, experimental tasks where examinees explore problem and solution spaces, combinations of naturalistic observations with capability testing, as well as physiological assessments as indirect measures of creative metacognition.}, language = {en} } @article{BinTareafBergerHennigetal.2020, author = {Bin Tareaf, Raad and Berger, Philipp and Hennig, Patrick and Meinel, Christoph}, title = {Cross-platform personality exploration system for online social networks}, series = {Web intelligence}, volume = {18}, journal = {Web intelligence}, number = {1}, publisher = {IOS Press}, address = {Amsterdam}, issn = {2405-6456}, doi = {10.3233/WEB-200427}, pages = {35 -- 51}, year = {2020}, abstract = {Social networking sites (SNS) are a rich source of latent information about individual characteristics. Crawling and analyzing this content provides a new approach for enterprises to personalize services and put forward product recommendations. In the past few years, commercial brands made a gradual appearance on social media platforms for advertisement, customers support and public relation purposes and by now it became a necessity throughout all branches. This online identity can be represented as a brand personality that reflects how a brand is perceived by its customers. We exploited recent research in text analysis and personality detection to build an automatic brand personality prediction model on top of the (Five-Factor Model) and (Linguistic Inquiry and Word Count) features extracted from publicly available benchmarks. Predictive evaluation on brands' accounts reveals that Facebook platform provides a slight advantage over Twitter platform in offering more self-disclosure for users' to express their emotions especially their demographic and psychological traits. Results also confirm the wider perspective that the same social media account carry a quite similar and comparable personality scores over different social media platforms. For evaluating our prediction results on actual brands' accounts, we crawled the Facebook API and Twitter API respectively for 100k posts from the most valuable brands' pages in the USA and we visualize exemplars of comparison results and present suggestions for future directions.}, language = {en} } @misc{TorkuraSukmanaStraussetal.2018, author = {Torkura, Kennedy A. and Sukmana, Muhammad Ihsan Haikal and Strauss, Tim and Graupner, Hendrik and Cheng, Feng and Meinel, Christoph}, title = {CSBAuditor}, series = {17th International Symposium on Network Computing and Applications (NCA)}, journal = {17th International Symposium on Network Computing and Applications (NCA)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-7659-2}, doi = {10.1109/NCA.2018.8548329}, pages = {10}, year = {2018}, abstract = {Cloud Storage Brokers (CSB) provide seamless and concurrent access to multiple Cloud Storage Services (CSS) while abstracting cloud complexities from end-users. However, this multi-cloud strategy faces several security challenges including enlarged attack surfaces, malicious insider threats, security complexities due to integration of disparate components and API interoperability issues. Novel security approaches are imperative to tackle these security issues. Therefore, this paper proposes CSBAuditor, a novel cloud security system that continuously audits CSB resources, to detect malicious activities and unauthorized changes e.g. bucket policy misconfigurations, and remediates these anomalies. The cloud state is maintained via a continuous snapshotting mechanism thereby ensuring fault tolerance. We adopt the principles of chaos engineering by integrating Broker Monkey, a component that continuously injects failure into our reference CSB system, Cloud RAID. Hence, CSBAuditor is continuously tested for efficiency i.e. its ability to detect the changes injected by Broker Monkey. CSBAuditor employs security metrics for risk analysis by computing severity scores for detected vulnerabilities using the Common Configuration Scoring System, thereby overcoming the limitation of insufficient security metrics in existing cloud auditing schemes. CSBAuditor has been tested using various strategies including chaos engineering failure injection strategies. Our experimental evaluation validates the efficiency of our approach against the aforementioned security issues with a detection and recovery rate of over 96 \%.}, language = {en} } @misc{LosterNaumannEhmuelleretal.2018, author = {Loster, Michael and Naumann, Felix and Ehmueller, Jan and Feldmann, Benjamin}, title = {CurEx}, series = {Proceedings of the 27th ACM International Conference on Information and Knowledge Management}, journal = {Proceedings of the 27th ACM International Conference on Information and Knowledge Management}, publisher = {Association for Computing Machinery}, address = {New York}, isbn = {978-1-4503-6014-2}, doi = {10.1145/3269206.3269229}, pages = {1883 -- 1886}, year = {2018}, abstract = {The integration of diverse structured and unstructured information sources into a unified, domain-specific knowledge base is an important task in many areas. A well-maintained knowledge base enables data analysis in complex scenarios, such as risk analysis in the financial sector or investigating large data leaks, such as the Paradise or Panama papers. Both the creation of such knowledge bases, as well as their continuous maintenance and curation involves many complex tasks and considerable manual effort. With CurEx, we present a modular system that allows structured and unstructured data sources to be integrated into a domain-specific knowledge base. In particular, we (i) enable the incremental improvement of each individual integration component; (ii) enable the selective generation of multiple knowledge graphs from the information contained in the knowledge base; and (iii) provide two distinct user interfaces tailored to the needs of data engineers and end-users respectively. The former has curation capabilities and controls the integration process, whereas the latter focuses on the exploration of the generated knowledge graph.}, language = {en} } @article{OmotoshoAyegbaEmuoyibofarheetal.2019, author = {Omotosho, Adebayo and Ayegba, Peace and Emuoyibofarhe, Justice and Meinel, Christoph}, title = {Current State of ICT in Healthcare Delivery in Developing Countries}, series = {International Journal of Online and Biomedical Engineering}, volume = {15}, journal = {International Journal of Online and Biomedical Engineering}, number = {8}, publisher = {Kassel University Press}, address = {Kassel}, issn = {2626-8493}, doi = {10.3991/ijoe.v15i08.10294}, pages = {91 -- 107}, year = {2019}, abstract = {Electronic health is one of the most popular applications of information and communication technologies and it has contributed immensely to health delivery through the provision of quality health service and ubiquitous access at a lower cost. Even though this mode of health service is increasingly becoming known or used in developing nations, these countries are faced with a myriad of challenges when implementing and deploying e-health services on both small and large scale. It is estimated that the Africa population alone carries the highest percentage of the world's global diseases despite its certain level of e-health adoption. This paper aims at analyzing the progress so far and the current state of e-health in developing countries particularly Africa and propose a framework for further improvement.}, language = {en} } @phdthesis{Koumarelas2020, author = {Koumarelas, Ioannis}, title = {Data preparation and domain-agnostic duplicate detection}, doi = {10.25932/publishup-48913}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-489131}, school = {Universit{\"a}t Potsdam}, pages = {x, 97}, year = {2020}, abstract = {Successfully completing any data science project demands careful consideration across its whole process. Although the focus is often put on later phases of the process, in practice, experts spend more time in earlier phases, preparing data, to make them consistent with the systems' requirements or to improve their models' accuracies. Duplicate detection is typically applied during the data cleaning phase, which is dedicated to removing data inconsistencies and improving the overall quality and usability of data. While data cleaning involves a plethora of approaches to perform specific operations, such as schema alignment and data normalization, the task of detecting and removing duplicate records is particularly challenging. Duplicates arise when multiple records representing the same entities exist in a database. Due to numerous reasons, spanning from simple typographical errors to different schemas and formats of integrated databases. Keeping a database free of duplicates is crucial for most use-cases, as their existence causes false negatives and false positives when matching queries against it. These two data quality issues have negative implications for tasks, such as hotel booking, where users may erroneously select a wrong hotel, or parcel delivery, where a parcel can get delivered to the wrong address. Identifying the variety of possible data issues to eliminate duplicates demands sophisticated approaches. While research in duplicate detection is well-established and covers different aspects of both efficiency and effectiveness, our work in this thesis focuses on the latter. We propose novel approaches to improve data quality before duplicate detection takes place and apply the latter in datasets even when prior labeling is not available. Our experiments show that improving data quality upfront can increase duplicate classification results by up to 19\%. To this end, we propose two novel pipelines that select and apply generic as well as address-specific data preparation steps with the purpose of maximizing the success of duplicate detection. Generic data preparation, such as the removal of special characters, can be applied to any relation with alphanumeric attributes. When applied, data preparation steps are selected only for attributes where there are positive effects on pair similarities, which indirectly affect classification, or on classification directly. Our work on addresses is twofold; first, we consider more domain-specific approaches to improve the quality of values, and, second, we experiment with known and modified versions of similarity measures to select the most appropriate per address attribute, e.g., city or country. To facilitate duplicate detection in applications where gold standard annotations are not available and obtaining them is not possible or too expensive, we propose MDedup. MDedup is a novel, rule-based, and fully automatic duplicate detection approach that is based on matching dependencies. These dependencies can be used to detect duplicates and can be discovered using state-of-the-art algorithms efficiently and without any prior labeling. MDedup uses two pipelines to first train on datasets with known labels, learning to identify useful matching dependencies, and then be applied on unseen datasets, regardless of any existing gold standard. Finally, our work is accompanied by open source code to enable repeatability of our research results and application of our approaches to other datasets.}, language = {en} } @phdthesis{Papenbrock2017, author = {Papenbrock, Thorsten}, title = {Data profiling - efficient discovery of dependencies}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-406705}, school = {Universit{\"a}t Potsdam}, pages = {viii, ii, 141}, year = {2017}, abstract = {Data profiling is the computer science discipline of analyzing a given dataset for its metadata. The types of metadata range from basic statistics, such as tuple counts, column aggregations, and value distributions, to much more complex structures, in particular inclusion dependencies (INDs), unique column combinations (UCCs), and functional dependencies (FDs). If present, these statistics and structures serve to efficiently store, query, change, and understand the data. Most datasets, however, do not provide their metadata explicitly so that data scientists need to profile them. While basic statistics are relatively easy to calculate, more complex structures present difficult, mostly NP-complete discovery tasks; even with good domain knowledge, it is hardly possible to detect them manually. Therefore, various profiling algorithms have been developed to automate the discovery. None of them, however, can process datasets of typical real-world size, because their resource consumptions and/or execution times exceed effective limits. In this thesis, we propose novel profiling algorithms that automatically discover the three most popular types of complex metadata, namely INDs, UCCs, and FDs, which all describe different kinds of key dependencies. The task is to extract all valid occurrences from a given relational instance. The three algorithms build upon known techniques from related work and complement them with algorithmic paradigms, such as divide \& conquer, hybrid search, progressivity, memory sensitivity, parallelization, and additional pruning to greatly improve upon current limitations. Our experiments show that the proposed algorithms are orders of magnitude faster than related work. They are, in particular, now able to process datasets of real-world, i.e., multiple gigabytes size with reasonable memory and time consumption. Due to the importance of data profiling in practice, industry has built various profiling tools to support data scientists in their quest for metadata. These tools provide good support for basic statistics and they are also able to validate individual dependencies, but they lack real discovery features even though some fundamental discovery techniques are known for more than 15 years. To close this gap, we developed Metanome, an extensible profiling platform that incorporates not only our own algorithms but also many further algorithms from other researchers. With Metanome, we make our research accessible to all data scientists and IT-professionals that are tasked with data profiling. Besides the actual metadata discovery, the platform also offers support for the ranking and visualization of metadata result sets. Being able to discover the entire set of syntactically valid metadata naturally introduces the subsequent task of extracting only the semantically meaningful parts. This is challenge, because the complete metadata results are surprisingly large (sometimes larger than the datasets itself) and judging their use case dependent semantic relevance is difficult. To show that the completeness of these metadata sets is extremely valuable for their usage, we finally exemplify the efficient processing and effective assessment of functional dependencies for the use case of schema normalization.}, language = {en} } @misc{BazhenovaZerbatoWeske2018, author = {Bazhenova, Ekaterina and Zerbato, Francesca and Weske, Mathias}, title = {Data-Centric Extraction of DMN Decision Models from BPMN Process Models}, series = {Business Process Management Workshops}, volume = {308}, journal = {Business Process Management Workshops}, publisher = {Springer}, address = {Berlin}, isbn = {978-3-319-74030-0}, issn = {1865-1348}, doi = {10.1007/978-3-319-74030-0_43}, pages = {542 -- 555}, year = {2018}, abstract = {Operational decisions in business processes can be modeled by using the Decision Model and Notation (DMN). The complementary use of DMN for decision modeling and of the Business Process Model and Notation (BPMN) for process design realizes the separation of concerns principle. For supporting separation of concerns during the design phase, it is crucial to understand which aspects of decision-making enclosed in a process model should be captured by a dedicated decision model. Whereas existing work focuses on the extraction of decision models from process control flow, the connection of process-related data and decision models is still unexplored. In this paper, we investigate how process-related data used for making decisions can be represented in process models and we distinguish a set of BPMN patterns capturing such information. Then, we provide a formal mapping of the identified BPMN patterns to corresponding DMN models and apply our approach to a real-world healthcare process.}, 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} } @article{SchlosserBoissier2018, author = {Schlosser, Rainer and Boissier, Martin}, title = {Dealing with the dimensionality curse in dynamic pricing competition}, series = {Computers \& Operations Research}, volume = {100}, journal = {Computers \& Operations Research}, publisher = {Elsevier}, address = {Oxford}, issn = {0305-0548}, doi = {10.1016/j.cor.2018.07.011}, pages = {26 -- 42}, year = {2018}, abstract = {Most sales applications are characterized by competition and limited demand information. For successful pricing strategies, frequent price adjustments as well as anticipation of market dynamics are crucial. Both effects are challenging as competitive markets are complex and computations of optimized pricing adjustments can be time-consuming. We analyze stochastic dynamic pricing models under oligopoly competition for the sale of perishable goods. To circumvent the curse of dimensionality, we propose a heuristic approach to efficiently compute price adjustments. To demonstrate our strategy's applicability even if the number of competitors is large and their strategies are unknown, we consider different competitive settings in which competitors frequently and strategically adjust their prices. For all settings, we verify that our heuristic strategy yields promising results. We compare the performance of our heuristic against upper bounds, which are obtained by optimal strategies that take advantage of perfect price anticipations. We find that price adjustment frequencies can have a larger impact on expected profits than price anticipations. Finally, our approach has been applied on Amazon for the sale of used books. We have used a seller's historical market data to calibrate our model. Sales results show that our data-driven strategy outperforms the rule-based strategy of an experienced seller by a profit increase of more than 20\%.}, language = {en} } @book{BartzKrestel2021, author = {Bartz, Christian and Krestel, Ralf}, title = {Deep learning for computer vision in the art domain}, number = {139}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-514-9}, issn = {1613-5652}, doi = {10.25932/publishup-51290}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-512906}, publisher = {Universit{\"a}t Potsdam}, pages = {vii, 79}, year = {2021}, abstract = {In recent years, computer vision algorithms based on machine learning have seen rapid development. In the past, research mostly focused on solving computer vision problems such as image classification or object detection on images displaying natural scenes. Nowadays other fields such as the field of cultural heritage, where an abundance of data is available, also get into the focus of research. In the line of current research endeavours, we collaborated with the Getty Research Institute which provided us with a challenging dataset, containing images of paintings and drawings. In this technical report, we present the results of the seminar "Deep Learning for Computer Vision". In this seminar, students of the Hasso Plattner Institute evaluated state-of-the-art approaches for image classification, object detection and image recognition on the dataset of the Getty Research Institute. The main challenge when applying modern computer vision methods to the available data is the availability of annotated training data, as the dataset provided by the Getty Research Institute does not contain a sufficient amount of annotated samples for the training of deep neural networks. However, throughout the report we show that it is possible to achieve satisfying to very good results, when using further publicly available datasets, such as the WikiArt dataset, for the training of machine learning models.}, language = {en} } @phdthesis{Yang2019, author = {Yang, Haojin}, title = {Deep representation learning for multimedia data analysis}, school = {Universit{\"a}t Potsdam}, pages = {278}, year = {2019}, language = {en} } @phdthesis{Rezaei2019, author = {Rezaei, Mina}, title = {Deep representation learning from imbalanced medical imaging}, doi = {10.25932/publishup-44275}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-442759}, school = {Universit{\"a}t Potsdam}, pages = {xxviii, 160}, year = {2019}, abstract = {Medical imaging plays an important role in disease diagnosis, treatment planning, and clinical monitoring. One of the major challenges in medical image analysis is imbalanced training data, in which the class of interest is much rarer than the other classes. Canonical machine learning algorithms suppose that the number of samples from different classes in the training dataset is roughly similar or balance. Training a machine learning model on an imbalanced dataset can introduce unique challenges to the learning problem. A model learned from imbalanced training data is biased towards the high-frequency samples. The predicted results of such networks have low sensitivity and high precision. In medical applications, the cost of misclassification of the minority class could be more than the cost of misclassification of the majority class. For example, the risk of not detecting a tumor could be much higher than referring to a healthy subject to a doctor. The current Ph.D. thesis introduces several deep learning-based approaches for handling class imbalanced problems for learning multi-task such as disease classification and semantic segmentation. At the data-level, the objective is to balance the data distribution through re-sampling the data space: we propose novel approaches to correct internal bias towards fewer frequency samples. These approaches include patient-wise batch sampling, complimentary labels, supervised and unsupervised minority oversampling using generative adversarial networks for all. On the other hand, at algorithm-level, we modify the learning algorithm to alleviate the bias towards majority classes. In this regard, we propose different generative adversarial networks for cost-sensitive learning, ensemble learning, and mutual learning to deal with highly imbalanced imaging data. We show evidence that the proposed approaches are applicable to different types of medical images of varied sizes on different applications of routine clinical tasks, such as disease classification and semantic segmentation. Our various implemented algorithms have shown outstanding results on different medical imaging challenges.}, language = {en} } @article{ZieglerPfitznerSchulzetal.2022, author = {Ziegler, Joceline and Pfitzner, Bjarne and Schulz, Heinrich and Saalbach, Axel and Arnrich, Bert}, title = {Defending against Reconstruction Attacks through Differentially Private Federated Learning for Classification of Heterogeneous Chest X-ray Data}, series = {Sensors}, volume = {22}, journal = {Sensors}, edition = {14}, publisher = {MDPI}, address = {Basel, Schweiz}, issn = {1424-8220}, doi = {10.3390/s22145195}, pages = {25}, year = {2022}, abstract = {Privacy regulations and the physical distribution of heterogeneous data are often primary concerns for the development of deep learning models in a medical context. This paper evaluates the feasibility of differentially private federated learning for chest X-ray classification as a defense against data privacy attacks. To the best of our knowledge, we are the first to directly compare the impact of differentially private training on two different neural network architectures, DenseNet121 and ResNet50. Extending the federated learning environments previously analyzed in terms of privacy, we simulated a heterogeneous and imbalanced federated setting by distributing images from the public CheXpert and Mendeley chest X-ray datasets unevenly among 36 clients. Both non-private baseline models achieved an area under the receiver operating characteristic curve (AUC) of 0.940.94 on the binary classification task of detecting the presence of a medical finding. We demonstrate that both model architectures are vulnerable to privacy violation by applying image reconstruction attacks to local model updates from individual clients. The attack was particularly successful during later training stages. To mitigate the risk of a privacy breach, we integrated R{\´e}nyi differential privacy with a Gaussian noise mechanism into local model training. We evaluate model performance and attack vulnerability for privacy budgets ε∈{1,3,6,10}�∈{1,3,6,10}. The DenseNet121 achieved the best utility-privacy trade-off with an AUC of 0.940.94 for ε=6�=6. Model performance deteriorated slightly for individual clients compared to the non-private baseline. The ResNet50 only reached an AUC of 0.760.76 in the same privacy setting. Its performance was inferior to that of the DenseNet121 for all considered privacy constraints, suggesting that the DenseNet121 architecture is more robust to differentially private training.}, language = {en} } @misc{ZieglerPfitznerSchulzetal.2022, author = {Ziegler, Joceline and Pfitzner, Bjarne and Schulz, Heinrich and Saalbach, Axel and Arnrich, Bert}, title = {Defending against Reconstruction Attacks through Differentially Private Federated Learning for Classification of Heterogeneous Chest X-ray Data}, series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, journal = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, number = {14}, doi = {10.25932/publishup-58132}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-581322}, pages = {25}, year = {2022}, abstract = {Privacy regulations and the physical distribution of heterogeneous data are often primary concerns for the development of deep learning models in a medical context. This paper evaluates the feasibility of differentially private federated learning for chest X-ray classification as a defense against data privacy attacks. To the best of our knowledge, we are the first to directly compare the impact of differentially private training on two different neural network architectures, DenseNet121 and ResNet50. Extending the federated learning environments previously analyzed in terms of privacy, we simulated a heterogeneous and imbalanced federated setting by distributing images from the public CheXpert and Mendeley chest X-ray datasets unevenly among 36 clients. Both non-private baseline models achieved an area under the receiver operating characteristic curve (AUC) of 0.940.94 on the binary classification task of detecting the presence of a medical finding. We demonstrate that both model architectures are vulnerable to privacy violation by applying image reconstruction attacks to local model updates from individual clients. The attack was particularly successful during later training stages. To mitigate the risk of a privacy breach, we integrated R{\´e}nyi differential privacy with a Gaussian noise mechanism into local model training. We evaluate model performance and attack vulnerability for privacy budgets ε∈{1,3,6,10}�∈{1,3,6,10}. The DenseNet121 achieved the best utility-privacy trade-off with an AUC of 0.940.94 for ε=6�=6. Model performance deteriorated slightly for individual clients compared to the non-private baseline. The ResNet50 only reached an AUC of 0.760.76 in the same privacy setting. Its performance was inferior to that of the DenseNet121 for all considered privacy constraints, suggesting that the DenseNet121 architecture is more robust to differentially private training.}, language = {en} } @article{KrentzMeinel2018, author = {Krentz, Konrad-Felix and Meinel, Christoph}, title = {Denial-of-sleep defenses for IEEE 802.15.4 coordinated sampled listening (CSL)}, series = {Computer Networks}, volume = {148}, journal = {Computer Networks}, publisher = {Elsevier}, address = {Amsterdam}, issn = {1389-1286}, doi = {10.1016/j.comnet.2018.10.021}, pages = {60 -- 71}, year = {2018}, abstract = {Coordinated sampled listening (CSL) is a standardized medium access control protocol for IEEE 80215.4 networks. Unfortunately, CSL comes without any protection against so-called denial-of-sleep attacks. Such attacks deprive energy-constrained devices of entering low-power sleep modes, thereby draining their charge. Repercussions of denial-of-sleep attacks include long outages, violated quality-of-service guarantees, and reduced customer satisfaction. However, while CSL has no built-in denial-of-sleep defenses, there already exist denial-of-sleep defenses for a predecessor of CSL, namely ContikiMAC. In this paper, we make two main contributions. First, motivated by the fact that CSL has many advantages over ContikiMAC, we tailor the existing denial-of-sleep defenses for ContikiMAC to CSL. Second, we propose several security enhancements to these existing denial-of-sleep defenses. In effect, our denial-of-sleep defenses for CSL mitigate denial-of-sleep attacks significantly better, as well as protect against a larger range of denial-of-sleep attacks than the existing denial-of-sleep defenses for ContikiMAC. We show the soundness of our denial-of-sleep defenses for CSL both analytically, as well as empirically using a whole new implementation of CSL. (C) 2018 Elsevier B.V. All rights reserved.}, language = {en} } @article{GiannatelliTomasini2023, author = {Giannatelli, Ada and Tomasini, Alessandra}, title = {Descriptors and EU Standards to support the recognition of MOOCs}, series = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, journal = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, editor = {Meinel, Christoph and Schweiger, Stefanie and Staubitz, Thomas and Conrad, Robert and Alario Hoyos, Carlos and Ebner, Martin and Sancassani, Susanna and Żur, Agnieszka and Friedl, Christian and Halawa, Sherif and Gamage, Dilrukshi and Scott, Jeffrey and Kristine Jonson Carlon, May and Deville, Yves and Gaebel, Michael and Delgado Kloos, Carlos and von Schmieden, Karen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-62396}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-623967}, pages = {133 -- 146}, year = {2023}, abstract = {Digital technologies have enabled a variety of learning offers that opened new challenges in terms of recognition of formal, informal and non-formal learning, such as MOOCs. This paper focuses on how providing relevant data to describe a MOOC is conducive to increase the transparency of information and, ultimately, the flexibility of European higher education. The EU-funded project ECCOE took up these challenges and developed a solution by identifying the most relevant descriptors of a learning opportunity with a view to supporting a European system for micro-credentials. Descriptors indicate the specific properties of a learning opportunity according to European standards. They can provide a recognition framework also for small volumes of learning (micro-credentials) to support the integration of non-formal learning (MOOCs) into formal learning (e.g. institutional university courses) and to tackle skills shortage, upskilling and reskilling by acquiring relevant competencies. The focus on learning outcomes can facilitate the recognition of skills and competences of students and enhance both virtual and physical mobility and employability. This paper presents two contexts where ECCOE descriptors have been adopted: the Politecnico di Milano MOOC platform (Polimi Open Knowledge - POK), which is using these descriptors as the standard information to document the features of its learning opportunities, and the EU-funded Uforest project on urban forestry, which developed a blended training program for students of partner universities whose MOOCs used the ECCOE descriptors. Practice with ECCOE descriptors shows how they can be used not only to detail MOOC features, but also as a compass to design the learning offer. In addition, some rules of thumb can be derived and applied when using specific descriptors.}, language = {en} } @misc{BenderGrumGronauetal.2019, author = {Bender, Benedict and Grum, Marcus and Gronau, Norbert and Alfa, Attahiru and Maharaj, B. T.}, title = {Design of a worldwide simulation system for distributed cyber-physical production networks}, series = {2019 IEEE International Conference on Engineering, Technology and Innovation (ICE/ITMC)}, journal = {2019 IEEE International Conference on Engineering, Technology and Innovation (ICE/ITMC)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-7281-3401-7}, issn = {2334-315X}, doi = {10.1109/ICE.2019.8792609}, pages = {7}, year = {2019}, abstract = {Modern production infrastructures of globally operating companies usually consist of multiple distributed production sites. While the organization of individual sites consisting of Industry 4.0 components itself is demanding, new questions regarding the organization and allocation of resources emerge considering the total production network. In an attempt to face the challenge of efficient distribution and processing both within and across sites, we aim to provide a hybrid simulation approach as a first step towards optimization. Using hybrid simulation allows us to include real and simulated concepts and thereby benchmark different approaches with reasonable effort. A simulation concept is conceptualized and demonstrated qualitatively using a global multi-site example.}, language = {en} } @misc{PufahlWongWeske2018, author = {Pufahl, Luise and Wong, Tsun Yin and Weske, Mathias}, title = {Design of an extensible BPMN process simulator}, series = {Business Process Management Workshops (BPM 2017)}, volume = {308}, journal = {Business Process Management Workshops (BPM 2017)}, publisher = {Springer}, address = {Berlin}, isbn = {978-3-319-74030-0}, issn = {1865-1348}, doi = {10.1007/978-3-319-74030-0_62}, pages = {782 -- 795}, year = {2018}, abstract = {Business process simulation is an important means for quantitative analysis of a business process and to compare different process alternatives. With the Business Process Model and Notation (BPMN) being the state-of-the-art language for the graphical representation of business processes, many existing process simulators support already the simulation of BPMN diagrams. However, they do not provide well-defined interfaces to integrate new concepts in the simulation environment. In this work, we present the design and architecture of a proof-of-concept implementation of an open and extensible BPMN process simulator. It also supports the simulation of multiple BPMN processes at a time and relies on the building blocks of the well-founded discrete event simulation. The extensibility is assured by a plug-in concept. Its feasibility is demonstrated by extensions supporting new BPMN concepts, such as the simulation of business rule activities referencing decision models and batch activities.}, language = {en} } @phdthesis{Traifeh2023, author = {Traifeh, Hanadi}, title = {Design Thinking in the Arab world}, doi = {10.25932/publishup-59891}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-598911}, school = {Universit{\"a}t Potsdam}, pages = {ix, 196}, year = {2023}, abstract = {Design Thinking is a human-centered approach to innovation that has become increasingly popular globally over the last decade. While the spread of Design Thinking is well understood and documented in the Western cultural contexts, particularly in Europe and the US due to the popularity of the Stanford-Potsdam Design Thinking education model, this is not the case when it comes to non-Western cultural contexts. This thesis fills a gap identified in the literature regarding how Design Thinking emerged, was perceived, adopted, and practiced in the Arab world. The culture in that part of the world differs from that of the Western context, which impacts the mindset of people and how they interact with Design Thinking tools and methods. A mixed-methods research approach was followed in which both quantitative and qualitative methods were employed. First, two methods were used in the quantitative phase: a social media analysis using Twitter as a source of data, and an online questionnaire. The results and analysis of the quantitative data informed the design of the qualitative phase in which two methods were employed: ten semi-structured interviews, and participant observation of seven Design Thinking training events. According to the analyzed data, the Arab world appears to have had an early, though relatively weak, and slow, adoption of Design Thinking since 2006. Increasing adoption, however, has been witnessed over the last decade, especially in Saudi Arabia, the United Arab Emirates and Egypt. The results also show that despite its limited spread, Design Thinking has been practiced the most in education, information technology and communication, administrative services, and the non-profit sectors. The way it is being practiced, though, is not fully aligned with how it is being practiced and taught in the US and Europe, as most people in the region do not necessarily believe in all mindset attributes introduced by the Stanford-Potsdam tradition. Practitioners in the Arab world also seem to shy away from the 'wild side' of Design Thinking in particular, and do not fully appreciate the connection between art-design, and science-engineering. This questions the role of the educational institutions in the region since -according to the findings- they appear to be leading the movement in promoting and developing Design Thinking in the Arab world. Nonetheless, it is notable that people seem to be aware of the positive impact of applying Design Thinking in the region, and its potential to bring meaningful transformation. However, they also seem to be concerned about the current cultural, social, political, and economic challenges that may challenge this transformation. Therefore, they call for more awareness and demand to create Arabic, culturally appropriate programs to respond to the local needs. On another note, the lack of Arabic content and local case studies on Design Thinking were identified by several interviewees and were also confirmed by the participant observation as major challenges that are slowing down the spread of Design Thinking or sometimes hampering capacity building in the region. Other challenges that were revealed by the study are: changing the mindset of people, the lack of dedicated Design Thinking spaces, and the need for clear instructions on how to apply Design Thinking methods and activities. The concept of time and how Arabs deal with it, gender management during trainings, and hierarchy and power dynamics among training participants are also among the identified challenges. Another key finding revealed by the study is the confirmation of التفكير التصميمي as the Arabic term to be most widely adopted in the region to refer to Design Thinking, since four other Arabic terms were found to be associated with Design Thinking. Based on the findings of the study, the thesis concludes by presenting a list of recommendations on how to overcome the mentioned challenges and what factors should be considered when designing and implementing culturally-customized Design Thinking training in the Arab region.}, language = {en} } @book{GerkenUebernickeldePaula2022, author = {Gerken, Stefanie and Uebernickel, Falk and de Paula, Danielly}, title = {Design Thinking: a Global Study on Implementation Practices in Organizations}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-525-5}, doi = {10.25932/publishup-53466}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-534668}, publisher = {Universit{\"a}t Potsdam}, pages = {230}, year = {2022}, abstract = {These days design thinking is no longer a "new approach". Among practitioners, as well as academics, interest in the topic has gathered pace over the last two decades. However, opinions are divided over the longevity of the phenomenon: whether design thinking is merely "old wine in new bottles," a passing trend, or still evolving as it is being spread to an increasing number of organizations and industries. Despite its growing relevance and the diffusion of design thinking, knowledge on the actual status quo in organizations remains scarce. With a new study, the research team of Prof. Uebernickel and Stefanie Gerken investigates temporal developments and changes in design thinking practices in organizations over the past six years comparing the results of the 2015 "Parts without a whole" study with current practices and future developments. Companies of all sizes and from different parts of the world participated in the survey. The findings from qualitative interviews with experts, i.e., people who have years of knowledge with design thinking, were cross-checked with the results from an exploratory analysis of the survey data. This analysis uncovers significant variances and similarities in how design thinking is interpreted and applied in businesses.}, language = {en} } @phdthesis{Santuber2023, author = {Santuber, Joaquin}, title = {Designing for digital justice}, doi = {10.25932/publishup-60417}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-604178}, school = {Universit{\"a}t Potsdam}, pages = {xviii, 183}, year = {2023}, abstract = {At the beginning of 2020, with COVID-19, courts of justice worldwide had to move online to continue providing judicial service. Digital technologies materialized the court practices in ways unthinkable shortly before the pandemic creating resonances with judicial and legal regulation, as well as frictions. A better understanding of the dynamics at play in the digitalization of courts is paramount for designing justice systems that serve their users better, ensure fair and timely dispute resolutions, and foster access to justice. Building on three major bodies of literature —e-justice, digitalization and organization studies, and design research— Designing for Digital Justice takes a nuanced approach to account for human and more-than-human agencies. Using a qualitative approach, I have studied in depth the digitalization of Chilean courts during the pandemic, specifically between April 2020 and September 2022. Leveraging a comprehensive source of primary and secondary data, I traced back the genealogy of the novel materializations of courts' practices structured by the possibilities offered by digital technologies. In five (5) cases studies, I show in detail how the courts got to 1) work remotely, 2) host hearings via videoconference, 3) engage with users via social media (i.e., Facebook and Chat Messenger), 4) broadcast a show with judges answering questions from users via Facebook Live, and 5) record, stream, and upload judicial hearings to YouTube to fulfil the publicity requirement of criminal hearings. The digitalization of courts during the pandemic is characterized by a suspended normativity, which makes innovation possible yet presents risks. While digital technologies enabled the judiciary to provide services continuously, they also created the risk of displacing traditional judicial and legal regulation. Contributing to liminal innovation and digitalization research, Designing for Digital Justice theorizes four phases: 1) the pre-digitalization phase resulting in the development of regulation, 2) the hotspot of digitalization resulting in the extension of regulation, 3) the digital innovation redeveloping regulation (moving to a new, preliminary phase), and 4) the permanence of temporal practices displacing regulation. Contributing to design research Designing for Digital Justice provides new possibilities for innovation in the courts, focusing at different levels to better address tensions generated by digitalization. Fellow researchers will find in these pages a sound theoretical advancement at the intersection of digitalization and justice with novel methodological references. Practitioners will benefit from the actionable governance framework Designing for Digital Justice Model, which provides three fields of possibilities for action to design better justice systems. Only by taking into account digital, legal, and social factors can we design better systems that promote access to justice, the rule of law, and, ultimately social peace.}, language = {en} } @misc{KoetzingLagodzinskiLengleretal.2018, author = {K{\"o}tzing, Timo and Lagodzinski, Gregor J. A. and Lengler, Johannes and Melnichenko, Anna}, title = {Destructiveness of Lexicographic Parsimony Pressure and Alleviation by a Concatenation Crossover in Genetic Programming}, series = {Parallel Problem Solving from Nature - PPSN XV}, volume = {11102}, journal = {Parallel Problem Solving from Nature - PPSN XV}, publisher = {Springer}, address = {Cham}, isbn = {978-3-319-99259-4}, issn = {0302-9743}, doi = {10.1007/978-3-319-99259-4_4}, pages = {42 -- 54}, year = {2018}, abstract = {For theoretical analyses there are two specifics distinguishing GP from many other areas of evolutionary computation. First, the variable size representations, in particular yielding a possible bloat (i.e. the growth of individuals with redundant parts). Second, the role and realization of crossover, which is particularly central in GP due to the tree-based representation. Whereas some theoretical work on GP has studied the effects of bloat, crossover had a surprisingly little share in this work. We analyze a simple crossover operator in combination with local search, where a preference for small solutions minimizes bloat (lexicographic parsimony pressure); the resulting algorithm is denoted Concatenation Crossover GP. For this purpose three variants of the wellstudied Majority test function with large plateaus are considered. We show that the Concatenation Crossover GP can efficiently optimize these test functions, while local search cannot be efficient for all three variants independent of employing bloat control.}, language = {en} }