@phdthesis{Najafi2023, author = {Najafi, Pejman}, title = {Leveraging data science \& engineering for advanced security operations}, doi = {10.25932/publishup-61225}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-612257}, school = {Universit{\"a}t Potsdam}, pages = {xix, 180}, year = {2023}, abstract = {The Security Operations Center (SOC) represents a specialized unit responsible for managing security within enterprises. To aid in its responsibilities, the SOC relies heavily on a Security Information and Event Management (SIEM) system that functions as a centralized repository for all security-related data, providing a comprehensive view of the organization's security posture. Due to the ability to offer such insights, SIEMS are considered indispensable tools facilitating SOC functions, such as monitoring, threat detection, and incident response. Despite advancements in big data architectures and analytics, most SIEMs fall short of keeping pace. Architecturally, they function merely as log search engines, lacking the support for distributed large-scale analytics. Analytically, they rely on rule-based correlation, neglecting the adoption of more advanced data science and machine learning techniques. This thesis first proposes a blueprint for next-generation SIEM systems that emphasize distributed processing and multi-layered storage to enable data mining at a big data scale. Next, with the architectural support, it introduces two data mining approaches for advanced threat detection as part of SOC operations. First, a novel graph mining technique that formulates threat detection within the SIEM system as a large-scale graph mining and inference problem, built on the principles of guilt-by-association and exempt-by-reputation. The approach entails the construction of a Heterogeneous Information Network (HIN) that models shared characteristics and associations among entities extracted from SIEM-related events/logs. Thereon, a novel graph-based inference algorithm is used to infer a node's maliciousness score based on its associations with other entities in the HIN. Second, an innovative outlier detection technique that imitates a SOC analyst's reasoning process to find anomalies/outliers. The approach emphasizes explainability and simplicity, achieved by combining the output of simple context-aware univariate submodels that calculate an outlier score for each entry. Both approaches were tested in academic and real-world settings, demonstrating high performance when compared to other algorithms as well as practicality alongside a large enterprise's SIEM system. This thesis establishes the foundation for next-generation SIEM systems that can enhance today's SOCs and facilitate the transition from human-centric to data-driven security operations.}, language = {en} } @article{Perscheid2021, author = {Perscheid, Cindy}, title = {Integrative biomarker detection on high-dimensional gene expression data sets}, series = {Briefings in bioinformatics}, volume = {22}, journal = {Briefings in bioinformatics}, number = {3}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1467-5463}, doi = {10.1093/bib/bbaa151}, pages = {18}, year = {2021}, abstract = {Gene expression data provide the expression levels of tens of thousands of genes from several hundred samples. These data are analyzed to detect biomarkers that can be of prognostic or diagnostic use. Traditionally, biomarker detection for gene expression data is the task of gene selection. The vast number of genes is reduced to a few relevant ones that achieve the best performance for the respective use case. Traditional approaches select genes based on their statistical significance in the data set. This results in issues of robustness, redundancy and true biological relevance of the selected genes. Integrative analyses typically address these shortcomings by integrating multiple data artifacts from the same objects, e.g. gene expression and methylation data. When only gene expression data are available, integrative analyses instead use curated information on biological processes from public knowledge bases. With knowledge bases providing an ever-increasing amount of curated biological knowledge, such prior knowledge approaches become more powerful. This paper provides a thorough overview on the status quo of biomarker detection on gene expression data with prior biological knowledge. We discuss current shortcomings of traditional approaches, review recent external knowledge bases, provide a classification and qualitative comparison of existing prior knowledge approaches and discuss open challenges for this kind of gene selection.}, 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} } @article{LosterKoumarelasNaumann2021, author = {Loster, Michael and Koumarelas, Ioannis and Naumann, Felix}, title = {Knowledge transfer for entity resolution with siamese neural networks}, series = {ACM journal of data and information quality}, volume = {13}, journal = {ACM journal of data and information quality}, number = {1}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {1936-1955}, doi = {10.1145/3410157}, pages = {25}, year = {2021}, abstract = {The integration of multiple data sources is a common problem in a large variety of applications. Traditionally, handcrafted similarity measures are used to discover, merge, and integrate multiple representations of the same entity-duplicates-into a large homogeneous collection of data. Often, these similarity measures do not cope well with the heterogeneity of the underlying dataset. In addition, domain experts are needed to manually design and configure such measures, which is both time-consuming and requires extensive domain expertise.
We propose a deep Siamese neural network, capable of learning a similarity measure that is tailored to the characteristics of a particular dataset. With the properties of deep learning methods, we are able to eliminate the manual feature engineering process and thus considerably reduce the effort required for model construction. In addition, we show that it is possible to transfer knowledge acquired during the deduplication of one dataset to another, and thus significantly reduce the amount of data required to train a similarity measure. We evaluated our method on multiple datasets and compare our approach to state-of-the-art deduplication methods. Our approach outperforms competitors by up to +26 percent F-measure, depending on task and dataset. In addition, we show that knowledge transfer is not only feasible, but in our experiments led to an improvement in F-measure of up to +4.7 percent.}, language = {en} } @phdthesis{Baier2015, author = {Baier, Thomas}, title = {Matching events and activities}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-84548}, school = {Universit{\"a}t Potsdam}, pages = {xxii, 213}, year = {2015}, abstract = {Nowadays, business processes are increasingly supported by IT services that produce massive amounts of event data during process execution. Aiming at a better process understanding and improvement, this event data can be used to analyze processes using process mining techniques. Process models can be automatically discovered and the execution can be checked for conformance to specified behavior. Moreover, existing process models can be enhanced and annotated with valuable information, for example for performance analysis. While the maturity of process mining algorithms is increasing and more tools are entering the market, process mining projects still face the problem of different levels of abstraction when comparing events with modeled business activities. Mapping the recorded events to activities of a given process model is essential for conformance checking, annotation and understanding of process discovery results. Current approaches try to abstract from events in an automated way that does not capture the required domain knowledge to fit business activities. Such techniques can be a good way to quickly reduce complexity in process discovery. Yet, they fail to enable techniques like conformance checking or model annotation, and potentially create misleading process discovery results by not using the known business terminology. In this thesis, we develop approaches that abstract an event log to the same level that is needed by the business. Typically, this abstraction level is defined by a given process model. Thus, the goal of this thesis is to match events from an event log to activities in a given process model. To accomplish this goal, behavioral and linguistic aspects of process models and event logs as well as domain knowledge captured in existing process documentation are taken into account to build semiautomatic matching approaches. The approaches establish a pre--processing for every available process mining technique that produces or annotates a process model, thereby reducing the manual effort for process analysts. While each of the presented approaches can be used in isolation, we also introduce a general framework for the integration of different matching approaches. The approaches have been evaluated in case studies with industry and using a large industry process model collection and simulated event logs. The evaluation demonstrates the effectiveness and efficiency of the approaches and their robustness towards nonconforming execution logs.}, language = {en} } @book{HerbstMaschlerNiephausetal.2015, author = {Herbst, Eva-Maria and Maschler, Fabian and Niephaus, Fabio and Reimann, Max and Steier, Julia and Felgentreff, Tim and Lincke, Jens and Taeumel, Marcel and Hirschfeld, Robert and Witt, Carsten}, title = {ecoControl}, number = {93}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-318-3}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-72147}, publisher = {Universit{\"a}t Potsdam}, pages = {viii, 142}, year = {2015}, abstract = {Eine dezentrale Energieversorgung ist ein erster Schritt in Richtung Energiewende. Dabei werden auch in Mehrfamilienh{\"a}usern vermehrt verschiedene Strom- und W{\"a}rmeerzeuger eingesetzt. Besonders in Deutschland kommen in diesem Zusammenhang Blockheizkraftwerke immer h{\"a}ufiger zum Einsatz, weil sie Gas sehr effizient in Strom und W{\"a}rme umwandeln k{\"o}nnen. Außerdem erm{\"o}glichen sie, im Zusammenspiel mit anderen Energiesystemen wie beispielsweise Photovoltaik-Anlagen, eine kontinuierliche und dezentrale Energieversorgung. Bei dem Betrieb von unterschiedlichen Energiesystemen ist es w{\"u}nschenswert, dass die Systeme aufeinander abgestimmt arbeiten. Allerdings ist es bisher schwierig, heterogene Energiesysteme effizient miteinander zu betreiben. Dadurch bleiben Einsparungspotentiale ungenutzt. Eine zentrale Steuerung kann deshalb die Effizienz des Gesamtsystems verbessern. Mit ecoControl stellen wir einen erweiterbaren Prototypen vor, der die Kooperation von Energiesystemen optimiert und Umweltfaktoren miteinbezieht. Dazu stellt die Software eine einheitliche Bedienungsoberfl{\"a}che zur Konfiguration aller Systeme zur Verf{\"u}gung. Außerdem bietet sie die M{\"o}glichkeit, Optimierungsalgorithmen mit Hilfe einer Programmierschnittstelle zu entwickeln, zu testen und auszuf{\"u}hren. Innerhalb solcher Algorithmen k{\"o}nnen von ecoControl bereitgestellte Vorhersagen genutzt werden. Diese Vorhersagen basieren auf dem individuellen Verhalten von jedem Energiesystem, Wettervorhersagen und auf Prognosen des Energieverbrauchs. Mithilfe einer Simulation k{\"o}nnen Techniker unterschiedliche Konfigurationen und Optimierungen sofort ausprobieren, ohne diese {\"u}ber einen langen Zeitraum an realen Ger{\"a}ten testen zu m{\"u}ssen. ecoControl hilft dar{\"u}ber hinaus auch Hausverwaltungen und Vermietern bei der Verwaltung und Analyse der Energiekosten. Wir haben anhand von Fallbeispielen gezeigt, dass Optimierungsalgorithmen, welche die Nutzung von W{\"a}rmespeichern verbessern, die Effizienz des Gesamtsystems erheblich verbessern k{\"o}nnen. Schließlich kommen wir zu dem Schluss, dass ecoControl in einem n{\"a}chsten Schritt unter echten Bedingungen getestet werden muss, sobald eine geeignete Hardwarekomponente verf{\"u}gbar ist. {\"U}ber diese Schnittstelle werden die Messwerte an ecoControl gesendet und Steuersignale an die Ger{\"a}te weitergeleitet.}, language = {de} } @article{DittmarBuchholzKuehn2016, author = {Dittmar, Anke and Buchholz, Gregor and K{\"u}hn, Mathias}, title = {Eine Studie zum kollaborativen Modellieren in der Softwaretechnik-Ausbildung}, series = {Commentarii informaticae didacticae (CID)}, journal = {Commentarii informaticae didacticae (CID)}, number = {10}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-376-3}, issn = {1868-0844}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-94806}, pages = {41 -- 53}, year = {2016}, abstract = {Die Vermittlung von Modellierungsf{\"a}higkeiten in der Softwaretechnik-Ausbildung konzentriert sich meist auf Modellierungskonzepte, Notationen und Entwicklungswerkzeuge. Die Betrachtung der Modellierungsaktivit{\"a}ten, etwa die Entwicklung und Gegen{\"u}berstellung alternativer Modellvorschl{\"a}ge, steht weniger im Vordergrund. Die vorliegende Studie untersucht zwei Formen des kollaborativen Modellierens am Tabletop in Bezug auf ihren Einfluss auf die Modellierungsaktivit{\"a}ten in kleinen Gruppen. Die Ergebnisse zeigen, dass sowohl selbstorganisierte als auch moderierte Modellierungssitzungen das Entwickeln eines gemeinsamen Modellverst{\"a}ndnisses f{\"o}rdern. In moderierten Sitzungen wurden zudem mehr alternative L{\"o}sungsideen entwickelt und in st{\"a}rkerem Maße diskutiert.}, language = {de} } @phdthesis{AlSaffar2016, author = {Al-Saffar, Loay Talib Ahmed}, title = {Analysing prerequisites, expectations, apprehensions, and attitudes of university students studying Computer science}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-98437}, school = {Universit{\"a}t Potsdam}, pages = {xii, 131}, year = {2016}, abstract = {The main objective of this dissertation is to analyse prerequisites, expectations, apprehensions, and attitudes of students studying computer science, who are willing to gain a bachelor degree. The research will also investigate in the students' learning style according to the Felder-Silverman model. These investigations fall in the attempt to make an impact on reducing the "dropout"/shrinkage rate among students, and to suggest a better learning environment. The first investigation starts with a survey that has been made at the computer science department at the University of Baghdad to investigate the attitudes of computer science students in an environment dominated by women, showing the differences in attitudes between male and female students in different study years. Students are accepted to university studies via a centrally controlled admission procedure depending mainly on their final score at school. This leads to a high percentage of students studying subjects they do not want. Our analysis shows that 75\% of the female students do not regret studying computer science although it was not their first choice. And according to statistics over previous years, women manage to succeed in their study and often graduate on top of their class. We finish with a comparison of attitudes between the freshman students of two different cultures and two different university enrolment procedures (University of Baghdad, in Iraq, and the University of Potsdam, in Germany) both with opposite gender majority. The second step of investigation took place at the department of computer science at the University of Potsdam in Germany and analyzes the learning styles of students studying the three major fields of study offered by the department (computer science, business informatics, and computer science teaching). Investigating the differences in learning styles between the students of those study fields who usually take some joint courses is important to be aware of which changes are necessary to be adopted in the teaching methods to address those different students. It was a two stage study using two questionnaires; the main one is based on the Index of Learning Styles Questionnaire of B. A. Solomon and R. M. Felder, and the second questionnaire was an investigation on the students' attitudes towards the findings of their personal first questionnaire. Our analysis shows differences in the preferences of learning style between male and female students of the different study fields, as well as differences between students with the different specialties (computer science, business informatics, and computer science teaching). The third investigation looks closely into the difficulties, issues, apprehensions and expectations of freshman students studying computer science. The study took place at the computer science department at the University of Potsdam with a volunteer sample of students. The goal is to determine and discuss the difficulties and issues that they are facing in their study that may lead them to think in dropping-out, changing the study field, or changing the university. The research continued with the same sample of students (with business informatics students being the majority) through more than three semesters. Difficulties and issues during the study were documented, as well as students' attitudes, apprehensions, and expectations. Some of the professors and lecturers opinions and solutions to some students' problems were also documented. Many participants had apprehensions and difficulties, especially towards informatics subjects. Some business informatics participants began to think of changing the university, in particular when they reached their third semester, others thought about changing their field of study. Till the end of this research, most of the participants continued in their studies (the study they have started with or the new study they have changed to) without leaving the higher education system.}, language = {en} } @book{NeuhausPolzeChowdhuryy2011, author = {Neuhaus, Christian and Polze, Andreas and Chowdhuryy, Mohammad M. R.}, title = {Survey on healthcare IT systems : standards, regulations and security}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-128-8}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-51463}, publisher = {Universit{\"a}t Potsdam}, pages = {53}, year = {2011}, abstract = {IT systems for healthcare are a complex and exciting field. One the one hand, there is a vast number of improvements and work alleviations that computers can bring to everyday healthcare. Some ways of treatment, diagnoses and organisational tasks were even made possible by computer usage in the first place. On the other hand, there are many factors that encumber computer usage and make development of IT systems for healthcare a challenging, sometimes even frustrating task. These factors are not solely technology-related, but just as well social or economical conditions. This report describes some of the idiosyncrasies of IT systems in the healthcare domain, with a special focus on legal regulations, standards and security.}, language = {en} } @book{AbedjanNaumann2011, author = {Abedjan, Ziawasch and Naumann, Felix}, title = {Advancing the discovery of unique column combinations}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-148-6}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-53564}, publisher = {Universit{\"a}t Potsdam}, pages = {25}, year = {2011}, abstract = {Unique column combinations of a relational database table are sets of columns that contain only unique values. Discovering such combinations is a fundamental research problem and has many different data management and knowledge discovery applications. Existing discovery algorithms are either brute force or have a high memory load and can thus be applied only to small datasets or samples. In this paper, the wellknown GORDIAN algorithm and "Apriori-based" algorithms are compared and analyzed for further optimization. We greatly improve the Apriori algorithms through efficient candidate generation and statistics-based pruning methods. A hybrid solution HCAGORDIAN combines the advantages of GORDIAN and our new algorithm HCA, and it significantly outperforms all previous work in many situations.}, language = {en} } @article{SchlierkampThurner2015, author = {Schlierkamp, Kathrin and Thurner, Veronika}, title = {Was will ich eigentlich hier?}, series = {HDI 2014 : Gestalten von {\"U}berg{\"a}ngen}, volume = {2015}, journal = {HDI 2014 : Gestalten von {\"U}berg{\"a}ngen}, number = {9}, editor = {Schubert, Sigrid and Schwill, Andreas}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-84748}, pages = {179 -- 187}, year = {2015}, abstract = {Die Wahl des richtigen Studienfaches und die daran anschließende Studieneingangsphase sind oft entscheidend f{\"u}r den erfolgreichen Verlauf eines Studiums. Eine große Herausforderung besteht dabei darin, bereits in den ersten Wochen des Studiums bestehende Defizite in vermeintlich einfachen Schl{\"u}sselkompetenzen zu erkennen und diese so bald wie m{\"o}glich zu beheben. Eine zweite, nicht minder wichtige Herausforderung ist es, m{\"o}glichst fr{\"u}hzeitig f{\"u}r jeden einzelnen Studierenden zu erkennen, ob er bzw. sie das individuell richtige Studienfach gew{\"a}hlt hat, das den jeweiligen pers{\"o}nlichen Neigungen, Interessen und F{\"a}higkeiten entspricht und zur Verwirklichung der eigenen Lebensziele beitr{\"a}gt. Denn nur dann sind Studierende ausreichend stark und dauerhaft intrinsisch motiviert, um ein anspruchsvolles, komplexes Studium erfolgreich durchzuziehen. In diesem Beitrag fokussieren wir eine Maßnahme, die die Studierenden an einen Prozess zur systematischen Reflexion des eigenen Lernprozesses und der eigenen Ziele heranf{\"u}hrt und beides in Relation setzt.}, language = {de} } @article{VossebergCzernikErbetal.2015, author = {Vosseberg, Karin and Czernik, Sofie and Erb, Ulrike and Vielhaber, Michael}, title = {Projektorientierte Studieneingangsphase}, series = {HDI 2014 : Gestalten von {\"U}berg{\"a}ngen}, volume = {2015}, journal = {HDI 2014 : Gestalten von {\"U}berg{\"a}ngen}, number = {9}, editor = {Schubert, Sigrid and Schwill, Andreas}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-84730}, pages = {169 -- 177}, year = {2015}, abstract = {Ziel einer neuen Studieneingangsphase ist, den Studierenden bis zum Ende des ersten Semesters ein vielf{\"a}ltiges Berufsbild der Informatik und Wirtschaftsinformatik mit dem breiten Aufgabenspektrum aufzubl{\"a}ttern und damit die Zusammenh{\"a}nge zwischen den einzelnen Modulen des Curriculums zu verdeutlichen. Die Studierenden sollen in die Lage versetzt werden, sehr eigenst{\"a}ndig die Planung und Gestaltung ihres Studiums in die Hand zu nehmen.}, language = {de} } @article{Broeker2015, author = {Br{\"o}ker, Kathrin}, title = {Unterst{\"u}tzung Informatik-Studierender durch ein Lernzentrum}, series = {HDI 2014 : Gestalten von {\"U}berg{\"a}ngen}, volume = {2015}, journal = {HDI 2014 : Gestalten von {\"U}berg{\"a}ngen}, number = {9}, editor = {Schubert, Sigrid and Schwill, Andreas}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-84754}, pages = {189 -- 197}, year = {2015}, abstract = {In diesem Papier wird das Konzept eines Lernzentrums f{\"u}r die Informatik (LZI) an der Universit{\"a}t Paderborn vorgestellt. Ausgehend von den fachspezifischen Schwierigkeiten der Informatik Studierenden werden die Angebote des LZIs erl{\"a}utert, die sich {\"u}ber die vier Bereiche Individuelle Beratung und Betreuung, „Offener Lernraum", Workshops und Lehrveranstaltungen sowie Forschung erstrecken. Eine erste Evaluation mittels Feedbackb{\"o}gen zeigt, dass das Angebot bei den Studierenden positiv aufgenommen wird. Zuk{\"u}nftig soll das Angebot des LZIs weiter ausgebaut und verbessert werden. Ausgangsbasis dazu sind weitere Studien.}, language = {de} } @phdthesis{Prasse2016, author = {Prasse, Paul}, title = {Pattern recognition for computer security}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-100251}, school = {Universit{\"a}t Potsdam}, pages = {VI, 75}, year = {2016}, abstract = {Computer Security deals with the detection and mitigation of threats to computer networks, data, and computing hardware. This thesis addresses the following two computer security problems: email spam campaign and malware detection. Email spam campaigns can easily be generated using popular dissemination tools by specifying simple grammars that serve as message templates. A grammar is disseminated to nodes of a bot net, the nodes create messages by instantiating the grammar at random. Email spam campaigns can encompass huge data volumes and therefore pose a threat to the stability of the infrastructure of email service providers that have to store them. Malware -software that serves a malicious purpose- is affecting web servers, client computers via active content, and client computers through executable files. Without the help of malware detection systems it would be easy for malware creators to collect sensitive information or to infiltrate computers. The detection of threats -such as email-spam messages, phishing messages, or malware- is an adversarial and therefore intrinsically difficult problem. Threats vary greatly and evolve over time. The detection of threats based on manually-designed rules is therefore difficult and requires a constant engineering effort. Machine-learning is a research area that revolves around the analysis of data and the discovery of patterns that describe aspects of the data. Discriminative learning methods extract prediction models from data that are optimized to predict a target attribute as accurately as possible. Machine-learning methods hold the promise of automatically identifying patterns that robustly and accurately detect threats. This thesis focuses on the design and analysis of discriminative learning methods for the two computer-security problems under investigation: email-campaign and malware detection. The first part of this thesis addresses email-campaign detection. We focus on regular expressions as a syntactic framework, because regular expressions are intuitively comprehensible by security engineers and administrators, and they can be applied as a detection mechanism in an extremely efficient manner. In this setting, a prediction model is provided with exemplary messages from an email-spam campaign. The prediction model has to generate a regular expression that reveals the syntactic pattern that underlies the entire campaign, and that a security engineers finds comprehensible and feels confident enough to use the expression to blacklist further messages at the email server. We model this problem as two-stage learning problem with structured input and output spaces which can be solved using standard cutting plane methods. Therefore we develop an appropriate loss function, and derive a decoder for the resulting optimization problem. The second part of this thesis deals with the problem of predicting whether a given JavaScript or PHP file is malicious or benign. Recent malware analysis techniques use static or dynamic features, or both. In fully dynamic analysis, the software or script is executed and observed for malicious behavior in a sandbox environment. By contrast, static analysis is based on features that can be extracted directly from the program file. In order to bypass static detection mechanisms, code obfuscation techniques are used to spread a malicious program file in many different syntactic variants. Deobfuscating the code before applying a static classifier can be subjected to mostly static code analysis and can overcome the problem of obfuscated malicious code, but on the other hand increases the computational costs of malware detection by an order of magnitude. In this thesis we present a cascaded architecture in which a classifier first performs a static analysis of the original code and -based on the outcome of this first classification step- the code may be deobfuscated and classified again. We explore several types of features including token \$n\$-grams, orthogonal sparse bigrams, subroutine-hashings, and syntax-tree features and study the robustness of detection methods and feature types against the evolution of malware over time. The developed tool scans very large file collections quickly and accurately. Each model is evaluated on real-world data and compared to reference methods. Our approach of inferring regular expressions to filter emails belonging to an email spam campaigns leads to models with a high true-positive rate at a very low false-positive rate that is an order of magnitude lower than that of a commercial content-based filter. Our presented system -REx-SVMshort- is being used by a commercial email service provider and complements content-based and IP-address based filtering. Our cascaded malware detection system is evaluated on a high-quality data set of almost 400,000 conspicuous PHP files and a collection of more than 1,00,000 JavaScript files. From our case study we can conclude that our system can quickly and accurately process large data collections at a low false-positive rate.}, language = {en} } @phdthesis{Abedjan2014, author = {Abedjan, Ziawasch}, title = {Improving RDF data with data mining}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-71334}, school = {Universit{\"a}t Potsdam}, year = {2014}, abstract = {Linked Open Data (LOD) comprises very many and often large public data sets and knowledge bases. Those datasets are mostly presented in the RDF triple structure of subject, predicate, and object, where each triple represents a statement or fact. Unfortunately, the heterogeneity of available open data requires significant integration steps before it can be used in applications. Meta information, such as ontological definitions and exact range definitions of predicates, are desirable and ideally provided by an ontology. However in the context of LOD, ontologies are often incomplete or simply not available. Thus, it is useful to automatically generate meta information, such as ontological dependencies, range definitions, and topical classifications. Association rule mining, which was originally applied for sales analysis on transactional databases, is a promising and novel technique to explore such data. We designed an adaptation of this technique for min-ing Rdf data and introduce the concept of "mining configurations", which allows us to mine RDF data sets in various ways. Different configurations enable us to identify schema and value dependencies that in combination result in interesting use cases. To this end, we present rule-based approaches for auto-completion, data enrichment, ontology improvement, and query relaxation. Auto-completion remedies the problem of inconsistent ontology usage, providing an editing user with a sorted list of commonly used predicates. A combination of different configurations step extends this approach to create completely new facts for a knowledge base. We present two approaches for fact generation, a user-based approach where a user selects the entity to be amended with new facts and a data-driven approach where an algorithm discovers entities that have to be amended with missing facts. As knowledge bases constantly grow and evolve, another approach to improve the usage of RDF data is to improve existing ontologies. Here, we present an association rule based approach to reconcile ontology and data. Interlacing different mining configurations, we infer an algorithm to discover synonymously used predicates. Those predicates can be used to expand query results and to support users during query formulation. We provide a wide range of experiments on real world datasets for each use case. The experiments and evaluations show the added value of association rule mining for the integration and usability of RDF data and confirm the appropriateness of our mining configuration methodology.}, language = {en} } @inproceedings{OPUS4-7665, title = {Proceedings of the Second HPI Cloud Symposium "Operating the Cloud" 2014}, number = {94}, editor = {Bosse, Sascha and Elsaid, Mohamed Esam and Feinbube, Frank and M{\"u}ller, Hendrik}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-319-0}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-76654}, pages = {vii, 59}, year = {2015}, abstract = {Every year, the Hasso Plattner Institute (HPI) invites guests from industry and academia to a collaborative scientific workshop on the topic "Operating the Cloud". Our goal is to provide a forum for the exchange of knowledge and experience between industry and academia. Hence, HPI's Future SOC Lab is the adequate environment to host this event which is also supported by BITKOM. On the occasion of this workshop we called for submissions of research papers and practitioners' reports. "Operating the Cloud" aims to be a platform for productive discussions of innovative ideas, visions, and upcoming technologies in the field of cloud operation and administration. In this workshop proceedings the results of the second HPI cloud symposium "Operating the Cloud" 2014 are published. We thank the authors for exciting presentations and insights into their current work and research. Moreover, we look forward to more interesting submissions for the upcoming symposium in 2015.}, language = {en} } @phdthesis{Videla2014, author = {Videla, Santiago}, title = {Reasoning on the response of logical signaling networks with answer set programming}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-71890}, school = {Universit{\"a}t Potsdam}, year = {2014}, abstract = {Deciphering the functioning of biological networks is one of the central tasks in systems biology. In particular, signal transduction networks are crucial for the understanding of the cellular response to external and internal perturbations. Importantly, in order to cope with the complexity of these networks, mathematical and computational modeling is required. We propose a computational modeling framework in order to achieve more robust discoveries in the context of logical signaling networks. More precisely, we focus on modeling the response of logical signaling networks by means of automated reasoning using Answer Set Programming (ASP). ASP provides a declarative language for modeling various knowledge representation and reasoning problems. Moreover, available ASP solvers provide several reasoning modes for assessing the multitude of answer sets. Therefore, leveraging its rich modeling language and its highly efficient solving capacities, we use ASP to address three challenging problems in the context of logical signaling networks: learning of (Boolean) logical networks, experimental design, and identification of intervention strategies. Overall, the contribution of this thesis is three-fold. Firstly, we introduce a mathematical framework for characterizing and reasoning on the response of logical signaling networks. Secondly, we contribute to a growing list of successful applications of ASP in systems biology. Thirdly, we present a software providing a complete pipeline for automated reasoning on the response of logical signaling networks.}, language = {en} } @book{MeyerWeske2014, author = {Meyer, Andreas and Weske, Mathias}, title = {Weak conformance between process models and synchronized object life cycles}, number = {91}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-303-9}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-71722}, publisher = {Universit{\"a}t Potsdam}, pages = {31}, year = {2014}, abstract = {Process models specify behavioral execution constraints between activities as well as between activities and data objects. A data object is characterized by its states and state transitions represented as object life cycle. For process execution, all behavioral execution constraints must be correct. Correctness can be verified via soundness checking which currently only considers control flow information. For data correctness, conformance between a process model and its object life cycles is checked. Current approaches abstract from dependencies between multiple data objects and require fully specified process models although, in real-world process repositories, often underspecified models are found. Coping with these issues, we introduce the concept of synchronized object life cycles and we define a mapping of data constraints of a process model to Petri nets extending an existing mapping. Further, we apply the notion of weak conformance to process models to tell whether each time an activity needs to access a data object in a particular state, it is guaranteed that the data object is in or can reach the expected state. Then, we introduce an algorithm for an integrated verification of control flow correctness and weak data conformance using soundness checking.}, language = {en} } @article{WesselsMetzger2015, author = {Weßels, Doris and Metzger, Christiane}, title = {Die Arbeitswelt im Fokus}, series = {HDI 2014 : Gestalten von {\"U}berg{\"a}ngen}, volume = {2015}, journal = {HDI 2014 : Gestalten von {\"U}berg{\"a}ngen}, number = {9}, editor = {Schwill, Andreas and Schubert, Sigrid}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-80289}, pages = {77 -- 92}, year = {2015}, abstract = {F{\"u}r Bachelor-Studierende der Wirtschaftsinformatik im zweiten Semester an der Fachhochschule Kiel werden im Modul Informationsmanagement neben klassischen didaktischen Ans{\"a}tzen in einer seminaristischen Unterrichtsform so genannte „Aktivbausteine" eingesetzt: Studierende erhalten zum einen die Gelegenheit, sich im Kontakt mit Fach- und F{\"u}hrungskr{\"a}ften aus der Industrie ein konkretes Bild vom Beruf der Wirtschaftsinformatikerin bzw. des Wirtschaftsinformatikers zu machen; zum anderen erarbeiten sie innovative Ans{\"a}tze der Prozessverbesserung aus Sicht der IT oder mit Nutzenpotenzial f{\"u}r die IT und pr{\"a}sentieren ihre Ergebnisse {\"o}ffentlich im Rahmen des Kieler Prozessmanagementforums. Diese Aktivbausteine dienen insbesondere der Berufsfeldorientierung: Durch die Informationen, die die Studierenden {\"u}ber die Anforderungen und T{\"a}tigkeiten von im Beruf stehenden Menschen erhalten, werden sie in die Lage versetzt, fundierte Entscheidungen bzgl. ihrer Studiengestaltung und Berufswahl zu treffen. Im Beitrag wird die Konzeption der Bausteine vorgestellt und deren Grad der Zielerreichung durch aktuelle Evaluationsergebnisse erl{\"a}utert. Zudem wird die motivationale Wirkung der Aktivbausteine anhand der Theorie der Selbstbestimmung von Deci und Ryan [DR1985, DR1993, DR2004] erl{\"a}utert.}, language = {de} } @phdthesis{Haider2013, author = {Haider, Peter}, title = {Prediction with Mixture Models}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-69617}, school = {Universit{\"a}t Potsdam}, year = {2013}, abstract = {Learning a model for the relationship between the attributes and the annotated labels of data examples serves two purposes. Firstly, it enables the prediction of the label for examples without annotation. Secondly, the parameters of the model can provide useful insights into the structure of the data. If the data has an inherent partitioned structure, it is natural to mirror this structure in the model. Such mixture models predict by combining the individual predictions generated by the mixture components which correspond to the partitions in the data. Often the partitioned structure is latent, and has to be inferred when learning the mixture model. Directly evaluating the accuracy of the inferred partition structure is, in many cases, impossible because the ground truth cannot be obtained for comparison. However it can be assessed indirectly by measuring the prediction accuracy of the mixture model that arises from it. This thesis addresses the interplay between the improvement of predictive accuracy by uncovering latent cluster structure in data, and further addresses the validation of the estimated structure by measuring the accuracy of the resulting predictive model. In the application of filtering unsolicited emails, the emails in the training set are latently clustered into advertisement campaigns. Uncovering this latent structure allows filtering of future emails with very low false positive rates. In order to model the cluster structure, a Bayesian clustering model for dependent binary features is developed in this thesis. Knowing the clustering of emails into campaigns can also aid in uncovering which emails have been sent on behalf of the same network of captured hosts, so-called botnets. This association of emails to networks is another layer of latent clustering. Uncovering this latent structure allows service providers to further increase the accuracy of email filtering and to effectively defend against distributed denial-of-service attacks. To this end, a discriminative clustering model is derived in this thesis that is based on the graph of observed emails. The partitionings inferred using this model are evaluated through their capacity to predict the campaigns of new emails. Furthermore, when classifying the content of emails, statistical information about the sending server can be valuable. Learning a model that is able to make use of it requires training data that includes server statistics. In order to also use training data where the server statistics are missing, a model that is a mixture over potentially all substitutions thereof is developed. Another application is to predict the navigation behavior of the users of a website. Here, there is no a priori partitioning of the users into clusters, but to understand different usage scenarios and design different layouts for them, imposing a partitioning is necessary. The presented approach simultaneously optimizes the discriminative as well as the predictive power of the clusters. Each model is evaluated on real-world data and compared to baseline methods. The results show that explicitly modeling the assumptions about the latent cluster structure leads to improved predictions compared to the baselines. It is beneficial to incorporate a small number of hyperparameters that can be tuned to yield the best predictions in cases where the prediction accuracy can not be optimized directly.}, language = {en} } @book{FelgentreffBorningHirschfeld2013, author = {Felgentreff, Tim and Borning, Alan and Hirschfeld, Robert}, title = {Babelsberg : specifying and solving constraints on object behavior}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-265-0}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-67296}, publisher = {Universit{\"a}t Potsdam}, pages = {53}, year = {2013}, abstract = {Constraints allow developers to specify desired properties of systems in a number of domains, and have those properties be maintained automatically. This results in compact, declarative code, avoiding scattered code to check and imperatively re-satisfy invariants. Despite these advantages, constraint programming is not yet widespread, with standard imperative programming still the norm. There is a long history of research on integrating constraint programming with the imperative paradigm. However, this integration typically does not unify the constructs for encapsulation and abstraction from both paradigms. This impedes re-use of modules, as client code written in one paradigm can only use modules written to support that paradigm. Modules require redundant definitions if they are to be used in both paradigms. We present a language - Babelsberg - that unifies the constructs for en- capsulation and abstraction by using only object-oriented method definitions for both declarative and imperative code. Our prototype - Babelsberg/R - is an extension to Ruby, and continues to support Ruby's object-oriented se- mantics. It allows programmers to add constraints to existing Ruby programs in incremental steps by placing them on the results of normal object-oriented message sends. It is implemented by modifying a state-of-the-art Ruby virtual machine. The performance of standard object-oriented code without con- straints is only modestly impacted, with typically less than 10\% overhead compared with the unmodified virtual machine. Furthermore, our architec- ture for adding multiple constraint solvers allows Babelsberg to deal with constraints in a variety of domains. We argue that our approach provides a useful step toward making con- straint solving a generic tool for object-oriented programmers. We also provide example applications, written in our Ruby-based implementation, which use constraints in a variety of application domains, including interactive graphics, circuit simulations, data streaming with both hard and soft constraints on performance, and configuration file Management.}, language = {en} } @book{PufahlMeyerWeske2013, author = {Pufahl, Luise and Meyer, Andreas and Weske, Mathias}, title = {Batch regions : process instance synchronization based on data}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-280-3}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-69081}, publisher = {Universit{\"a}t Potsdam}, pages = {18}, year = {2013}, abstract = {Business process automation improves organizations' efficiency to perform work. In existing business process management systems, process instances run independently from each other. However, synchronizing instances carrying similar characteristics, i.e., sharing the same data, can reduce process execution costs. For example, if an online retailer receives two orders from one customer, there is a chance that they can be packed and shipped together to save shipment costs. In this paper, we use concepts from the database domain and introduce data views to business processes to identify instances which can be synchronized. Based on data views, we introduce the concept of batch regions for a context-aware instance synchronization over a set of connected activities. We also evaluate the concepts introduced in this paper with a case study comparing costs for normal and batch processing.}, language = {de} } @book{GieseBecker2013, author = {Giese, Holger and Becker, Basil}, title = {Modeling and verifying dynamic evolving service-oriented architectures}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-246-9}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-65112}, publisher = {Universit{\"a}t Potsdam}, pages = {97}, year = {2013}, abstract = {The service-oriented architecture supports the dynamic assembly and runtime reconfiguration of complex open IT landscapes by means of runtime binding of service contracts, launching of new components and termination of outdated ones. Furthermore, the evolution of these IT landscapes is not restricted to exchanging components with other ones using the same service contracts, as new services contracts can be added as well. However, current approaches for modeling and verification of service-oriented architectures do not support these important capabilities to their full extend.In this report we present an extension of the current OMG proposal for service modeling with UML - SoaML - which overcomes these limitations. It permits modeling services and their service contracts at different levels of abstraction, provides a formal semantics for all modeling concepts, and enables verifying critical properties. Our compositional and incremental verification approach allows for complex properties including communication parameters and time and covers besides the dynamic binding of service contracts and the replacement of components also the evolution of the systems by means of new service contracts. The modeling as well as verification capabilities of the presented approach are demonstrated by means of a supply chain example and the verification results of a first prototype are shown.}, language = {en} } @book{RoggeSoltiMansvanderAalstetal.2013, author = {Rogge-Solti, Andreas and Mans, Ronny S. and van der Aalst, Wil M. P. and Weske, Mathias}, title = {Repairing event logs using stochastic process models}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-258-2}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-66797}, publisher = {Universit{\"a}t Potsdam}, pages = {19}, year = {2013}, abstract = {Companies strive to improve their business processes in order to remain competitive. Process mining aims to infer meaningful insights from process-related data and attracted the attention of practitioners, tool-vendors, and researchers in recent years. Traditionally, event logs are assumed to describe the as-is situation. But this is not necessarily the case in environments where logging may be compromised due to manual logging. For example, hospital staff may need to manually enter information regarding the patient's treatment. As a result, events or timestamps may be missing or incorrect. In this paper, we make use of process knowledge captured in process models, and provide a method to repair missing events in the logs. This way, we facilitate analysis of incomplete logs. We realize the repair by combining stochastic Petri nets, alignments, and Bayesian networks. We evaluate the results using both synthetic data and real event data from a Dutch hospital.}, language = {en} } @book{OPUS4-6813, title = {Cloud security mechanisms}, number = {87}, editor = {Neuhaus, Christian and Polze, Andreas}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-281-0}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-68168}, publisher = {Universit{\"a}t Potsdam}, pages = {78}, year = {2014}, abstract = {Cloud computing has brought great benefits in cost and flexibility for provisioning services. The greatest challenge of cloud computing remains however the question of security. The current standard tools in access control mechanisms and cryptography can only partly solve the security challenges of cloud infrastructures. In the recent years of research in security and cryptography, novel mechanisms, protocols and algorithms have emerged that offer new ways to create secure services atop cloud infrastructures. This report provides introductions to a selection of security mechanisms that were part of the "Cloud Security Mechanisms" seminar in summer term 2013 at HPI.}, language = {en} } @phdthesis{Kunze2013, author = {Kunze, Matthias}, title = {Searching business process models by example}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-68844}, school = {Universit{\"a}t Potsdam}, year = {2013}, abstract = {Business processes are fundamental to the operations of a company. Each product manufactured and every service provided is the result of a series of actions that constitute a business process. Business process management is an organizational principle that makes the processes of a company explicit and offers capabilities to implement procedures, control their execution, analyze their performance, and improve them. Therefore, business processes are documented as process models that capture these actions and their execution ordering, and make them accessible to stakeholders. As these models are an essential knowledge asset, they need to be managed effectively. In particular, the discovery and reuse of existing knowledge becomes challenging in the light of companies maintaining hundreds and thousands of process models. In practice, searching process models has been solved only superficially by means of free-text search of process names and their descriptions. Scientific contributions are limited in their scope, as they either present measures for process similarity or elaborate on query languages to search for particular aspects. However, they fall short in addressing efficient search, the presentation of search results, and the support to reuse discovered models. This thesis presents a novel search method, where a query is expressed by an exemplary business process model that describes the behavior of a possible answer. This method builds upon a formal framework that captures and compares the behavior of process models by the execution ordering of actions. The framework contributes a conceptual notion of behavioral distance that quantifies commonalities and differences of a pair of process models, and enables process model search. Based on behavioral distances, a set of measures is proposed that evaluate the quality of a particular search result to guide the user in assessing the returned matches. A projection of behavioral aspects to a process model enables highlighting relevant fragments that led to a match and facilitates its reuse. The thesis further elaborates on two search techniques that provide concrete behavioral distance functions as an instantiation of the formal framework. Querying enables search with a notion of behavioral inclusion with regard to the query. In contrast, similarity search obtains process models that are similar to a query, even if the query is not precisely matched. For both techniques, indexes are presented that enable efficient search. Methods to evaluate the quality and performance of process model search are introduced and applied to the techniques of this thesis. They show good results with regard to human assessment and scalability in a practical setting.}, language = {en} } @book{PapeTrefferHirschfeldetal.2013, author = {Pape, Tobias and Treffer, Arian and Hirschfeld, Robert and Haupt, Michael}, title = {Extending a Java Virtual Machine to Dynamic Object-oriented Languages}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-266-7}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-67438}, publisher = {Universit{\"a}t Potsdam}, pages = {163}, year = {2013}, abstract = {There are two common approaches to implement a virtual machine (VM) for a dynamic object-oriented language. On the one hand, it can be implemented in a C-like language for best performance and maximum control over the resulting executable. On the other hand, it can be implemented in a language such as Java that allows for higher-level abstractions. These abstractions, such as proper object-oriented modularization, automatic memory management, or interfaces, are missing in C-like languages but they can simplify the implementation of prevalent but complex concepts in VMs, such as garbage collectors (GCs) or just-in-time compilers (JITs). Yet, the implementation of a dynamic object-oriented language in Java eventually results in two VMs on top of each other (double stack), which impedes performance. For statically typed languages, the Maxine VM solves this problem; it is written in Java but can be executed without a Java virtual machine (JVM). However, it is currently not possible to execute dynamic object-oriented languages in Maxine. This work presents an approach to bringing object models and execution models of dynamic object-oriented languages to the Maxine VM and the application of this approach to Squeak/Smalltalk. The representation of objects in and the execution of dynamic object-oriented languages pose certain challenges to the Maxine VM that lacks certain variation points necessary to enable an effortless and straightforward implementation of dynamic object-oriented languages' execution models. The implementation of Squeak/Smalltalk in Maxine as a feasibility study is to unveil such missing variation points.}, language = {en} } @misc{KaminskiSchaubSiegeletal.2013, author = {Kaminski, Roland and Schaub, Torsten H. and Siegel, Anne and Videla, Santiago}, title = {Minimal intervention strategies in logical signaling networks with ASP}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch Naturwissenschaftliche Reihe}, number = {4-5}, issn = {1866-8372}, doi = {10.25932/publishup-41570}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-415704}, pages = {675 -- 690}, year = {2013}, abstract = {Proposing relevant perturbations to biological signaling networks is central to many problems in biology and medicine because it allows for enabling or disabling certain biological outcomes. In contrast to quantitative methods that permit fine-grained (kinetic) analysis, qualitative approaches allow for addressing large-scale networks. This is accomplished by more abstract representations such as logical networks. We elaborate upon such a qualitative approach aiming at the computation of minimal interventions in logical signaling networks relying on Kleene's three-valued logic and fixpoint semantics. We address this problem within answer set programming and show that it greatly outperforms previous work using dedicated algorithms.}, language = {en} } @article{KeverpuetzKueppers2018, author = {Keverp{\"u}tz, Claudia and K{\"u}ppers, Bastian}, title = {Konsistente Lehr-Lern-Prozesse in der dualen IT-Ausbildung}, series = {Commentarii informaticae didacticae}, journal = {Commentarii informaticae didacticae}, number = {12}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-416341}, pages = {91 -- 100}, year = {2018}, abstract = {In der dualen IT-Ausbildung als Verbindung von beruflicher und akademischer Qualifikation werden die berufstypischen Werkzeuge, wie z. B. Laptops, ebenso in den Lehr-Lern-Prozessen der akademischen Unterrichtseinheiten eingesetzt. Im Pr{\"u}fungswesen wird oft auf klassische Papierklausuren zur{\"u}ckgegriffen. Unterrichtseinheiten mit hohem Blended-Learning-Anteil ohne E-Pr{\"u}fung werden dabei als „nicht konsistent" wahrgenommen. In diesem Artikel wird eine empirische Studie dargelegt, die untersucht, welche Einfl{\"u}sse aus der pers{\"o}nlichen Lernbiografie bei den Lehrenden in einer dualen IT-Ausbildung dazu f{\"u}hren k{\"o}nnen, die M{\"o}glichkeiten eines E-Assessments als summative Modulpr{\"u}fung anzunehmen oder abzulehnen. Beispielhaft wurden in der dargelegten Studie Interviews mit Dozenten gef{\"u}hrt und diese hinsichtlich der Verbindung zwischen Lernbiografie, Gestaltung der Didaktik der Lehr-Lern-Prozesse, Zufriedenheit und Ver{\"a}nderungsbereitschaft untersucht.}, language = {de} } @phdthesis{Klimke2018, author = {Klimke, Jan}, title = {Web-based provisioning and application of large-scale virtual 3D city models}, doi = {10.25932/publishup-42805}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-428053}, school = {Universit{\"a}t Potsdam}, pages = {xiii, 141}, year = {2018}, abstract = {Virtual 3D city models represent and integrate a variety of spatial data and georeferenced data related to urban areas. With the help of improved remote-sensing technology, official 3D cadastral data, open data or geodata crowdsourcing, the quantity and availability of such data are constantly expanding and its quality is ever improving for many major cities and metropolitan regions. There are numerous fields of applications for such data, including city planning and development, environmental analysis and simulation, disaster and risk management, navigation systems, and interactive city maps. The dissemination and the interactive use of virtual 3D city models represent key technical functionality required by nearly all corresponding systems, services, and applications. The size and complexity of virtual 3D city models, their management, their handling, and especially their visualization represent challenging tasks. For example, mobile applications can hardly handle these models due to their massive data volume and data heterogeneity. Therefore, the efficient usage of all computational resources (e.g., storage, processing power, main memory, and graphics hardware, etc.) is a key requirement for software engineering in this field. Common approaches are based on complex clients that require the 3D model data (e.g., 3D meshes and 2D textures) to be transferred to them and that then render those received 3D models. However, these applications have to implement most stages of the visualization pipeline on client side. Thus, as high-quality 3D rendering processes strongly depend on locally available computer graphics resources, software engineering faces the challenge of building robust cross-platform client implementations. Web-based provisioning aims at providing a service-oriented software architecture that consists of tailored functional components for building web-based and mobile applications that manage and visualize virtual 3D city models. This thesis presents corresponding concepts and techniques for web-based provisioning of virtual 3D city models. In particular, it introduces services that allow us to efficiently build applications for virtual 3D city models based on a fine-grained service concept. The thesis covers five main areas: 1. A Service-Based Concept for Image-Based Provisioning of Virtual 3D City Models It creates a frame for a broad range of services related to the rendering and image-based dissemination of virtual 3D city models. 2. 3D Rendering Service for Virtual 3D City Models This service provides efficient, high-quality 3D rendering functionality for virtual 3D city models. In particular, it copes with requirements such as standardized data formats, massive model texturing, detailed 3D geometry, access to associated feature data, and non-assumed frame-to-frame coherence for parallel service requests. In addition, it supports thematic and artistic styling based on an expandable graphics effects library. 3. Layered Map Service for Virtual 3D City Models It generates a map-like representation of virtual 3D city models using an oblique view. It provides high visual quality, fast initial loading times, simple map-based interaction and feature data access. Based on a configurable client framework, mobile and web-based applications for virtual 3D city models can be created easily. 4. Video Service for Virtual 3D City Models It creates and synthesizes videos from virtual 3D city models. Without requiring client-side 3D rendering capabilities, users can create camera paths by a map-based user interface, configure scene contents, styling, image overlays, text overlays, and their transitions. The service significantly reduces the manual effort typically required to produce such videos. The videos can automatically be updated when the underlying data changes. 5. Service-Based Camera Interaction It supports task-based 3D camera interactions, which can be integrated seamlessly into service-based visualization applications. It is demonstrated how to build such web-based interactive applications for virtual 3D city models using this camera service. These contributions provide a framework for design, implementation, and deployment of future web-based applications, systems, and services for virtual 3D city models. The approach shows how to decompose the complex, monolithic functionality of current 3D geovisualization systems into independently designed, implemented, and operated service- oriented units. In that sense, this thesis also contributes to microservice architectures for 3D geovisualization systems—a key challenge of today's IT systems engineering to build scalable IT solutions.}, 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{GebserSchaubThieleetal.2011, author = {Gebser, Martin and Schaub, Torsten H. and Thiele, Sven and Veber, Philippe}, title = {Detecting inconsistencies in large biological networks with answer set programming}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, number = {561}, issn = {1866-8372}, doi = {10.25932/publishup-41246}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-412467}, pages = {38}, year = {2011}, abstract = {We introduce an approach to detecting inconsistencies in large biological networks by using answer set programming. To this end, we build upon a recently proposed notion of consistency between biochemical/genetic reactions and high-throughput profiles of cell activity. We then present an approach based on answer set programming to check the consistency of large-scale data sets. Moreover, we extend this methodology to provide explanations for inconsistencies by determining minimal representations of conflicts. In practice, this can be used to identify unreliable data or to indicate missing reactions.}, language = {en} } @misc{DurzinskyMarwanOstrowskietal.2011, author = {Durzinsky, Markus and Marwan, Wolfgang and Ostrowski, Max and Schaub, Torsten H. and Wagler, Annegret}, title = {Automatic network reconstruction using ASP}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, number = {560}, issn = {1866-8372}, doi = {10.25932/publishup-41241}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-412419}, pages = {18}, year = {2011}, abstract = {Building biological models by inferring functional dependencies from experimental data is an important issue in Molecular Biology. To relieve the biologist from this traditionally manual process, various approaches have been proposed to increase the degree of automation. However, available approaches often yield a single model only, rely on specific assumptions, and/or use dedicated, heuristic algorithms that are intolerant to changing circumstances or requirements in the view of the rapid progress made in Biotechnology. Our aim is to provide a declarative solution to the problem by appeal to Answer Set Programming (ASP) overcoming these difficulties. We build upon an existing approach to Automatic Network Reconstruction proposed by part of the authors. This approach has firm mathematical foundations and is well suited for ASP due to its combinatorial flavor providing a characterization of all models explaining a set of experiments. The usage of ASP has several benefits over the existing heuristic algorithms. First, it is declarative and thus transparent for biological experts. Second, it is elaboration tolerant and thus allows for an easy exploration and incorporation of biological constraints. Third, it allows for exploring the entire space of possible models. Finally, our approach offers an excellent performance, matching existing, special-purpose systems.}, language = {en} } @misc{EhrigGolasHabeletal.2014, author = {Ehrig, Hartmut and Golas, Ulrike and Habel, Annegret and Lambers, Leen and Orejas, Fernando}, title = {M-adhesive transformation systems with nested application conditions}, series = {Postprints der Universit{\"a}t Potsdam : Digital Engineering Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Digital Engineering Reihe}, number = {001}, doi = {10.25932/publishup-41565}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-415651}, pages = {50}, year = {2014}, abstract = {Nested application conditions generalise the well-known negative application conditions and are important for several application domains. In this paper, we present Local Church-Rosser, Parallelism, Concurrency and Amalgamation Theorems for rules with nested application conditions in the framework of M-adhesive categories, where M-adhesive categories are slightly more general than weak adhesive high-level replacement categories. Most of the proofs are based on the corresponding statements for rules without application conditions and two shift lemmas stating that nested application conditions can be shifted over morphisms and rules.}, language = {en} } @phdthesis{Dick2016, author = {Dick, Uwe}, title = {Discriminative Classification Models for Internet Security}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-102593}, school = {Universit{\"a}t Potsdam}, pages = {x, 57}, year = {2016}, abstract = {Services that operate over the Internet are under constant threat of being exposed to fraudulent use. Maintaining good user experience for legitimate users often requires the classification of entities as malicious or legitimate in order to initiate countermeasures. As an example, inbound email spam filters decide for spam or non-spam. They can base their decision on both the content of each email as well as on features that summarize prior emails received from the sending server. In general, discriminative classification methods learn to distinguish positive from negative entities. Each decision for a label may be based on features of the entity and related entities. When labels of related entities have strong interdependencies---as can be assumed e.g. for emails being delivered by the same user---classification decisions should not be made independently and dependencies should be modeled in the decision function. This thesis addresses the formulation of discriminative classification problems that are tailored for the specific demands of the following three Internet security applications. Theoretical and algorithmic solutions are devised to protect an email service against flooding of user inboxes, to mitigate abusive usage of outbound email servers, and to protect web servers against distributed denial of service attacks. In the application of filtering an inbound email stream for unsolicited emails, utilizing features that go beyond each individual email's content can be valuable. Information about each sending mail server can be aggregated over time and may help in identifying unwanted emails. However, while this information will be available to the deployed email filter, some parts of the training data that are compiled by third party providers may not contain this information. The missing features have to be estimated at training time in order to learn a classification model. In this thesis an algorithm is derived that learns a decision function that integrates over a distribution of values for each missing entry. The distribution of missing values is a free parameter that is optimized to learn an optimal decision function. The outbound stream of emails of an email service provider can be separated by the customer IDs that ask for delivery. All emails that are sent by the same ID in the same period of time are related, both in content and in label. Hijacked customer accounts may send batches of unsolicited emails to other email providers, which in turn might blacklist the sender's email servers after detection of incoming spam emails. The risk of being blocked from further delivery depends on the rate of outgoing unwanted emails and the duration of high spam sending rates. An optimization problem is developed that minimizes the expected cost for the email provider by learning a decision function that assigns a limit on the sending rate to customers based on the each customer's email stream. Identifying attacking IPs during HTTP-level DDoS attacks allows to block those IPs from further accessing the web servers. DDoS attacks are usually carried out by infected clients that are members of the same botnet and show similar traffic patterns. HTTP-level attacks aim at exhausting one or more resources of the web server infrastructure, such as CPU time. If the joint set of attackers cannot increase resource usage close to the maximum capacity, no effect will be experienced by legitimate users of hosted web sites. However, if the additional load raises the computational burden towards the critical range, user experience will degrade until service may be unavailable altogether. As the loss of missing one attacker depends on block decisions for other attackers---if most other attackers are detected, not blocking one client will likely not be harmful---a structured output model has to be learned. In this thesis an algorithm is developed that learns a structured prediction decoder that searches the space of label assignments, guided by a policy. Each model is evaluated on real-world data and is compared to reference methods. The results show that modeling each classification problem according to the specific demands of the task improves performance over solutions that do not consider the constraints inherent to an application.}, language = {en} } @article{Rolf2010, author = {Rolf, Arno}, title = {Themeng{\"a}rten in der Informatik-Ausbildung}, series = {Commentarii informaticae didacticae : (CID)}, journal = {Commentarii informaticae didacticae : (CID)}, number = {4}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, issn = {1868-0844}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64281}, pages = {7 -- 12}, year = {2010}, abstract = {Die M{\"o}glichkeiten sich zu informieren, am Leben der vielen Anderen teilzunehmen ist durch das Internet mit seinen Tweets, Google-Angeboten und sozialen Netzwerken wie Facebook ins Unermessliche gewachsen. Zugleich f{\"u}hlen sich viele Nutzer {\"u}berfordert und meinen, im Meer der Informationen zu ertrinken. So bekennt Frank Schirrmacher in seinem Buch Payback, dass er den geistigen Anforderungen unserer Zeit nicht mehr gewachsen ist. Sein Kopf komme nicht mehr mit. Er sei unkonzentriert, vergesslich und st{\"a}ndig abgelenkt. Das, was vielen zum Problem geworden ist, sehen viele Studierende eher pragmatisch. Der Wissenserwerb in Zeiten von Internet und E-Learning l{\"a}uft an Hochschulen h{\"a}ufig nach der Helene-Hegemann-Methode ab: Zun{\"a}chst machen sich die Studierenden, z.B. im Rahmen einer Studien- oder Hausarbeit, bei Wikipedia „schlau", ein Einstieg ist geschafft. Anschließend wird dieses Wissen mit Google angereichert. Damit ist {\"U}berblickswissen vorhanden. Mit geschickter copy-and-paste-Komposition l{\"a}sst sich daraus schon ein „Werk" erstellen. Der ein oder andere Studierende gibt sich mit diesem Wissenserwerb zufrieden und bricht seinen Lernprozess hier bereits ab. Nun ist zwar am Ende jeder Studierende f{\"u}r seinen Wissenserwerb selbst verantwortlich. Die erkennbar unbefriedigende Situation sollte die Hochschulen aber herausfordern, das Internet in Vorlesungen und Seminaren auszuprobieren und sinnvolle Anwendungen zu entwickeln. Beispiele gibt es durchaus. Unter der Metapher E-Learning hat sich ein umfangreicher Forschungsschwerpunkt an den Universit{\"a}ten entwickelt. Einige Beispiele von vielen: So hat der Osnabr{\"u}cker Informatik-Professor Oliver Vornberger seine Vorlesungen als Video ins Netz gestellt. Per RSS ist es m{\"o}glich, Sequenzen aufs iPod zu laden. Die {\"u}bliche Dozentenangst, dann w{\"u}rden sie ja vor leeren B{\"a}nken sitzen, scheint unbegr{\"u}ndet. Sie werden von den Studierenden vor allem zur Pr{\"u}fungsvorbereitung genutzt. Wie ist das Internet, das f{\"u}r die junge Generation zu einem alles andere verdr{\"a}ngenden Universalmedium geworden ist, didaktisch in die Hochschullehre einzubinden? Wie also ist konkret mit diesen Herausforderungen umzugehen? Dies soll uns im Folgenden besch{\"a}ftigen.}, language = {de} } @article{MetzgerHaag2013, author = {Metzger, Christiane and Haag, Johann}, title = {„Ich k{\"o}nnte nie wieder zu einem ‚normalen' Stundenplan zur{\"u}ck!"}, series = {Commentarii informaticae didacticae : (CID)}, journal = {Commentarii informaticae didacticae : (CID)}, number = {5}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, issn = {1868-0844}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64884}, pages = {67 -- 78}, year = {2013}, abstract = {Im Bachelor-Studiengang (B. Sc.) IT Security an der Fachhochschule St. P{\"o}lten wurde im Wintersemester 2011/12 versuchsweise die Lehrorganisation im ersten Fachsemester ver{\"a}ndert: Die Module bzw. Teilmodule wurden nicht mehr alle parallel zueinander unterrichtet, sondern jedes Modul wurde exklusiv {\"u}ber einige Wochen abgehalten. Im Beitrag werden die Auswirkungen und bisherigen Erfahrungen mit dieser Reorganisation der Lehre geschildert: So haben sich die Noten im Mittel um etwa eine Note verbessert, die Zahl derjenigen Studierenden, die durch Pr{\"u}fungen durchfallen, ist drastisch gesunken. Die Zufriedenheit der Studierenden und Lehrenden ist so groß, dass diese Form der Lehrorganisation im gesamten Bachelor- und auch im Masterstudiengang {\"u}bernommen wird.}, language = {de} } @article{KlingerPolutinaBibel2013, author = {Klinger, Melanie and Polutina, Olena and Bibel, Ariane}, title = {Studentische eLearning-Beratung}, series = {Commentarii informaticae didacticae : (CID)}, journal = {Commentarii informaticae didacticae : (CID)}, number = {5}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, issn = {1868-0844}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-65003}, pages = {131 -- 136}, year = {2013}, abstract = {Der vorliegende Beitrag besch{\"a}ftigt sich mit der Frage, wie der eLearning-Support in großen Institutionen effizient gestaltet werden kann. Vorgestellt wird ein experimentelles Beratungsprojekt, das Lehrende bei der Gestaltung von eLearning-Maßnahmen mithilfe der Lernplattform ILIAS1 unterst{\"u}tzt. Neben der Zielsetzung des Projekts werden dessen Aufbau und erste Praxiserfahrungen er{\"o}rtert. Außerdem werden Potenziale des Beratungsformats, die insbesondere mit der individuellen Vor-Ort-Beratung der Lehrenden durch hochschuldidaktisch geschulte Studierende einhergehen, erl{\"a}utert. Abschließend werden Grenzen und Weiterentwicklungsperspektiven des Projekts dargestellt. Am Beispiel der ILIAS-Beratung soll gezeigt werden, dass es sich einer nachhaltigen Organisationsentwicklung als zutr{\"a}glich erweist, Kooperationen erschiedenartiger Organisationseinheiten zu f{\"o}rdern und die entstehenden Synergieeffekte zu nutzen.}, language = {de} } @article{BergesMuehlingHubwieseretal.2013, author = {Berges, Marc and M{\"u}hling, Andreas and Hubwieser, Peter and Steuer, Horst}, title = {Informatik f{\"u}r Nichtinformatiker}, series = {Commentarii informaticae didacticae : (CID)}, journal = {Commentarii informaticae didacticae : (CID)}, number = {5}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, issn = {1868-0844}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64962}, pages = {105 -- 110}, year = {2013}, abstract = {Wir stellen die Konzeption und erste Ergebnisse einer neuartigen Informatik- Lehrveranstaltung f{\"u}r Studierende der Geod{\"a}sie vor. Das Konzept verbindet drei didaktische Ideen: Kontextorientierung, Peer-Tutoring und Praxisbezug (Course). Die Studierenden sollen dabei in zwei Semestern wichtige Grundlagen der Informatik verstehen und anzuwenden lernen. Durch enge Verzahnung der Aufgaben mit einem f{\"u}r Nichtinformatiker relevanten Kontext, sowie einem sehr hohen Anteil von Selbstt{\"a}tigkeit der Studierenden soll die Motivation f{\"u}r fachfremde Themen gesteigert werden. Die Ergebnisse zeigen, dass die Veranstaltung sehr erfolgreich war.}, language = {de} } @article{EngbringSelke2013, author = {Engbring, Dieter and Selke, Harald}, title = {Informatik und Gesellschaft als Gebiet der Informatik}, series = {Commentarii informaticae didacticae : (CID)}, journal = {Commentarii informaticae didacticae : (CID)}, number = {5}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, issn = {1868-0844}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64977}, pages = {111 -- 116}, year = {2013}, abstract = {In diesem Beitrag berichten wir {\"u}ber die Erfahrungen einer umgestalteten Lehre im Bereich Informatik und Gesellschft (IuG). Die Gr{\"u}nde f{\"u}r die Umge staltung und die Konzeption werden skizziert. Die Erfahrungen haben wir zu Thesen verdichtet: 1. Informatik und Gesellschaft sollte eine Pflichtveranstaltung im Bachelor-Studium sein, in der Studierende einen {\"U}berblick erhalten, welche gesellschaftlichen Rahmenbedingungen f{\"u}r sie relevant sind und wie man diese in die Praxis mit einbeziehen kann. 2. Historische Inhalte der Informatik sollen hier aufgearbeitet werden, indem man aktuelle Entwicklungen im Kontext ihrer Genese betrachtet.}, language = {de} } @article{Doerge2013, author = {D{\"o}rge, Christina}, title = {Entwicklung eines Kompetenzrahmenmodells f{\"u}r die universit{\"a}re Lehre}, series = {Commentarii informaticae didacticae : (CID)}, journal = {Commentarii informaticae didacticae : (CID)}, number = {5}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, issn = {1868-0844}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64946}, pages = {91 -- 97}, year = {2013}, abstract = {Zurzeit haben wir es mit der folgenden Situation an Universit{\"a}ten zu tun: Studierende kommen mit unterschiedlichem Wissen und Kompetenzen zur Universit{\"a}t, um informatikbezogene Studieng{\"a}nge zu belegen. Diesem Umstand muss in den universit{\"a}ren Kursen entgegengewirkt werden, um ein einheitliches Bildungsziel zu erreichen. F{\"u}r einige Studierende bedeutet dies oft eine Lehrbelastung in einem ohnehin sehr zeitintensiven Studium, was nicht selten zum Studienabbruch f{\"u}hrt. Ein anderes Problem ist die fehlende Transparenz bez{\"u}glich der Gegenst{\"a}nde des Informatikstudiums: einige angehende Studierende kommen mit einem von der Realit{\"a}t abweichenden Bild der Informatik zur Universit{\"a}t, andere entscheiden sich u. U. deshalb gegen ein Informatikstudium, da ihnen nicht bewusst ist, dass das Studium f{\"u}r sie interessant sein k{\"o}nnte. In diesem Artikel soll ein L{\"o}sungsvorschlag anhand eines Kompetenzrahmenmodells vorgestellt werden, mit dessen Hilfe eine Verbesserung der Hochschulsituation erreicht werden kann.}, language = {de} } @article{AlSaffar2013, author = {Al-Saffar, Loay Talib Ahmed}, title = {Where girls take the role of boys in CS}, series = {Commentarii informaticae didacticae : (CID)}, journal = {Commentarii informaticae didacticae : (CID)}, number = {5}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, issn = {1868-0844}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-65034}, pages = {149 -- 154}, year = {2013}, abstract = {A survey has been carried out in the Computer Science (CS) department at the University of Baghdad to investigate the attitudes of CS students in a female dominant environment, showing the differences between male and female students in different academic years. We also compare the attitudes of the freshman students of two different cultures (University of Baghdad, Iraq, and the University of Potsdam).}, language = {en} } @article{Petre2013, author = {Petre, Marian}, title = {Computing is not a spectator sport}, series = {Commentarii informaticae didacticae : (CID)}, journal = {Commentarii informaticae didacticae : (CID)}, number = {5}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, issn = {1868-0844}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-65045}, pages = {155 -- 159}, year = {2013}, abstract = {This talk will describe My Digital Life (TU100), a distance learning module that introduces computer science through immediate engagement with ubiquitous computing (ubicomp). This talk will describe some of the principles and concepts we have adopted for this modern computing introduction: the idea of the 'informed digital citizen'; engagement through narrative; playful pedagogy; making the power of ubicomp available to novices; setting technical skills in real contexts. It will also trace how the pedagogy is informed by experiences and research in Computer Science education.}, language = {en} } @phdthesis{Glander2012, author = {Glander, Tassilo}, title = {Multi-scale representations of virtual 3D city models}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64117}, school = {Universit{\"a}t Potsdam}, year = {2012}, abstract = {Virtual 3D city and landscape models are the main subject investigated in this thesis. They digitally represent urban space and have many applications in different domains, e.g., simulation, cadastral management, and city planning. Visualization is an elementary component of these applications. Photo-realistic visualization with an increasingly high degree of detail leads to fundamental problems for comprehensible visualization. A large number of highly detailed and textured objects within a virtual 3D city model may create visual noise and overload the users with information. Objects are subject to perspective foreshortening and may be occluded or not displayed in a meaningful way, as they are too small. In this thesis we present abstraction techniques that automatically process virtual 3D city and landscape models to derive abstracted representations. These have a reduced degree of detail, while essential characteristics are preserved. After introducing definitions for model, scale, and multi-scale representations, we discuss the fundamentals of map generalization as well as techniques for 3D generalization. The first presented technique is a cell-based generalization of virtual 3D city models. It creates abstract representations that have a highly reduced level of detail while maintaining essential structures, e.g., the infrastructure network, landmark buildings, and free spaces. The technique automatically partitions the input virtual 3D city model into cells based on the infrastructure network. The single building models contained in each cell are aggregated to abstracted cell blocks. Using weighted infrastructure elements, cell blocks can be computed on different hierarchical levels, storing the hierarchy relation between the cell blocks. Furthermore, we identify initial landmark buildings within a cell by comparing the properties of individual buildings with the aggregated properties of the cell. For each block, the identified landmark building models are subtracted using Boolean operations and integrated in a photo-realistic way. Finally, for the interactive 3D visualization we discuss the creation of the virtual 3D geometry and their appearance styling through colors, labeling, and transparency. We demonstrate the technique with example data sets. Additionally, we discuss applications of generalization lenses and transitions between abstract representations. The second technique is a real-time-rendering technique for geometric enhancement of landmark objects within a virtual 3D city model. Depending on the virtual camera distance, landmark objects are scaled to ensure their visibility within a specific distance interval while deforming their environment. First, in a preprocessing step a landmark hierarchy is computed, this is then used to derive distance intervals for the interactive rendering. At runtime, using the virtual camera distance, a scaling factor is computed and applied to each landmark. The scaling factor is interpolated smoothly at the interval boundaries using cubic B{\´e}zier splines. Non-landmark geometry that is near landmark objects is deformed with respect to a limited number of landmarks. We demonstrate the technique by applying it to a highly detailed virtual 3D city model and a generalized 3D city model. In addition we discuss an adaptation of the technique for non-linear projections and mobile devices. The third technique is a real-time rendering technique to create abstract 3D isocontour visualization of virtual 3D terrain models. The virtual 3D terrain model is visualized as a layered or stepped relief. The technique works without preprocessing and, as it is implemented using programmable graphics hardware, can be integrated with minimal changes into common terrain rendering techniques. Consequently, the computation is done in the rendering pipeline for each vertex, primitive, i.e., triangle, and fragment. For each vertex, the height is quantized to the nearest isovalue. For each triangle, the vertex configuration with respect to their isovalues is determined first. Using the configuration, the triangle is then subdivided. The subdivision forms a partial step geometry aligned with the triangle. For each fragment, the surface appearance is determined, e.g., depending on the surface texture, shading, and height-color-mapping. Flexible usage of the technique is demonstrated with applications from focus+context visualization, out-of-core terrain rendering, and information visualization. This thesis presents components for the creation of abstract representations of virtual 3D city and landscape models. Re-using visual language from cartography, the techniques enable users to build on their experience with maps when interpreting these representations. Simultaneously, characteristics of 3D geovirtual environments are taken into account by addressing and discussing, e.g., continuous scale, interaction, and perspective.}, language = {en} } @article{DuennebierDiethelm2010, author = {D{\"u}nnebier, Malte and Diethelm, Ira}, title = {Ein virtueller Lernraum f{\"u}r die Informatiklehrerweiterbildung}, series = {Commentarii informaticae didacticae : (CID)}, journal = {Commentarii informaticae didacticae : (CID)}, number = {4}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, issn = {1868-0844}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64359}, pages = {65 -- 70}, year = {2010}, abstract = {Bei der Suche nach M{\"o}glichkeiten, die Weiterbildung f{\"u}r Informatiklehrkr{\"a}fte auszubauen, bietet sich der Einsatz virtueller Lernr{\"a}ume an. Dieses Papier berichtet {\"u}ber ein Projekt, in dem ein exemplarischer virtueller Lernraum f{\"u}r kollaboratives Lernen in der Lehrerweiterbildung in Informatik theoriegeleitet erstellt, erprobt und bewertet wurde. Die erzielten Ergebnisse {\"u}ber das Nutzungsverhalten k{\"o}nnen f{\"u}r weitere E-Learningprojekte in der Lehrerbildung hilfreich sein. Der Schwerpunkt dieses Papiers liegt auf der Gestaltung des Lernraums unter Beachtung der speziellen Situation der Informatiklehrkr{\"a}fte, nicht auf der didaktischen Aufbereitung der betreffenden Lerneinheit.}, language = {de} } @article{BollMeinhardtGronewoldetal.2010, author = {Boll, Susanne and Meinhardt, Rolf and Gronewold, Sabine and Krekeler, Larissa}, title = {Informatik f{\"u}r Migratinnen und Migranten Einf{\"u}hrung eines neuen Studienprogramms an der Universit{\"a}t Oldenburg}, series = {Commentarii informaticae didacticae : (CID)}, journal = {Commentarii informaticae didacticae : (CID)}, number = {4}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, issn = {1868-0844}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64370}, pages = {79 -- 86}, year = {2010}, abstract = {F{\"u}r die Integration und den Bedarf der hochqualifizierten Migranten auf dem Arbeitsmarkt in Deutschland gibt es viele {\"U}berlegungen, aber noch keine ausreichenden L{\"o}sungen. Dieser Artikel beschreibt eine praktische L{\"o}sung {\"u}ber die Umsetzung des Konzepts f{\"u}r die Qualifizierung der akademischen Migranten am Beispiel eines Studienprogramms in Informatik an der Universit{\"a}t Oldenburg.}, language = {de} } @article{LaroqueSchulteUrban2010, author = {Laroque, Christoph and Schulte, Jonas and Urban, Diana}, title = {KoProV}, series = {Commentarii informaticae didacticae : (CID)}, journal = {Commentarii informaticae didacticae : (CID)}, number = {4}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, issn = {1868-0844}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64445}, pages = {99 -- 105}, year = {2010}, abstract = {In der universit{\"a}ren Lehre {\"a}ndert sich der Leitgedanke von einer qualifikationsorientierten hin zu einer kompetenzorientierten Ausbildung. Der Begriff Kompetenz l{\"a}sst sich dabei grob in die fachlichen und die {\"u}berfachlichen Kompetenzen unterteilen. Insbesondere die Vermittlung von Schl{\"u}sselqualifikationen hat in der Lehre von naturwissenschaftlichen Fachrichtungen nur unzureichend Einzug erhalten. W{\"a}hrend der klassische Vorlesungsbetrieb auf den Erwerb von Fachkompetenz zielt, stoßen ausschließlich projektorientierte Veranstaltungen schnell an ihre Grenzen hinsichtlich der Teilnehmergr{\"o}ße oder Umfang der Lerninhalte. Um auf geeignete Art und Weise den Erwerb von {\"u}berfachlichen Kompetenzen zu erm{\"o}glichen, bedarf es neuer didaktischer Konzepte, die eine engere Verkn{\"u}pfung von klassischen Vorlesungen und dem projektorientierten Lernen vorsehen. In diesem Sinne versucht der skizzierte Ansatz der koordinierten Projektvorlesung(KoProV) Wissensvermittlung im Rahmen von Vorlesungseinheiten mit koordinierten Praxisphasen in Teilgruppen zu verbinden. F{\"u}r eine erfolgreiche Durchf{\"u}hrung und Erarbeitung des begleitenden Praxisprojektes durch mehrere Teilgruppen sind organisatorische und technische Randbedingungen zu beachten.}, language = {de} } @article{Kiss2010, author = {Kiss, G{\´a}bor}, title = {Analyse der Studienleistungen von Studierenden an der Universit{\"a}t {\´O}buda und deren Implikationen f{\"u}r die Informatikausbildung}, series = {Commentarii informaticae didacticae : (CID)}, journal = {Commentarii informaticae didacticae : (CID)}, number = {4}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, issn = {1868-0844}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64364}, pages = {71 -- 77}, year = {2010}, abstract = {In der letzten Jahren ist die Zahl der erfolgreichen Pr{\"u}fungen von Studierenden im Informatikkurs des ersten Studienjahres f{\"u}r verschiedene Studieng{\"a}nge an der Universit{\"a}t {\´O}buda stark gesunken. Dies betrifft Pr{\"u}fungen in den Teilgebieten Rechnerarchitektur, Betrieb von Peripherieger{\"a}ten, Bin{\"a}re Codierung und logische Operationen, Computerviren, Computernetze und das Internet, Steganographie und Kryptographie, Betriebsysteme. Mehr als der H{\"a}lfte der Studenten konnte die Pr{\"u}fungen der ersten Semester nicht erfolgreich absolvieren. Die hier vorgelegte Analyse der Studienleistungen zielt darauf ab, Gr{\"u}nde f{\"u}r diese Entwicklung zu identifizieren, die Zahl der Abbrecher zu reduzieren und die Leistungen der Studenten zu verbessern. Die Analyse zeigt, dass die Studenten die erforderlichen Lehrmaterialen erst ein bis zwei Tage vor oder sogar erst am Tag der Klausuren vom Server downloaden, so dass sie nicht mehr hinreichend Zeit zum Lernen haben. Diese Tendenz zeigt sich bei allen Teilgebieten des Studiengangs. Ein Mangel an kontinuierlicher Mitarbeit scheint einer der Gr{\"u}nde f{\"u}r ein fr{\"u}hes Scheitern zu sein. Ferner zeigt sich die Notwendigkeit, dass bei den Lehrangeboten in Informatik auf eine kontinuierliche Kommunikation mit den Studierenden und R{\"u}ckmeldung zu aktuellen Unterrichtsinhalten zu achten ist. Dies kann durch motivierende Maßnahmen zur Teilnahme an den {\"U}bungen oder durch kleine w{\"o}chentliche schriftliche Tests geschehen.}, language = {de} } @phdthesis{Seibel2012, author = {Seibel, Andreas}, title = {Traceability and model management with executable and dynamic hierarchical megamodels}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64222}, school = {Universit{\"a}t Potsdam}, year = {2012}, abstract = {Nowadays, model-driven engineering (MDE) promises to ease software development by decreasing the inherent complexity of classical software development. In order to deliver on this promise, MDE increases the level of abstraction and automation, through a consideration of domain-specific models (DSMs) and model operations (e.g. model transformations or code generations). DSMs conform to domain-specific modeling languages (DSMLs), which increase the level of abstraction, and model operations are first-class entities of software development because they increase the level of automation. Nevertheless, MDE has to deal with at least two new dimensions of complexity, which are basically caused by the increased linguistic and technological heterogeneity. The first dimension of complexity is setting up an MDE environment, an activity comprised of the implementation or selection of DSMLs and model operations. Setting up an MDE environment is both time-consuming and error-prone because of the implementation or adaptation of model operations. The second dimension of complexity is concerned with applying MDE for actual software development. Applying MDE is challenging because a collection of DSMs, which conform to potentially heterogeneous DSMLs, are required to completely specify a complex software system. A single DSML can only be used to describe a specific aspect of a software system at a certain level of abstraction and from a certain perspective. Additionally, DSMs are usually not independent but instead have inherent interdependencies, reflecting (partial) similar aspects of a software system at different levels of abstraction or from different perspectives. A subset of these dependencies are applications of various model operations, which are necessary to keep the degree of automation high. This becomes even worse when addressing the first dimension of complexity. Due to continuous changes, all kinds of dependencies, including the applications of model operations, must also be managed continuously. This comprises maintaining the existence of these dependencies and the appropriate (re-)application of model operations. The contribution of this thesis is an approach that combines traceability and model management to address the aforementioned challenges of configuring and applying MDE for software development. The approach is considered as a traceability approach because it supports capturing and automatically maintaining dependencies between DSMs. The approach is considered as a model management approach because it supports managing the automated (re-)application of heterogeneous model operations. In addition, the approach is considered as a comprehensive model management. Since the decomposition of model operations is encouraged to alleviate the first dimension of complexity, the subsequent composition of model operations is required to counteract their fragmentation. A significant portion of this thesis concerns itself with providing a method for the specification of decoupled yet still highly cohesive complex compositions of heterogeneous model operations. The approach supports two different kinds of compositions - data-flow compositions and context compositions. Data-flow composition is used to define a network of heterogeneous model operations coupled by sharing input and output DSMs alone. Context composition is related to a concept used in declarative model transformation approaches to compose individual model transformation rules (units) at any level of detail. In this thesis, context composition provides the ability to use a collection of dependencies as context for the composition of other dependencies, including model operations. In addition, the actual implementation of model operations, which are going to be composed, do not need to implement any composition concerns. The approach is realized by means of a formalism called an executable and dynamic hierarchical megamodel, based on the original idea of megamodels. This formalism supports specifying compositions of dependencies (traceability and model operations). On top of this formalism, traceability is realized by means of a localization concept, and model management by means of an execution concept.}, language = {en} } @book{SchwalbKruegerPlattner2013, author = {Schwalb, David and Kr{\"u}ger, Jens and Plattner, Hasso}, title = {Cache conscious column organization in in-memory column stores}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-228-5}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-63890}, publisher = {Universit{\"a}t Potsdam}, pages = {v, 84}, year = {2013}, abstract = {Cost models are an essential part of database systems, as they are the basis of query performance optimization. Based on predictions made by cost models, the fastest query execution plan can be chosen and executed or algorithms can be tuned and optimised. In-memory databases shifts the focus from disk to main memory accesses and CPU costs, compared to disk based systems where input and output costs dominate the overall costs and other processing costs are often neglected. However, modelling memory accesses is fundamentally different and common models do not apply anymore. This work presents a detailed parameter evaluation for the plan operators scan with equality selection, scan with range selection, positional lookup and insert in in-memory column stores. Based on this evaluation, a cost model based on cache misses for estimating the runtime of the considered plan operators using different data structures is developed. Considered are uncompressed columns, bit compressed and dictionary encoded columns with sorted and unsorted dictionaries. Furthermore, tree indices on the columns and dictionaries are discussed. Finally, partitioned columns consisting of one partition with a sorted and one with an unsorted dictionary are investigated. New values are inserted in the unsorted dictionary partition and moved periodically by a merge process to the sorted partition. An efficient attribute merge algorithm is described, supporting the update performance required to run enterprise applications on read-optimised databases. Further, a memory traffic based cost model for the merge process is provided.}, language = {en} } @book{VogelGiese2013, author = {Vogel, Thomas and Giese, Holger}, title = {Model-driven engineering of adaptation engines for self-adaptive software : executable runtime megamodels}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-227-8}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-63825}, publisher = {Universit{\"a}t Potsdam}, pages = {vi, 59}, year = {2013}, abstract = {The development of self-adaptive software requires the engineering of an adaptation engine that controls and adapts the underlying adaptable software by means of feedback loops. The adaptation engine often describes the adaptation by using runtime models representing relevant aspects of the adaptable software and particular activities such as analysis and planning that operate on these runtime models. To systematically address the interplay between runtime models and adaptation activities in adaptation engines, runtime megamodels have been proposed for self-adaptive software. A runtime megamodel is a specific runtime model whose elements are runtime models and adaptation activities. Thus, a megamodel captures the interplay between multiple models and between models and activities as well as the activation of the activities. In this article, we go one step further and present a modeling language for ExecUtable RuntimE MegAmodels (EUREMA) that considerably eases the development of adaptation engines by following a model-driven engineering approach. We provide a domain-specific modeling language and a runtime interpreter for adaptation engines, in particular for feedback loops. Megamodels are kept explicit and alive at runtime and by interpreting them, they are directly executed to run feedback loops. Additionally, they can be dynamically adjusted to adapt feedback loops. Thus, EUREMA supports development by making feedback loops, their runtime models, and adaptation activities explicit at a higher level of abstraction. Moreover, it enables complex solutions where multiple feedback loops interact or even operate on top of each other. Finally, it leverages the co-existence of self-adaptation and off-line adaptation for evolution.}, language = {en} } @article{HeinischRomeike2013, author = {Heinisch, Isabelle and Romeike, Ralf}, title = {Outcome-orientierte Neuausrichtung in der Hochschullehre Informatik}, series = {Commentarii informaticae didacticae : (CID)}, journal = {Commentarii informaticae didacticae : (CID)}, number = {5}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, issn = {1868-0844}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64831}, pages = {9 -- 20}, year = {2013}, abstract = {Die Orientierung am Outcome eines Lernprozesses stellt einen wichtigen Pfeiler einer kompetenzorientierten Informatiklehre dar. Im Beitrag werden Konzeption und Erfahrungen eines Projekts zur outcome-orientierten Neuausrichtung der Informatiklehre unter Ber{\"u}cksichtigung der Theorie des Constructive Alignment beschrieben. Nach der theoretischen Fundierung der Kompetenzproblematik wird anhand eines Formulierungsmodells ein Prozess zur Erarbeitung beobachtbarer Lernergebnisse dargestellt. Die Diskussion der Projektziele und Erfahrungen in der Umsetzung und Evaluierung unterstreichen die Chancen und Herausforderungen f{\"u}r eine Steigerung der Studienqualit{\"a}t.}, language = {de} } @article{HolzBergerSchroeder2013, author = {Holz, Jan and Berger, Nadine and Schroeder, Ulrike}, title = {Anwendungsorientierte Gestaltung eines Informatik-Vorkurses als Studienmotivator}, series = {Commentarii informaticae didacticae : (CID)}, journal = {Commentarii informaticae didacticae : (CID)}, number = {5}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, issn = {1868-0844}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64871}, pages = {56 -- 66}, year = {2013}, abstract = {Zur Unterst{\"u}tzung von Studierenden in der Studieneingangsphase wurde an der RWTH Aachen ein neuartiger und motivierender Einstieg in den Vorkurs Informatik entwickelt und zum Wintersemester 2011/12 erprobt. Dabei wurde die grafische Programmierung mittels App Inventor eingef{\"u}hrt, die zur Umsetzung anwendungsbezogener Projekte genutzt wurde. In diesem Beitrag werden die Motivation f{\"u}r die Neugestaltung, das Konzept und die Evaluation des Testlaufs beschrieben. Diese dienen als Grundlage f{\"u}r eine vollst{\"a}ndige Neukonzeption des Vorkurses f{\"u}r das Wintersemester 2012/2013.}, language = {de} } @book{BeyhlBlouinGieseetal.2016, author = {Beyhl, Thomas and Blouin, Dominique and Giese, Holger and Lambers, Leen}, title = {On the operationalization of graph queries with generalized discrimination networks}, number = {106}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-372-5}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-96279}, publisher = {Universit{\"a}t Potsdam}, pages = {33}, year = {2016}, abstract = {Graph queries have lately gained increased interest due to application areas such as social networks, biological networks, or model queries. For the relational database case the relational algebra and generalized discrimination networks have been studied to find appropriate decompositions into subqueries and ordering of these subqueries for query evaluation or incremental updates of query results. For graph database queries however there is no formal underpinning yet that allows us to find such suitable operationalizations. Consequently, we suggest a simple operational concept for the decomposition of arbitrary complex queries into simpler subqueries and the ordering of these subqueries in form of generalized discrimination networks for graph queries inspired by the relational case. The approach employs graph transformation rules for the nodes of the network and thus we can employ the underlying theory. We further show that the proposed generalized discrimination networks have the same expressive power as nested graph conditions.}, language = {en} } @unpublished{GrapentinHeidlerKorschetal.2014, author = {Grapentin, Andreas and Heidler, Kirstin and Korsch, Dimitri and Kumar Sah, Rakesh and Kunzmann, Nicco and Henning, Johannes and Mattis, Toni and Rein, Patrick and Seckler, Eric and Groneberg, Bj{\"o}rn and Zimmermann, Florian}, title = {Embedded operating system projects}, number = {90}, editor = {Hentschel, Uwe and Richter, Daniel and Polze, Andreas}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-296-4}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-69154}, pages = {xi, 87}, year = {2014}, abstract = {In today's life, embedded systems are ubiquitous. But they differ from traditional desktop systems in many aspects - these include predictable timing behavior (real-time), the management of scarce resources (memory, network), reliable communication protocols, energy management, special purpose user-interfaces (headless operation), system configuration, programming languages (to support software/hardware co-design), and modeling techniques. Within this technical report, authors present results from the lecture "Operating Systems for Embedded Computing" that has been offered by the "Operating Systems and Middleware" group at HPI in Winter term 2013/14. Focus of the lecture and accompanying projects was on principles of real-time computing. Students had the chance to gather practical experience with a number of different OSes and applications and present experiences with near-hardware programming. Projects address the entire spectrum, from bare-metal programming to harnessing a real-time OS to exercising the full software/hardware co-design cycle. Three outstanding projects are at the heart of this technical report. Project 1 focuses on the development of a bare-metal operating system for LEGO Mindstorms EV3. While still a toy, it comes with a powerful ARM processor, 64 MB of main memory, standard interfaces, such as Bluetooth and network protocol stacks. EV3 runs a version of 1 1 Introduction Linux. Sources are available from Lego's web site. However, many devices and their driver software are proprietary and not well documented. Developing a new, bare-metal OS for the EV3 requires an understanding of the EV3 boot process. Since no standard input/output devices are available, initial debugging steps are tedious. After managing these initial steps, the project was able to adapt device drivers for a few Lego devices to an extent that a demonstrator (the Segway application) could be successfully run on the new OS. Project 2 looks at the EV3 from a different angle. The EV3 is running a pretty decent version of Linux- in principle, the RT_PREEMPT patch can turn any Linux system into a real-time OS by modifying the behavior of a number of synchronization constructs at the heart of the OS. Priority inversion is a problem that is solved by protocols such as priority inheritance or priority ceiling. Real-time OSes implement at least one of the protocols. The central idea of the project was the comparison of non-real-time and real-time variants of Linux on the EV3 hardware. A task set that showed effects of priority inversion on standard EV3 Linux would operate flawlessly on the Linux version with the RT_PREEMPT-patch applied. If only patching Lego's version of Linux was that easy... Project 3 takes the notion of real-time computing more seriously. The application scenario was centered around our Carrera Digital 132 racetrack. Obtaining position information from the track, controlling individual cars, detecting and modifying the Carrera Digital protocol required design and implementation of custom controller hardware. What to implement in hardware, firmware, and what to implement in application software - this was the central question addressed by the project.}, language = {en} } @phdthesis{Polyvyanyy2012, author = {Polyvyanyy, Artem}, title = {Structuring process models}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-59024}, school = {Universit{\"a}t Potsdam}, year = {2012}, abstract = {One can fairly adopt the ideas of Donald E. Knuth to conclude that process modeling is both a science and an art. Process modeling does have an aesthetic sense. Similar to composing an opera or writing a novel, process modeling is carried out by humans who undergo creative practices when engineering a process model. Therefore, the very same process can be modeled in a myriad number of ways. Once modeled, processes can be analyzed by employing scientific methods. Usually, process models are formalized as directed graphs, with nodes representing tasks and decisions, and directed arcs describing temporal constraints between the nodes. Common process definition languages, such as Business Process Model and Notation (BPMN) and Event-driven Process Chain (EPC) allow process analysts to define models with arbitrary complex topologies. The absence of structural constraints supports creativity and productivity, as there is no need to force ideas into a limited amount of available structural patterns. Nevertheless, it is often preferable that models follow certain structural rules. A well-known structural property of process models is (well-)structuredness. A process model is (well-)structured if and only if every node with multiple outgoing arcs (a split) has a corresponding node with multiple incoming arcs (a join), and vice versa, such that the set of nodes between the split and the join induces a single-entry-single-exit (SESE) region; otherwise the process model is unstructured. The motivations for well-structured process models are manifold: (i) Well-structured process models are easier to layout for visual representation as their formalizations are planar graphs. (ii) Well-structured process models are easier to comprehend by humans. (iii) Well-structured process models tend to have fewer errors than unstructured ones and it is less probable to introduce new errors when modifying a well-structured process model. (iv) Well-structured process models are better suited for analysis with many existing formal techniques applicable only for well-structured process models. (v) Well-structured process models are better suited for efficient execution and optimization, e.g., when discovering independent regions of a process model that can be executed concurrently. Consequently, there are process modeling languages that encourage well-structured modeling, e.g., Business Process Execution Language (BPEL) and ADEPT. However, the well-structured process modeling implies some limitations: (i) There exist processes that cannot be formalized as well-structured process models. (ii) There exist processes that when formalized as well-structured process models require a considerable duplication of modeling constructs. Rather than expecting well-structured modeling from start, we advocate for the absence of structural constraints when modeling. Afterwards, automated methods can suggest, upon request and whenever possible, alternative formalizations that are "better" structured, preferably well-structured. In this thesis, we study the problem of automatically transforming process models into equivalent well-structured models. The developed transformations are performed under a strong notion of behavioral equivalence which preserves concurrency. The findings are implemented in a tool, which is publicly available.}, language = {en} } @phdthesis{Meier2017, author = {Meier, Sebastian}, title = {Personal Big Data}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-406696}, school = {Universit{\"a}t Potsdam}, pages = {xxiv, 133}, year = {2017}, abstract = {Many users of cloud-based services are concerned about questions of data privacy. At the same time, they want to benefit from smart data-driven services, which require insight into a person's individual behaviour. The modus operandi of user modelling is that data is sent to a remote server where the model is constructed and merged with other users' data. This thesis proposes selective cloud computing, an alternative approach, in which the user model is constructed on the client-side and only an abstracted generalised version of the model is shared with the remote services. In order to demonstrate the applicability of this approach, the thesis builds an exemplary client-side user modelling technique. As this thesis is carried out in the area of Geoinformatics and spatio-temporal data is particularly sensitive, the application domain for this experiment is the analysis and prediction of a user's spatio-temporal behaviour. The user modelling technique is grounded in an innovative conceptual model, which builds upon spatial network theory combined with time-geography. The spatio-temporal constraints of time-geography are applied to the network structure in order to create individual spatio-temporal action spaces. This concept is translated into a novel algorithmic user modelling approach which is solely driven by the user's own spatio-temporal trajectory data that is generated by the user's smartphone. While modern smartphones offer a rich variety of sensory data, this thesis only makes use of spatio-temporal trajectory data, enriched by activity classification, as the input and foundation for the algorithmic model. The algorithmic model consists of three basal components: locations (vertices), trips (edges), and clusters (neighbourhoods). After preprocessing the incoming trajectory data in order to identify locations, user feedback is used to train an artificial neural network to learn temporal patterns for certain location types (e.g. work, home, bus stop, etc.). This Artificial Neural Network (ANN) is used to automatically detect future location types by their spatio-temporal patterns. The same is done in order to predict the duration of stay at a certain location. Experiments revealed that neural nets were the most successful statistical and machine learning tool to detect those patterns. The location type identification algorithm reached an accuracy of 87.69\%, the duration prediction on binned data was less successful and deviated by an average of 0.69 bins. A challenge for the location type classification, as well as for the subsequent components, was the imbalance of trips and connections as well as the low accuracy of the trajectory data. The imbalance is grounded in the fact that most users exhibit strong habitual patterns (e.g. home > work), while other patterns are rather rare by comparison. The accuracy problem derives from the energy-saving location sampling mode, which creates less accurate results. Those locations are then used to build a network that represents the user's spatio-temporal behaviour. An initial untrained ANN to predict movement on the network only reached 46\% average accuracy. Only lowering the number of included edges, focusing on more common trips, increased the performance. In order to further improve the algorithm, the spatial trajectories were introduced into the predictions. To overcome the accuracy problem, trips between locations were clustered into so-called spatial corridors, which were intersected with the user's current trajectory. The resulting intersected trips were ranked through a k-nearest-neighbour algorithm. This increased the performance to 56\%. In a final step, a combination of a network and spatial clustering algorithm was built in order to create clusters, therein reducing the variety of possible trips. By only predicting the destination cluster instead of the exact location, it is possible to increase the performance to 75\% including all classes. A final set of components shows in two exemplary ways how to deduce additional inferences from the underlying spatio-temporal data. The first example presents a novel concept for predicting the 'potential memorisation index' for a certain location. The index is based on a cognitive model which derives the index from the user's activity data in that area. The second example embeds each location in its urban fabric and thereby enriches its cluster's metadata by further describing the temporal-semantic activity in an area (e.g. going to restaurants at noon). The success of the client-side classification and prediction approach, despite the challenges of inaccurate and imbalanced data, supports the claimed benefits of the client-side modelling concept. Since modern data-driven services at some point do need to receive user data, the thesis' computational model concludes with a concept for applying generalisation to semantic, temporal, and spatial data before sharing it with the remote service in order to comply with the overall goal to improve data privacy. In this context, the potentials of ensemble training (in regards to ANNs) are discussed in order to highlight the potential of only sharing the trained ANN instead of the raw input data. While the results of our evaluation support the assets of the proposed framework, there are two important downsides of our approach compared to server-side modelling. First, both of these server-side advantages are rooted in the server's access to multiple users' data. This allows a remote service to predict spatio-in the user-specific data, which represents the second downside. While minor classes will likely be minor classes in a bigger dataset as well, for each class, there will still be more variety than in the user-specific dataset. The author emphasises that the approach presented in this work holds the potential to change the privacy paradigm in modern data-driven services. Finding combinations of client- and server-side modelling could prove a promising new path for data-driven innovation. Beyond the technological perspective, throughout the thesis the author also offers a critical view on the data- and technology-driven development of this work. By introducing the client-side modelling with user-specific artificial neural networks, users generate their own algorithm. Those user-specific algorithms are influenced less by generalised biases or developers' prejudices. Therefore, the user develops a more diverse and individual perspective through his or her user model. This concept picks up the idea of critical cartography, which questions the status quo of how space is perceived and represented.}, language = {en} } @misc{GebserKaufmannSchaub2012, author = {Gebser, Martin and Kaufmann, Benjamin and Schaub, Torsten H.}, title = {Multi-threaded ASP solving with clasp}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, number = {586}, issn = {1866-8372}, doi = {10.25932/publishup-41397}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-413977}, pages = {21}, year = {2012}, abstract = {We present the new multi-threaded version of the state-of-the-art answer set solver clasp. We detail its component and communication architecture and illustrate how they support the principal functionalities of clasp. Also, we provide some insights into the data representation used for different constraint types handled by clasp. All this is accompanied by an extensive experimental analysis of the major features related to multi-threading in clasp.}, language = {en} } @misc{HoosKaminskiLindaueretal.2015, author = {Hoos, Holger and Kaminski, Roland and Lindauer, Marius and Schaub, Torsten H.}, title = {aspeed}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, number = {588}, issn = {1866-8372}, doi = {10.25932/publishup-41474}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-414743}, pages = {26}, year = {2015}, abstract = {Although Boolean Constraint Technology has made tremendous progress over the last decade, the efficacy of state-of-the-art solvers is known to vary considerably across different types of problem instances, and is known to depend strongly on algorithm parameters. This problem was addressed by means of a simple, yet effective approach using handmade, uniform, and unordered schedules of multiple solvers in ppfolio, which showed very impressive performance in the 2011 Satisfiability Testing (SAT) Competition. Inspired by this, we take advantage of the modeling and solving capacities of Answer Set Programming (ASP) to automatically determine more refined, that is, nonuniform and ordered solver schedules from the existing benchmarking data. We begin by formulating the determination of such schedules as multi-criteria optimization problems and provide corresponding ASP encodings. The resulting encodings are easily customizable for different settings, and the computation of optimum schedules can mostly be done in the blink of an eye, even when dealing with large runtime data sets stemming from many solvers on hundreds to thousands of instances. Also, the fact that our approach can be customized easily enabled us to swiftly adapt it to generate parallel schedules for multi-processor machines.}, language = {en} } @misc{GebserHarrisonKaminskietal.2015, author = {Gebser, Martin and Harrison, Amelia and Kaminski, Roland and Lifschitz, Vladimir and Schaub, Torsten H.}, title = {Abstract gringo}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, number = {592}, issn = {1866-8372}, doi = {10.25932/publishup-41475}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-414751}, pages = {15}, year = {2015}, abstract = {This paper defines the syntax and semantics of the input language of the ASP grounder gringo. The definition covers several constructs that were not discussed in earlier work on the semantics of that language, including intervals, pools, division of integers, aggregates with non-numeric values, and lparse-style aggregate expressions. The definition is abstract in the sense that it disregards some details related to representing programs by strings of ASCII characters. It serves as a specification for gringo from Version 4.5 on.}, language = {en} } @misc{GebserLeeLierler2011, author = {Gebser, Martin and Lee, Joohyung and Lierler, Yuliya}, title = {On elementary loops of logic programs}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, number = {566}, issn = {1866-8372}, doi = {10.25932/publishup-41309}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-413091}, pages = {36}, year = {2011}, abstract = {Using the notion of an elementary loop, Gebser and Schaub (2005. Proceedings of the Eighth International Conference on Logic Programming and Nonmonotonic Reasoning (LPNMR'05 ), 53-65) refined the theorem on loop formulas attributable to Lin and Zhao (2004) by considering loop formulas of elementary loops only. In this paper, we reformulate the definition of an elementary loop, extend it to disjunctive programs, and study several properties of elementary loops, including how maximal elementary loops are related to minimal unfounded sets. The results provide useful insights into the stable model semantics in terms of elementary loops. For a nondisjunctive program, using a graph-theoretic characterization of an elementary loop, we show that the problem of recognizing an elementary loop is tractable. On the other hand, we also show that the corresponding problem is coNP-complete for a disjunctive program. Based on the notion of an elementary loop, we present the class of Head-Elementary-loop-Free (HEF) programs, which strictly generalizes the class of Head-Cycle-Free (HCF) programs attributable to Ben-Eliyahu and Dechter (1994. Annals of Mathematics and Artificial Intelligence 12, 53-87). Like an HCF program, an HEF program can be turned into an equivalent nondisjunctive program in polynomial time by shifting head atoms into the body.}, language = {en} } @article{KaitouaRablMarkl2020, author = {Kaitoua, Abdulrahman and Rabl, Tilmann and Markl, Volker}, title = {A distributed data exchange engine for polystores}, series = {Information technology : methods and applications of informatics and information technology}, volume = {62}, journal = {Information technology : methods and applications of informatics and information technology}, number = {3-4}, publisher = {De Gruyter}, address = {Berlin}, issn = {1611-2776}, doi = {10.1515/itit-2019-0037}, pages = {145 -- 156}, year = {2020}, abstract = {There is an increasing interest in fusing data from heterogeneous sources. Combining data sources increases the utility of existing datasets, generating new information and creating services of higher quality. A central issue in working with heterogeneous sources is data migration: In order to share and process data in different engines, resource intensive and complex movements and transformations between computing engines, services, and stores are necessary. Muses is a distributed, high-performance data migration engine that is able to interconnect distributed data stores by forwarding, transforming, repartitioning, or broadcasting data among distributed engines' instances in a resource-, cost-, and performance-adaptive manner. As such, it performs seamless information sharing across all participating resources in a standard, modular manner. We show an overall improvement of 30 \% for pipelining jobs across multiple engines, even when we count the overhead of Muses in the execution time. This performance gain implies that Muses can be used to optimise large pipelines that leverage multiple engines.}, language = {en} } @article{DreselerBoissierRabletal.2020, author = {Dreseler, Markus and Boissier, Martin and Rabl, Tilmann and Uflacker, Matthias}, title = {Quantifying TPC-H choke points and their optimizations}, series = {Proceedings of the VLDB Endowment}, volume = {13}, journal = {Proceedings of the VLDB Endowment}, number = {8}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {2150-8097}, doi = {10.14778/3389133.3389138}, pages = {1206 -- 1220}, year = {2020}, abstract = {TPC-H continues to be the most widely used benchmark for relational OLAP systems. It poses a number of challenges, also known as "choke points", which database systems have to solve in order to achieve good benchmark results. Examples include joins across multiple tables, correlated subqueries, and correlations within the TPC-H data set. Knowing the impact of such optimizations helps in developing optimizers as well as in interpreting TPC-H results across database systems. This paper provides a systematic analysis of choke points and their optimizations. It complements previous work on TPC-H choke points by providing a quantitative discussion of their relevance. It focuses on eleven choke points where the optimizations are beneficial independently of the database system. Of these, the flattening of subqueries and the placement of predicates have the biggest impact. Three queries (Q2, Q17, and Q21) are strongly ifluenced by the choice of an efficient query plan; three others (Q1, Q13, and Q18) are less influenced by plan optimizations and more dependent on an efficient execution engine.}, 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} } @phdthesis{Makowski2021, author = {Makowski, Silvia}, title = {Discriminative Models for Biometric Identification using Micro- and Macro-Movements of the Eyes}, school = {Universit{\"a}t Potsdam}, pages = {xi, 91}, year = {2021}, abstract = {Human visual perception is an active process. Eye movements either alternate between fixations and saccades or follow a smooth pursuit movement in case of moving targets. Besides these macroscopic gaze patterns, the eyes perform involuntary micro-movements during fixations which are commonly categorized into micro-saccades, drift and tremor. Eye movements are frequently studied in cognitive psychology, because they reflect a complex interplay of perception, attention and oculomotor control. A common insight of psychological research is that macro-movements are highly individual. Inspired by this finding, there has been a considerable amount of prior research on oculomotoric biometric identification. However, the accuracy of known approaches is too low and the time needed for identification is too long for any practical application. This thesis explores discriminative models for the task of biometric identification. Discriminative models optimize a quality measure of the predictions and are usually superior to generative approaches in discriminative tasks. However, using discriminative models requires to select a suitable form of data representation for sequential eye gaze data; i.e., by engineering features or constructing a sequence kernel and the performance of the classification model strongly depends on the data representation. We study two fundamentally different ways of representing eye gaze within a discriminative framework. In the first part of this thesis, we explore the integration of data and psychological background knowledge in the form of generative models to construct representations. To this end, we first develop generative statistical models of gaze behavior during reading and scene viewing that account for viewer-specific distributional properties of gaze patterns. In a second step, we develop a discriminative identification model by deriving Fisher kernel functions from these and several baseline models. We find that an SVM with Fisher kernel is able to reliably identify users based on their eye gaze during reading and scene viewing. However, since the generative models are constrained to use low-frequency macro-movements, they discard a significant amount of information contained in the raw eye tracking signal at a high cost: identification requires about one minute of input recording, which makes it inapplicable for real world biometric systems. In the second part of this thesis, we study a purely data-driven modeling approach. Here, we aim at automatically discovering the individual pattern hidden in the raw eye tracking signal. To this end, we develop a deep convolutional neural network DeepEyedentification that processes yaw and pitch gaze velocities and learns a representation end-to-end. Compared to prior work, this model increases the identification accuracy by one order of magnitude and the time to identification decreases to only seconds. The DeepEyedentificationLive model further improves upon the identification performance by processing binocular input and it also detects presentation-attacks. We find that by learning a representation, the performance of oculomotoric identification and presentation-attack detection can be driven close to practical relevance for biometric applications. Eye tracking devices with high sampling frequency and precision are expensive and the applicability of eye movement as a biometric feature heavily depends on cost of recording devices. In the last part of this thesis, we therefore study the requirements on data quality by evaluating the performance of the DeepEyedentificationLive network under reduced spatial and temporal resolution. We find that the method still attains a high identification accuracy at a temporal resolution of only 250 Hz and a precision of 0.03 degrees. Reducing both does not have an additive deteriorating effect.}, language = {en} } @article{WahlHoelscher2018, author = {Wahl, Marina and H{\"o}lscher, Michael}, title = {Und am Wochenende Blended Learning}, series = {E-Learning Symposium 2018}, journal = {E-Learning Symposium 2018}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-42191}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-421910}, pages = {17 -- 27}, year = {2018}, abstract = {Berufsbegleitende Studieng{\"a}nge stehen vor besonderen Schwierigkeiten, f{\"u}r die der Einsatz von Blended Learning-Szenarien sinnvoll sein kann. Welche speziellen Herausforderungen sich dabei ergeben und welche L{\"o}sungsans{\"a}tze dagegen steuern, betrachtet der folgende Artikel anhand eines Praxisberichts aus dem Studiengang M. P. A. Wissenschaftsmanagement an der Universit{\"a}t Speyer.}, language = {de} } @article{GautamZhangLandwehretal.2021, author = {Gautam, Khem Raj and Zhang, Guoqiang and Landwehr, Niels and Adolphs, Julian}, title = {Machine learning for improvement of thermal conditions inside a hybrid ventilated animal building}, series = {Computers and electronics in agriculture : COMPAG online ; an international journal}, volume = {187}, journal = {Computers and electronics in agriculture : COMPAG online ; an international journal}, publisher = {Elsevier Science}, address = {Amsterdam [u.a.]}, issn = {0168-1699}, doi = {10.1016/j.compag.2021.106259}, pages = {10}, year = {2021}, abstract = {In buildings with hybrid ventilation, natural ventilation opening positions (windows), mechanical ventilation rates, heating, and cooling are manipulated to maintain desired thermal conditions. The indoor temperature is regulated solely by ventilation (natural and mechanical) when the external conditions are favorable to save external heating and cooling energy. The ventilation parameters are determined by a rule-based control scheme, which is not optimal. This study proposes a methodology to enable real-time optimum control of ventilation parameters. We developed offline prediction models to estimate future thermal conditions from the data collected from building in operation. The developed offline model is then used to find the optimal controllable ventilation parameters in real-time to minimize the setpoint deviation in the building. With the proposed methodology, the experimental building's setpoint deviation improved for 87\% of time, on average, by 0.53 degrees C compared to the current deviations.}, language = {en} } @inproceedings{OPUS4-39635, title = {11. Workshop Testmethoden und Zuverl{\"a}ssigkeit von Schaltungen und Systemen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-9806494-1-4}, pages = {137 Seiten}, year = {1999}, language = {de} } @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} } @book{Mueller2017, author = {M{\"u}ller, Dorothee}, title = {Der Berufswahlprozess von Informatiklehrkr{\"a}ften}, number = {11}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-392-3}, issn = {1868-0844}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-101819}, publisher = {Universit{\"a}t Potsdam}, pages = {xiv, 299}, year = {2017}, abstract = {Seit Jahren ist der Mangel an Informatiklehrkr{\"a}ften bekannt und wird fachdidaktisch und politisch diskutiert. Aufgrund der geringen Anzahl von Studierenden mit dem Berufsziel Informatiklehrkraft ist eine Vergr{\"o}ßerung des Mangels vorhersehbar. Es stellt sich die Frage, warum so wenige Studierende sich f{\"u}r das Studienziel Lehramt Informatik entscheiden. Das Ziel der vorliegenden Arbeit ist es, die Berufswahl von Informatiklehrkr{\"a}ften aus der individuellen, biographischen Perspektive der Beteiligten zu erforschen und dabei Faktoren zu identifizieren, die die Berufswahl Informatiklehrkraft positiv oder negativ beeinflussen. Der Forschungsschwerpunkt liegt auf der qualitativen empirischen Untersuchung des Berufswahlprozesses, w{\"a}hrend eine quantitative Befragung aktiver Informatiklehrkr{\"a}fte zu berufswahlrelevanten Aspekten des Berufsbildes diese erg{\"a}nzt. Das Forschungskonzept der qualitativen Untersuchung orientiert sich an der Grounded Theory. Es wurden angehende Informatiklehrkr{\"a}fte zu ihrem Berufswahlprozess befragt, wobei die Daten durch m{\"u}ndliche Interviews, Gruppendiskussionen und schriftliche Berufswahlbiographien erhoben wurden. Die Datenauswertung orientiert sich zudem methodisch an der dokumentarischen Methode nach Ralf Bohnsack. Die Ergebnisse der Untersuchung zeigen, dass der Berufswahlprozess von angehenden Informatiklehrkr{\"a}ften h{\"a}ufig mit Umwegen in Form von Studienzielwechseln verbunden ist. Neben dem eigenen Bild der Informatik und dem Informatikselbstkonzept kommt dem Informatikunterricht der eigenen Schulzeit eine wichtige Rolle in diesem Prozess zu. Von der Lehrerforschung werden die Unterrichtserfahrungen w{\"a}hrend der eigenen Schulzeit im sp{\"a}ter studierten Fach als entscheidend f{\"u}r die Fachwahl identifiziert. Dies best{\"a}tigt sich in den Berufswahlbiographien derjenigen angehenden Informatiklehrkr{\"a}fte, die den Informatikunterricht ihrer eigenen Schulzeit positiv erinnern. Diese streben meist direkt in ihrem ersten Studium das Berufsziel Informatiklehrkraft an. Sie hatten zur Schulzeit ein positives Bild der Informatik und ein hohes Informatikselbstkonzept. Der Informatiklehrkraft ihrer Schulzeit bescheinigen sie oft eine berufliche Vorbildfunktion. Allerdings hatten die meisten der befragten angehenden Informatiklehrkr{\"a}fte selbst keinen Informatikunterricht oder erinnern diesen negativ. Der Weg zum Studium Informatiklehrkraft f{\"u}hrt bei diesen Befragten h{\"a}ufig {\"u}ber den Umweg von zun{\"a}chst anderen Studienentscheidungen, meistens {\"u}ber ein Lehramtsstudium mit anderen F{\"a}chern oder ein Informatikstudium. Die Informatikstudierenden haben zum Zeitpunkt ihrer ersten Studienwahl ein positives Bild der Informatik und ein hohes Informatikselbstkonzept aber kein positives Berufsbild Informatiklehrkraft. Ihr Wechsel von einem Informatikstudium zum Studium mit dem Berufsziel Informatiklehrkraft wird in der Regel durch den Wunsch nach einer st{\"a}rkeren sozialen Komponente im sp{\"a}teren Berufsalltag ausgel{\"o}st. Bei den Lehramtsstudierenden, die h{\"a}ufig zun{\"a}chst ein niedriges Informatikselbstkonzept und/oder ein negatives Bild der Informatik haben, kann es zu einer Umorientierung hin zum Studienziel Informatiklehrkraft kommen, wenn diese Vorstellungen sich w{\"a}hrend des ersten Studiums - z. B. durch den Besuch von universit{\"a}ren Lehrveranstaltungen zu informatischen Inhalten - {\"a}ndern. Die letztliche Entscheidung f{\"u}r den Beruf Informatiklehrkraft wird von denjenigen, die ihr Studienziel wechselten, mit Recht als durch Zuf{\"a}lle bestimmt empfunden.}, language = {de} } @inproceedings{KeilKonertDamniketal.2018, author = {Keil, Reinhard and Konert, Johannes and Damnik, Gregor and Gierl, Mark J. and Proske, Antje and K{\"o}rndle, Hermann and Narciss, Susanne and Wahl, Marina and H{\"o}lscher, Michael and Mariani, Ennio and Jaisli, Isabel and Tscherejkina, Anna and Morgiel, Anna and Moebert, Tobias and Herbstreit, Stephanie and M{\"a}ker, Daniela and Szalai, Cynthia and Braun, Iris and Kapp, Felix and Hara, Tenshi C. and Kubica, Tommy and Stumpf, Sarah}, title = {E-Learning Symposium 2018}, editor = {Lucke, Ulrike and Strickroth, Sven}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-42071}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-420711}, pages = {71}, year = {2018}, abstract = {In den vergangenen Jahren sind viele E-Learning-Innovationen entstanden. Einige davon wurden auf den vergangenen E-Learning Symposien der Universit{\"a}t Potsdam pr{\"a}sentiert: Das erste E-Learning Symposium im Jahr 2012 konzentrierte sich auf unterschiedliche M{\"o}glichkeiten der Studierendenaktivierung und Lehrgestaltung. Das Symposium 2014 r{\"u}ckte vor allem die Studierenden ins Zentrum der Aufmerksamkeit. Im Jahr 2016 kam es durch das Zusammengehen des Symposiums mit der DeLFI-Tagung zu einer Fokussierung auf technische Innovationen. Doch was ist aus den Leuchtt{\"u}rmen von gestern geworden, und brauchen wir {\"u}berhaupt noch neue Leuchtt{\"u}rme? Das Symposium setzt sich in diesem Jahr unter dem Motto „Innovation und Nachhaltigkeit - (k)ein Gegensatz?" mit mediengest{\"u}tzten Lehr- und Lernprozessen im universit{\"a}ren Kontext auseinander und reflektiert aktuelle technische sowie didaktische Entwicklungen mit Blick auf deren mittel- bis langfristigen Einsatz in der Praxis. Dieser Tagungsband zum E-Learning Symposium 2018 an der Universit{\"a}t Potsdam beinhaltet eine Mischung von Forschungs- und Praxisbeitr{\"a}gen aus verschiedenen Fachdisziplinen und er{\"o}ffnet vielschichtige Perspektiven auf das Thema E-Learning. Dabei werden die Vielfalt der didaktischen Einsatzszenarien als auch die Potentiale von Werk-zeugen und Methoden der Informatik in ihrem Zusammenspiel beleuchtet. In seiner Keynote widmet sich Reinhard Keil dem Motto des Symposiums und geht der Nachhaltigkeit bei E-Learning-Projekten auf den Grund. Dabei analysiert und beleuchtet er anhand seiner {\"u}ber 15-j{\"a}hrigen Forschungspraxis die wichtigsten Wirkfaktoren und formuliert Empfehlungen zur Konzeption von E-Learning-Projekten. Im Gegensatz zu rein auf Kostenersparnis ausgerichteten (hochschul-)politischen Forderungen proklamiert er den Ansatz der hypothesengeleiteten Technikgestaltung, in der Nachhaltigkeit als Leitfrage oder Forschungsstrategie verstanden werden kann. In eine {\"a}hnliche Richtung geht der Beitrag von Iris Braun et al., die {\"u}ber Erfolgsfaktoren beim Einsatz von Audience Response Systemen in der universit{\"a}ren Lehre berichten. Ein weiteres aktuelles Thema, sowohl f{\"u}r die Bildungstechnologie als auch in den Bildungswissenschaften allgemein, ist die Kompetenzorientierung und -modellierung. Hier geht es darum (Probleml{\"o}se-)F{\"a}higkeiten gezielt zu beschreiben und in den Mittelpunkt der Lehre zu stellen. Johannes Konert stellt in einem eingeladenen Vortrag zwei Projekte vor, die den Prozess beginnend bei der Definition von Kompetenzen, deren Modellierung in einem semantischen maschinenlesbaren Format bis hin zur Erarbeitung von Methoden zur Kompetenzmessung und der elektronischen Zertifizierung aufzeigen. Dabei geht er auf technische M{\"o}glichkeiten, aber auch Grenzen ein. Auf einer spezifischeren Ebene besch{\"a}ftigt sich Sarah Stumpf mit digitalen bzw. mediendidaktischen Kompetenzen im Lehramtsstudium und stellt ein Framework f{\"u}r die F{\"o}rderung ebensolcher Kompetenzen bei angehenden Lehrkr{\"a}ften vor. Der Einsatz von E-Learning birgt noch einige Herausforderungen. Dabei geht es oft um die Verbindung von Didaktik und Technik, den Erhalt von Aufmerksamkeit oder den Aufwand f{\"u}r das Erstellen von interaktiven Lehr- und Lerninhalten. Drei Beitr{\"a}ge in diesem Tagungsband besch{\"a}ftigen sich mit dieser Thematik in unterschiedlichen Kontexten und zeigen Best-Practices und L{\"o}sungsans{\"a}tze auf: Der Beitrag von Martina Wahl und Michael H{\"o}lscher behandelt den besonderen Kontext von Blended Learning-Szenarien in berufsbegleitenden Studieng{\"a}ngen. Um die Ver{\"o}ffentlichung eines global frei verf{\"u}gbaren Onlinekurses abseits der großen MOOC Plattformen und den didaktischen Herausforderungen auch hinsichtlich der Motivation geht es im Beitrag von Ennio Marani und Isabel Jaisli. Schließlich schlagen Gregor Damnik et al. die automatische Erzeugung von Aufgaben zur Erh{\"o}hung von Interaktivit{\"a}t und Adaptivit{\"a}t in digitalen Lernressourcen vor, um den teilweise erheblichen Erstellungsaufwand zu reduzieren. Zum Thema E-Learning z{\"a}hlen auch immer mobile Apps bzw. Spiele. Gleich zwei Beitr{\"a}ge besch{\"a}ftigen sich mit dem Einsatz von E-Learning-Tools im Gesundheitskontext: Anna Tscherejkina und Anna Morgiel stellen in ihrem Beitrag Minispiele zum Training von sozio-emotionalen Kompetenzen f{\"u}r Menschen mit Autismus vor, und Stephanie Herbstreit et al. berichten vom Einsatz einer mobilen Lern-App zur Verbesserung von klinisch-praktischem Unterricht.}, language = {de} } @inproceedings{SeegererRomeikeTillmannetal.2018, author = {Seegerer, Stefan and Romeike, Ralf and Tillmann, Alexander and Kr{\"o}mker, Detlef and Horn, Florian and Gattinger, Thorsten and Weicker, Karsten and Schmitz, Dennis and Moldt, Daniel and R{\"o}pke, Ren{\´e} and Larisch, Kathrin and Schroeder, Ulrik and Keverp{\"u}tz, Claudia and K{\"u}ppers, Bastian and Striewe, Michael and Kramer, Matthias and Grillenberger, Andreas and Frede, Christiane and Knobelsdorf, Maria and Greven, Christoph}, title = {Hochschuldidaktik der Informatik HDI 2018}, series = {Commentarii informaticae didacticae (CID)}, booktitle = {Commentarii informaticae didacticae (CID)}, number = {12}, editor = {Bergner, Nadine and R{\"o}pke, Ren{\´e} and Schroeder, Ulrik and Kr{\"o}mker, Detlef}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-435-7}, issn = {1868-0844}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-413542}, pages = {161}, year = {2018}, abstract = {Die 8. Fachtagung f{\"u}r Hochschuldidaktik der Informatik (HDI) fand im September 2018 zusammen mit der Deutschen E-Learning Fachtagung Informatik (DeLFI) unter dem gemeinsamen Motto „Digitalisierungswahnsinn? - Wege der Bildungstransformationen" in Frankfurt statt. Dabei widmet sich die HDI allen Fragen der informatischen Bildung im Hochschulbereich. Schwerpunkte bildeten in diesem Jahr u. a.: - Analyse der Inhalte und anzustrebenden Kompetenzen in Informatikveranstaltungen - Programmieren lernen \& Einstieg in Softwareentwicklung - Spezialthemen: Data Science, Theoretische Informatik und Wissenschaftliches Arbeiten Die Fachtagung widmet sich ausgew{\"a}hlten Fragestellungen dieser Themenkomplexe, die durch Vortr{\"a}ge ausgewiesener Experten und durch eingereichte Beitr{\"a}ge intensiv behandelt werden.}, language = {de} } @article{BorchertMockTomczaketal.2021, author = {Borchert, Florian and Mock, Andreas and Tomczak, Aurelie and H{\"u}gel, Jonas and Alkarkoukly, Samer and Knurr, Alexander and Volckmar, Anna-Lena and Stenzinger, Albrecht and Schirmacher, Peter and Debus, J{\"u}rgen and J{\"a}ger, Dirk and Longerich, Thomas and Fr{\"o}hling, Stefan and Eils, Roland and Bougatf, Nina and Sax, Ulrich and Schapranow, Matthieu-Patrick}, title = {Correction to: Knowledge bases and software support for variant interpretation in precision oncology}, series = {Briefings in bioinformatics}, volume = {22}, journal = {Briefings in bioinformatics}, number = {6}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1467-5463}, doi = {10.1093/bib/bbab246}, pages = {1}, year = {2021}, 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{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} } @inproceedings{GonnermannTeichmann2023, author = {Gonnermann, Jana and Teichmann, Malte}, title = {Influence of pre-experience on learning, usability and cognitive load in a virtual learning environment}, series = {Americas conference on information systems}, booktitle = {Americas conference on information systems}, number = {1871}, publisher = {AIS}, address = {Atlanta}, year = {2023}, abstract = {Virtual reality can have advantages for education and learning. However, it must be adequately designed so that the learner benefits from the technological possibilities. Understanding the underlying effects of the virtual learning environment and the learner's prior experience with virtual reality or prior knowledge of the content is necessary to design a proper virtual learning environment. This article presents a pre-study testing the design of a virtual learning environment for engineering vocational training courses. In the pre-study, 12 employees of two companies joined the training course in one of the two degrees of immersion (desktop VR and VR HMD). Quantitative results on learning success, cognitive load, usability, and motivation and qualitative learning process data were presented. The qualitative data assessment shows that overall, the employees were satisfied with the learning environment regardless of the level of immersion and that the participants asked for more guidance and structure accompanying the learning process. Further research is needed to test for solid group differences.}, language = {en} } @article{CombiOliboniWeskeetal.2021, author = {Combi, Carlo and Oliboni, Barbara and Weske, Mathias and Zerbato, Francesca}, title = {Seamless conceptual modeling of processes with transactional and analytical data}, series = {Data \& knowledge engineering}, volume = {134}, journal = {Data \& knowledge engineering}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0169-023X}, doi = {10.1016/j.datak.2021.101895}, pages = {14}, year = {2021}, abstract = {In the field of Business Process Management (BPM), modeling business processes and related data is a critical issue since process activities need to manage data stored in databases. The connection between processes and data is usually handled at the implementation level, even if modeling both processes and data at the conceptual level should help designers in improving business process models and identifying requirements for implementation. Especially in data -and decision-intensive contexts, business process activities need to access data stored both in databases and data warehouses. In this paper, we complete our approach for defining a novel conceptual view that bridges process activities and data. The proposed approach allows the designer to model the connection between business processes and database models and define the operations to perform, providing interesting insights on the overall connected perspective and hints for identifying activities that are crucial for decision support.}, language = {en} } @article{Schladebach2022, author = {Schladebach, Marcus}, title = {Satelliten-Megakonstellationen im Weltraumrecht}, series = {Kommunikation \& Recht : K \& R / Beihefter}, journal = {Kommunikation \& Recht : K \& R / Beihefter}, number = {2}, publisher = {dfv-Mediengruppe}, address = {Frankfurt am Main}, issn = {1434-6354}, pages = {26 -- 29}, year = {2022}, language = {de} } @article{KoerppenUllrichBertheau2021, author = {K{\"o}rppen, Tim and Ullrich, Andr{\´e} and Bertheau, Clementine}, title = {Durchblick statt Bauchgef{\"u}hl - Transformation zur Data-Driven Organization}, series = {Wirtschaftsinformatik \& Management}, volume = {13}, journal = {Wirtschaftsinformatik \& Management}, number = {6}, publisher = {Springer Gabler}, address = {Wiesbaden}, issn = {1867-5905}, doi = {10.1365/s35764-021-00370-7}, pages = {452 -- 459}, year = {2021}, abstract = {Um in der digitalisierten Wirtschaft mitzuspielen, m{\"u}ssen Unternehmen, Markt und insbesondere Kunden detailliert verstanden werden. Neben den „Big Playern" aus dem Silicon Valley sieht der deutsche Mittelstand, der zu großen Teilen noch auf gewachsenen IT-Infrastrukturen und Prozessen agiert, oft alt aus. Um in den n{\"a}chsten Jahren nicht g{\"a}nzlich abgeh{\"a}ngt zu werden, ist ein Umbruch notwendig. Sowohl Leistungserstellungsprozesse als auch Leistungsangebot m{\"u}ssen transparent und datenbasiert ausgerichtet werden. Nur so k{\"o}nnen Gesch{\"a}ftsvorf{\"a}lle, das Marktgeschehen sowie Handeln der Akteure integrativ bewertet und fundierte Entscheidungen getroffen werden. In diesem Beitrag wird das Konzept der Data-Driven Organization vorgestellt und aufgezeigt, wie Unternehmen den eigenen Analyticsreifegrad ermitteln und in einem iterativen Transformationsprozess steigern k{\"o}nnen.}, language = {de} } @article{UllrichTeichmannGronau2021, author = {Ullrich, Andr{\´e} and Teichmann, Malte and Gronau, Norbert}, title = {Fast trainable capabilities in software engineering-skill development in learning factories}, series = {Ji suan ji jiao yu = Computer Education / Qing hua da xue}, journal = {Ji suan ji jiao yu = Computer Education / Qing hua da xue}, number = {12}, publisher = {[Verlag nicht ermittelbar]}, address = {Bei jing shi}, issn = {1672-5913}, doi = {10.16512/j.cnki.jsjjy.2020.12.002}, pages = {2 -- 10}, year = {2021}, abstract = {The increasing demand for software engineers cannot completely be fulfilled by university education and conventional training approaches due to limited capacities. Accordingly, an alternative approach is necessary where potential software engineers are being educated in software engineering skills using new methods. We suggest micro tasks combined with theoretical lessons to overcome existing skill deficits and acquire fast trainable capabilities. This paper addresses the gap between demand and supply of software engineers by introducing an actionoriented and scenario-based didactical approach, which enables non-computer scientists to code. Therein, the learning content is provided in small tasks and embedded in learning factory scenarios. Therefore, different requirements for software engineers from the market side and from an academic viewpoint are analyzed and synthesized into an integrated, yet condensed skills catalogue. This enables the development of training and education units that focus on the most important skills demanded on the market. To achieve this objective, individual learning scenarios are developed. Of course, proper basic skills in coding cannot be learned over night but software programming is also no sorcery.}, language = {en} } @book{BarkowskyGiese2023, author = {Barkowsky, Matthias and Giese, Holger}, title = {Triple graph grammars for multi-version models}, number = {155}, isbn = {978-3-86956-556-9}, issn = {1613-5652}, doi = {10.25932/publishup-57399}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-573994}, publisher = {Universit{\"a}t Potsdam}, pages = {28 -- 28}, year = {2023}, abstract = {Like conventional software projects, projects in model-driven software engineering require adequate management of multiple versions of development artifacts, importantly allowing living with temporary inconsistencies. In the case of model-driven software engineering, employed versioning approaches also have to handle situations where different artifacts, that is, different models, are linked via automatic model transformations. In this report, we propose a technique for jointly handling the transformation of multiple versions of a source model into corresponding versions of a target model, which enables the use of a more compact representation that may afford improved execution time of both the transformation and further analysis operations. Our approach is based on the well-known formalism of triple graph grammars and a previously introduced encoding of model version histories called multi-version models. In addition to showing the correctness of our approach with respect to the standard semantics of triple graph grammars, we conduct an empirical evaluation that demonstrates the potential benefit regarding execution time performance.}, language = {en} } @article{BaberowskiLeonhardtRentschetal.2023, author = {Baberowski, David and Leonhardt, Thiemo and Rentsch, Susanne and Bergner, Nadine}, title = {Aufbau informatischer Kompetenzen im Kontext KI bei Lehramtsstudierenden des Faches Politik}, series = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)}, journal = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)}, number = {13}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-548-4}, issn = {1868-0844}, doi = {10.25932/publishup-61599}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-615995}, pages = {189 -- 209}, year = {2023}, abstract = {Lehrkr{\"a}fte aller F{\"a}cher ben{\"o}tigen informatische Kompetenzen, um der wachsenden Alltagsrelevanz von Informatik und aktuell g{\"u}ltigen Lehrpl{\"a}nen gerecht zu werden. Beispielsweise verweist in Sachsen der Lehrplan f{\"u}r das Fach Gemeinschaftskunde, Rechtserziehung und Wirtschaft am Gymnasium mit dem f{\"u}r die Jahrgangsstufe 11 vorgesehenem Thema „Digitalisierung und sozialer Wandel" auf K{\"u}nstliche Intelligenz (KI) und explizit auf die Bedeutung der informatischen Bildung. Um die n{\"o}tigen informatischen Grundlagen zu vermitteln, wurde f{\"u}r Lehramtsstudierende des Faches Politik ein Workshop erarbeitet, der die Grundlagen der Funktionsweise von KI anhand von {\"u}berwachtem maschinellen Lernen in neuronalen Netzen vermittelt. Inhalt des Workshops ist es, mit Bezug auf gesellschaftliche Implikationen wie Datenschutz bei Trainingsdaten und algorithmic bias einen informierten Diskurs zu politischen Themen zu erm{\"o}glichen. Ziele des Workshops f{\"u}r Lehramtsstudierende mit dem Fach Politik sind: (1) Aufbau informatischer Kompetenzen in Bezug zum Thema KI, (2) St{\"a}rkung der Diskussionsf{\"a}higkeiten der Studierenden durch passende informatische Kompetenzen und (3) Anregung der Studierenden zum Transfer auf passende Themenstellungen im Politikunterricht. Das Evaluationskonzept umfasst eine Pre-Post-Befragung zur Zuversicht zur Vermittlungskompetenz unter Bezug auf maschinelles Lernen in neuronalen Netzen im Unterricht, sowie die Analyse einer abschließenden Diskussion. F{\"u}r die Pre-Post-Befragung konnte eine Steigerung der Zuversicht zur Vermittlungskompetenz beobachtet werden. Die Analyse der Diskussion zeigte das Bewusstsein der Alltagsrelevanz des Themas KI bei den Teilnehmenden, aber noch keine Anwendung der informatischen Inhalte des Workshops zur St{\"u}tzung der Argumente in der Diskussion.}, language = {de} } @article{ThorbrueggeDeselSchaefer2023, author = {Thorbr{\"u}gge, Carsten and Desel, J{\"o}rg and Sch{\"a}fer, Len Ole}, title = {Vorqualifikationen und Anerkennungsoptionen im Informatikstudium}, series = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)}, journal = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)}, number = {13}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-548-4}, issn = {1868-0844}, doi = {10.25932/publishup-61394}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-613942}, pages = {73 -- 89}, year = {2023}, abstract = {Viele Informatikstudierende sammeln bereits vor ihrem Studium berufliche Erfahrungen im Informatikbereich, ohne dass diese inhaltlich und didaktisch im Studium ber{\"u}cksichtigt werden. Dieser Beitrag geht der Frage nach, welche Kompetenzen aus beruflichen Vorqualifikationen bei Informatikstudierenden existieren und wie diese in Bezug zu Anerkennungsoptionen gesetzt werden k{\"o}nnen. Betrachtet werden: die pauschale Anerkennung, die auf erworbenen Zertifikaten beruht; die individuelle Anerkennung, bei der individuell erworbene Kompetenzen nachgewiesen werden; die Adaption von individuellen Lernwegen, die Teilkompetenzen der Studierenden ber{\"u}cksichtigt. Es wird eine Interviewstudie vorgestellt, in der Kompetenzen f{\"u}r ein Sample von Informatikstudierenden mit Vorqualifikation als Fachinformatiker/in erhoben und eine Zuordnung zu den Anerkennungsoptionen vorgenommen wurde. F{\"u}r die pr{\"a}zisere Gestaltung von Anerkennungsprozessen und zur kritischen Reflexion der eingesetzten hochschuldidaktischen Konzepte wurde eine empirische Basis geschaffen. Die vorhandenen Konzepte richten sich traditionell an Abiturienten/ innen mit sehr geringem Informatikhintergrund und ber{\"u}cksichtigen die tats{\"a}chlich existierende Heterogenit{\"a}t der Studienanf{\"a}nger/innen nicht angemessen. Die Ergebnisse zeigen, dass die Befragten aus ihrer Vorqualifikation relevante fachliche Kompetenzen mitbringen, die mit den Anerkennungsoptionen korrespondieren und deren Weiterentwicklung dienen k{\"o}nnen. Dar{\"u}ber hinaus werden aus {\"u}berfachlichen Kompetenzen wie Selbststeuerungskompetenzen weitere Erkenntnisse zur Studiengestaltung gewonnen.}, language = {de} } @article{MarxFreundlichKlotzetal.2021, author = {Marx, Susanne and Freundlich, Heidi and Klotz, Michael and Kyl{\"a}nen, Mika and Niedoszytko, Grazyna and Swacha, Jakub and Vollerthum, Anne}, title = {Towards an Online Learning Community on Digitalization in Tourism}, series = {EMOOCs 2021}, journal = {EMOOCs 2021}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51598}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-515986}, pages = {9}, year = {2021}, abstract = {Information technology and digital solutions as enablers in the tourism sector require continuous development of skills, as digital transformation is characterized by fast change, complexity and uncertainty. This research investigates how a cMOOC concept could support the tourism industry. A consortium of three universities, a tourism association, and a tourist attraction investigates online learning needs and habits of tourism industry stakeholders in the field of digitalization in a cross-border study in the Baltic Sea region. The multi-national survey (n = 244) reveals a high interest in participating in an online learning community, with two-thirds of respondents seeing opportunities to contributing to such community apart from consuming knowledge. The paper demonstrates preferred ways of learning, motivational and hampering aspects as well as types of possible contributions.}, language = {en} } @article{Weicker2023, author = {Weicker, Karsten}, title = {Peer-Review als Katalysator im Lernprozess}, series = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)}, journal = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)}, number = {13}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-548-4}, issn = {1868-0844}, doi = {10.25932/publishup-61602}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-616025}, pages = {257 -- 277}, year = {2023}, abstract = {Peer-Reviews werden seit geraumer Zeit in unterschiedlichen Lehrszenarien eingesetzt. In diesem Paper wird untersucht, inwieweit das Peer- Review die Auseinandersetzung mit den Inhalten eines Grundlagenmoduls in einem pr{\"a}senzfreien Lehrszenario bef{\"o}rdern kann. Dabei scheint in den Ergebnissen die Qualit{\"a}t der selbst erstellten Reviews einer der wichtigsten Einflussfaktoren f{\"u}r den Lernerfolg zu sein, w{\"a}hrend Experten-Feedback und weitere Faktoren deutlich untergeordnet erscheinen. Die F{\"a}higkeit ausf{\"u}hrliche Peer-Reviews zu verfassen geht einher mit dem Erwerb von fachlicher Kompetenz bzw. entsprechenden fachlichen Vorkenntnissen.}, language = {de} } @article{OpelNetzerDesel2023, author = {Opel, Simone and Netzer, Cajus Marian and Desel, J{\"o}rg}, title = {Adaption von Lernwegen in adaptierten Lehrmaterialien f{\"u}r Studierende mit Berufsausbildungsabschluss}, series = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)}, journal = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)}, number = {13}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-548-4}, issn = {1868-0844}, doi = {10.25932/publishup-61418}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-614188}, pages = {91 -- 114}, year = {2023}, abstract = {Obwohl immer mehr Menschen nicht direkt ein Studium aufnehmen, sondern zuvor eine berufliche Ausbildung absolvieren, werden die in der Ausbildung erworbenen Kompetenzen von den Hochschulen inhaltlich und didaktisch meist ignoriert. Ein Ansatz, diese Kompetenzen zu w{\"u}rdigen, ist die formale Anrechnung von mitgebrachten Kompetenzen als (f{\"u}r den Studienabschluss erforderliche) Leistungspunkte. Eine andere Variante ist der Einsatz von speziell f{\"u}r die Zielgruppe der Studierenden mit Vorkenntnissen adaptiertem Lehr-Lernmaterial. Um dar{\"u}ber hinaus individuelle Unterschiede zu ber{\"u}cksichtigen, erlaubt eine weitere Adaption individueller Lernpfade den Lernenden, genau die jeweils fehlenden Kompetenzen zu erwerben. In diesem Beitrag stellen wir die exemplarische Entwicklung derartigen Materials anhand des Kurses „Datenbanken" f{\"u}r die Zielgruppe der Studierenden mit einer abgeschlossenen Ausbildung zum Fachinformatiker bzw. zur Fachinformatikerin vor.}, language = {de} } @article{Weber2023, author = {Weber, Gerhard}, title = {Informatik und Barrierefreiheit}, series = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)}, journal = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)}, number = {13}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-548-4}, issn = {1868-0844}, doi = {10.25932/publishup-61387}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-613874}, pages = {35 -- 50}, year = {2023}, abstract = {Barrierefreiheit kann durch Methoden der Informatik hergestellt und ausgebaut werden. Dieser eingeladene Beitrag stellt die Anforderungen von Menschen mit den umfangreichsten Benutzererfordernissen an Software vor, die z. B. eigene Schriftsysteme wie Braille und entsprechende taktile Ausgabeger{\"a}te verwenden. Assistive Technologien umfassen dabei auch Software verschiedenster Art. Es werden die wichtigsten Kompetenzen daf{\"u}r vorgestellt. Im Curriculum der Informatik k{\"o}nnen diese Kompetenzen im Rahmen von speziellen Vorlesungen und {\"U}bungen vermittelt werden oder sie werden in die jeweiligen Fachgebiete integriert. Um den Studienbetrieb ebenfalls barrierefrei zu gestalten, sind weitere Anstrengungen notwendig, die Lehrende, Verwaltung und die Hochschulleitung einbeziehen.}, language = {de} } @article{SchellSchwill2023, author = {Schell, Timon and Schwill, Andreas}, title = {„Es ist kompliziert, alles inklusive Privatleben unter einen Hut zu bekommen"}, series = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)}, journal = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)}, number = {13}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-548-4}, issn = {1868-0844}, doi = {10.25932/publishup-61388}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-613882}, pages = {53 -- 71}, year = {2023}, abstract = {Eine {\"u}bliche Erz{\"a}hlung verkn{\"u}pft lange Studienzeiten und hohe Abbrecherquoten im Informatikstudium zum einen mit der sehr gut bezahlten Nebent{\"a}tigkeit von Studierenden in der Informatikbranche, die deutlich studienzeitverl{\"a}ngernd sei; zum anderen werde wegen des hohen Bedarfs an Informatikern ein formeller Studienabschluss von den Studierenden h{\"a}ufig als entbehrlich betrachtet und eine Karriere in der Informatikbranche ohne abgeschlossenes Studium begonnen. In dieser Studie, durchgef{\"u}hrt an der Universit{\"a}t Potsdam, untersuchen wir, wie viele Informatikstudierende neben dem Studium innerhalb und außerhalb der Informatikbranche arbeiten, welche Erwartungen sie neben der Bezahlung damit verbinden und wie sich die T{\"a}tigkeit auf ihr Studium und ihre sp{\"a}tere berufliche Perspektive auswirkt. Aus aktuellem Anlass interessieren uns auch die Auswirkungen der Covid-19-Pandemie auf die Arbeitst{\"a}tigkeiten der Informatikstudierenden.}, language = {de} } @article{RoostapourNeumannNeumannetal.2022, author = {Roostapour, Vahid and Neumann, Aneta and Neumann, Frank and Friedrich, Tobias}, title = {Pareto optimization for subset selection with dynamic cost constraints}, series = {Artificial intelligence}, volume = {302}, journal = {Artificial intelligence}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0004-3702}, doi = {10.1016/j.artint.2021.103597}, pages = {17}, year = {2022}, abstract = {We consider the subset selection problem for function f with constraint bound B that changes over time. Within the area of submodular optimization, various greedy approaches are commonly used. For dynamic environments we observe that the adaptive variants of these greedy approaches are not able to maintain their approximation quality. Investigating the recently introduced POMC Pareto optimization approach, we show that this algorithm efficiently computes a phi=(alpha(f)/2)(1 - 1/e(alpha)f)-approximation, where alpha(f) is the submodularity ratio of f, for each possible constraint bound b <= B. Furthermore, we show that POMC is able to adapt its set of solutions quickly in the case that B increases. Our experimental investigations for the influence maximization in social networks show the advantage of POMC over generalized greedy algorithms. We also consider EAMC, a new evolutionary algorithm with polynomial expected time guarantee to maintain phi approximation ratio, and NSGA-II with two different population sizes as advanced multi-objective optimization algorithm, to demonstrate their challenges in optimizing the maximum coverage problem. Our empirical analysis shows that, within the same number of evaluations, POMC is able to perform as good as NSGA-II under linear constraint, while EAMC performs significantly worse than all considered algorithms in most cases.}, language = {en} } @inproceedings{KrasnovaGundlachBaumann2022, author = {Krasnova, Hanna and Gundlach, Jana and Baumann, Annika}, title = {Coming back for more}, series = {PACIS 2022 proceedings}, booktitle = {PACIS 2022 proceedings}, publisher = {AIS Electronic Library (AISeL)}, address = {[Erscheinungsort nicht ermittelbar]}, isbn = {9781958200018}, year = {2022}, abstract = {Recent spikes in social networking site (SNS) usage times have launched investigations into reasons for excessive SNS usage. Extending research on social factors (i.e., fear of missing out), this study considers the News Feed setup. More specifically, we suggest that the order of the News Feed (chronological vs. algorithmically assembled posts) affects usage behaviors. Against the background of the variable reward schedule, this study hypothesizes that the different orders exert serendipity differently. Serendipity, termed as unexpected lucky encounters with information, resembles variable rewards. Studies have evidenced a relation between variable rewards and excessive behaviors. Similarly, we hypothesize that order-induced serendipitous encounters affect SNS usage times and explore this link in a two-wave survey with an experimental setup (users using either chronological or algorithmic News Feeds). While theoretically extending explanations for increased SNS usage times by considering the News Feed order, practically the study will offer recommendations for relevant stakeholders.}, language = {en} } @inproceedings{AbramovaGundlachBilda2021, author = {Abramova, Olga and Gundlach, Jana and Bilda, Juliane}, title = {Understanding the role of newsfeed clutter in stereotype activation}, series = {PACIS 2021 proceedings}, booktitle = {PACIS 2021 proceedings}, number = {473}, publisher = {AIS Electronic Library (AISeL)}, address = {[Erscheinungsort nicht ermittelbar]}, isbn = {978-1-7336325-7-7}, year = {2021}, abstract = {Despite the phenomenal growth of Big Data Analytics in the last few years, little research is done to explicate the relationship between Big Data Analytics Capability (BDAC) and indirect strategic value derived from such digital capabilities. We attempt to address this gap by proposing a conceptual model of the BDAC - Innovation relationship using dynamic capability theory. The work expands on BDAC business value research and extends the nominal research done on BDAC - innovation. We focus on BDAC's relationship with different innovation objects, namely product, business process, and business model innovation, impacting all value chain activities. The insights gained will stimulate academic and practitioner interest in explicating strategic value generated from BDAC and serve as a framework for future research on the subject}, language = {en} } @article{NdashimyeHebieTjaden2022, author = {Ndashimye, Felix and Hebie, Oumarou and Tjaden, Jasper}, title = {Effectiveness of WhatsApp for measuring migration in follow-up phone surveys}, series = {Social science computer review}, journal = {Social science computer review}, publisher = {Sage}, address = {Thousand Oaks}, issn = {0894-4393}, doi = {10.1177/08944393221111340}, pages = {20}, year = {2022}, abstract = {Phone surveys have increasingly become important data collection tools in developing countries, particularly in the context of sudden contact restrictions due to the COVID-19 pandemic. So far, there is limited evidence regarding the potential of the messenger service WhatsApp for remote data collection despite its large global coverage and expanding membership. WhatsApp may offer advantages in terms of reducing panel attrition and cutting survey costs. WhatsApp may offer additional benefits to migration scholars interested in cross-border migration behavior which is notoriously difficult to measure using conventional face-to-face surveys. In this field experiment, we compared the response rates between WhatsApp and interactive voice response (IVR) modes using a sample of 8446 contacts in Senegal and Guinea. At 12\%, WhatsApp survey response rates were nearly eight percentage points lower than IVR survey response rates. However, WhatsApp offers higher survey completion rates, substantially lower costs and does not introduce more sample selection bias compared to IVR. We discuss the potential of WhatsApp surveys in low-income contexts and provide practical recommendations for field implementation.}, language = {en} } @article{SpiekermannKrasnovaHinzetal.2022, author = {Spiekermann, Sarah and Krasnova, Hanna and Hinz, Oliver and Baumann, Annika and Benlian, Alexander and Gimpel, Henner and Heimbach, Irina and Koester, Antonia and Maedche, Alexander and Niehaves, Bjoern and Risius, Marten and Trenz, Manuel}, title = {Values and ethics in information systems}, series = {Business \& information systems engineering}, volume = {64}, journal = {Business \& information systems engineering}, number = {2}, publisher = {Springer Gabler}, address = {Wiesbaden}, issn = {2363-7005}, doi = {10.1007/s12599-021-00734-8}, pages = {247 -- 264}, year = {2022}, language = {en} } @book{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} } @book{FlottererMaximovaSchneideretal.2022, author = {Flotterer, Boris and Maximova, Maria and Schneider, Sven and Dyck, Johannes and Z{\"o}llner, Christian and Giese, Holger and H{\´e}ly, Christelle and Gaucherel, C{\´e}dric}, title = {Modeling and Formal Analysis of Meta-Ecosystems with Dynamic Structure using Graph Transformation}, series = {Technische Berichte des Hasso-Plattner-Instituts f{\"u}r Digital Engineering an der Universit{\"a}t Potsdam}, journal = {Technische Berichte des Hasso-Plattner-Instituts f{\"u}r Digital Engineering an der Universit{\"a}t Potsdam}, number = {147}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-533-0}, issn = {1613-5652}, doi = {10.25932/publishup-54764}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-547643}, publisher = {Universit{\"a}t Potsdam}, pages = {47}, year = {2022}, abstract = {The dynamics of ecosystems is of crucial importance. Various model-based approaches exist to understand and analyze their internal effects. In this paper, we model the space structure dynamics and ecological dynamics of meta-ecosystems using the formal technique of Graph Transformation (short GT). We build GT models to describe how a meta-ecosystem (modeled as a graph) can evolve over time (modeled by GT rules) and to analyze these GT models with respect to qualitative properties such as the existence of structural stabilities. As a case study, we build three GT models describing the space structure dynamics and ecological dynamics of three different savanna meta-ecosystems. The first GT model considers a savanna meta-ecosystem that is limited in space to two ecosystem patches, whereas the other two GT models consider two savanna meta-ecosystems that are unlimited in the number of ecosystem patches and only differ in one GT rule describing how the space structure of the meta-ecosystem grows. In the first two GT models, the space structure dynamics and ecological dynamics of the meta-ecosystem shows two main structural stabilities: the first one based on grassland-savanna-woodland transitions and the second one based on grassland-desert transitions. The transition between these two structural stabilities is driven by high-intensity fires affecting the tree components. In the third GT model, the GT rule for savanna regeneration induces desertification and therefore a collapse of the meta-ecosystem. We believe that GT models provide a complementary avenue to that of existing approaches to rigorously study ecological phenomena.}, language = {en} } @misc{HempelKoseskaNikoloskietal.2017, author = {Hempel, Sabrina and Koseska, Aneta and Nikoloski, Zoran and Kurths, J{\"u}rgen}, title = {Unraveling gene regulatory networks from time-resolved gene expression data}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-400924}, pages = {26}, year = {2017}, abstract = {Background: Inferring regulatory interactions between genes from transcriptomics time-resolved data, yielding reverse engineered gene regulatory networks, is of paramount importance to systems biology and bioinformatics studies. Accurate methods to address this problem can ultimately provide a deeper insight into the complexity, behavior, and functions of the underlying biological systems. However, the large number of interacting genes coupled with short and often noisy time-resolved read-outs of the system renders the reverse engineering a challenging task. Therefore, the development and assessment of methods which are computationally efficient, robust against noise, applicable to short time series data, and preferably capable of reconstructing the directionality of the regulatory interactions remains a pressing research problem with valuable applications. Results: Here we perform the largest systematic analysis of a set of similarity measures and scoring schemes within the scope of the relevance network approach which are commonly used for gene regulatory network reconstruction from time series data. In addition, we define and analyze several novel measures and schemes which are particularly suitable for short transcriptomics time series. We also compare the considered 21 measures and 6 scoring schemes according to their ability to correctly reconstruct such networks from short time series data by calculating summary statistics based on the corresponding specificity and sensitivity. Our results demonstrate that rank and symbol based measures have the highest performance in inferring regulatory interactions. In addition, the proposed scoring scheme by asymmetric weighting has shown to be valuable in reducing the number of false positive interactions. On the other hand, Granger causality as well as information-theoretic measures, frequently used in inference of regulatory networks, show low performance on the short time series analyzed in this study. Conclusions: Our study is intended to serve as a guide for choosing a particular combination of similarity measures and scoring schemes suitable for reconstruction of gene regulatory networks from short time series data. We show that further improvement of algorithms for reverse engineering can be obtained if one considers measures that are rooted in the study of symbolic dynamics or ranks, in contrast to the application of common similarity measures which do not consider the temporal character of the employed data. Moreover, we establish that the asymmetric weighting scoring scheme together with symbol based measures (for low noise level) and rank based measures (for high noise level) are the most suitable choices.}, language = {en} } @article{CsehJuhos2021, author = {Cseh, {\´A}gnes and Juhos, Attila}, title = {Pairwise preferences in the stable marriage problem}, series = {ACM Transactions on Economics and Computation / Association for Computing Machinery}, volume = {9}, journal = {ACM Transactions on Economics and Computation / Association for Computing Machinery}, number = {1}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {2167-8375}, doi = {10.1145/3434427}, pages = {28}, year = {2021}, abstract = {We study the classical, two-sided stable marriage problem under pairwise preferences. In the most general setting, agents are allowed to express their preferences as comparisons of any two of their edges, and they also have the right to declare a draw or even withdraw from such a comparison. This freedom is then gradually restricted as we specify six stages of orderedness in the preferences, ending with the classical case of strictly ordered lists. We study all cases occurring when combining the three known notions of stability-weak, strong, and super-stability-under the assumption that each side of the bipartite market obtains one of the six degrees of orderedness. By designing three polynomial algorithms and two NP-completeness proofs, we determine the complexity of all cases not yet known and thus give an exact boundary in terms of preference structure between tractable and intractable cases.}, language = {en} } @article{CsehKavitha2021, author = {Cseh, {\´A}gnes and Kavitha, Telikepalli}, title = {Popular matchings in complete graphs}, series = {Algorithmica : an international journal in computer science}, volume = {83}, journal = {Algorithmica : an international journal in computer science}, number = {5}, publisher = {Springer}, address = {New York}, issn = {0178-4617}, doi = {10.1007/s00453-020-00791-7}, pages = {1493 -- 1523}, year = {2021}, abstract = {Our input is a complete graph G on n vertices where each vertex has a strict ranking of all other vertices in G. The goal is to construct a matching in G that is popular. A matching M is popular if M does not lose a head-to-head election against any matching M ': here each vertex casts a vote for the matching in {M,M '} in which it gets a better assignment. Popular matchings need not exist in the given instance G and the popular matching problem is to decide whether one exists or not. The popular matching problem in G is easy to solve for odd n. Surprisingly, the problem becomes NP-complete for even n, as we show here. This is one of the few graph theoretic problems efficiently solvable when n has one parity and NP-complete when n has the other parity.}, language = {en} } @article{BredeBotta2021, author = {Brede, Nuria and Botta, Nicola}, title = {On the correctness of monadic backward induction}, series = {Journal of functional programming}, volume = {31}, journal = {Journal of functional programming}, publisher = {Cambridge University Press}, address = {Cambridge}, issn = {1469-7653}, doi = {10.1017/S0956796821000228}, pages = {39}, year = {2021}, abstract = {In control theory, to solve a finite-horizon sequential decision problem (SDP) commonly means to find a list of decision rules that result in an optimal expected total reward (or cost) when taking a given number of decision steps. SDPs are routinely solved using Bellman's backward induction. Textbook authors (e.g. Bertsekas or Puterman) typically give more or less formal proofs to show that the backward induction algorithm is correct as solution method for deterministic and stochastic SDPs. Botta, Jansson and Ionescu propose a generic framework for finite horizon, monadic SDPs together with a monadic version of backward induction for solving such SDPs. In monadic SDPs, the monad captures a generic notion of uncertainty, while a generic measure function aggregates rewards. In the present paper, we define a notion of correctness for monadic SDPs and identify three conditions that allow us to prove a correctness result for monadic backward induction that is comparable to textbook correctness proofs for ordinary backward induction. The conditions that we impose are fairly general and can be cast in category-theoretical terms using the notion of Eilenberg-Moore algebra. They hold in familiar settings like those of deterministic or stochastic SDPs, but we also give examples in which they fail. Our results show that backward induction can safely be employed for a broader class of SDPs than usually treated in textbooks. However, they also rule out certain instances that were considered admissible in the context of Botta et al. 's generic framework. Our development is formalised in Idris as an extension of the Botta et al. framework and the sources are available as supplementary material.}, language = {en} } @article{StaufferMengeshaSeifertetal.2022, author = {Stauffer, Maxime and Mengesha, Isaak and Seifert, Konrad and Krawczuk, Igor and Fischer, Jens and Serugendo, Giovanna Di Marzo}, title = {A computational turn in policy process studies}, series = {Complexity}, volume = {2022}, journal = {Complexity}, publisher = {Wiley-Hindawi}, address = {London}, issn = {1076-2787}, doi = {10.1155/2022/8210732}, pages = {17}, year = {2022}, abstract = {The past three decades of policy process studies have seen the emergence of a clear intellectual lineage with regard to complexity. Implicitly or explicitly, scholars have employed complexity theory to examine the intricate dynamics of collective action in political contexts. However, the methodological counterparts to complexity theory, such as computational methods, are rarely used and, even if they are, they are often detached from established policy process theory. Building on a critical review of the application of complexity theory to policy process studies, we present and implement a baseline model of policy processes using the logic of coevolving networks. Our model suggests that an actor's influence depends on their environment and on exogenous events facilitating dialogue and consensus-building. Our results validate previous opinion dynamics models and generate novel patterns. Our discussion provides ground for further research and outlines the path for the field to achieve a computational turn.}, language = {en} }