@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} } @book{AbedjanGolabNaumannetal., author = {Abedjan, Ziawasch and Golab, Lukasz and Naumann, Felix and Papenbrock, Thorsten}, title = {Data Profiling}, series = {Synthesis lectures on data management, 52}, journal = {Synthesis lectures on data management, 52}, publisher = {Morgan \& Claypool Publishers}, address = {San Rafael}, isbn = {978-1-68173-446-0}, pages = {xviii, 136}, 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} } @book{AdamBrehmerHuettenrauchetal.2006, author = {Adam, Christian and Brehmer, Bastian and H{\"u}ttenrauch, Stefan and Jeske, Janin and Polze, Andreas and Rasche, Andreas and Sch{\"u}ler, Benjamin and Schult, Wolfgang}, title = {Aspektorientierte Programmierung : {\"U}berblick {\"u}ber Techniken und Werkzeuge}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-939469-23-0}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-33796}, publisher = {Universit{\"a}t Potsdam}, pages = {88}, year = {2006}, abstract = {Inhaltsverzeichnis 1 Einf{\"u}hrung 2 Aspektorientierte Programmierung 2.1 Ein System als Menge von Eigenschaften 2.2 Aspekte 2.3 Aspektweber 2.4 Vorteile Aspektorientierter Programmierung 2.5 Kategorisierung der Techniken und Werkzeuge f ¨ ur Aspektorientierte Programmierung 3 Techniken und Werkzeuge zur Analyse Aspektorientierter Softwareprogramme 3.1 Virtual Source File 3.2 FEAT 3.3 JQuery 3.4 Aspect Mining Tool 4 Techniken und Werkzeuge zum Entwurf Aspektorientierter Softwareprogramme 4.1 Concern Space Modeling Schema 4.2 Modellierung von Aspekten mit UML 4.3 CoCompose 4.4 Codagen Architect 5 Techniken und Werkzeuge zur Implementierung Aspektorientierter Softwareprogramme 5.1 Statische Aspektweber 5.2 Dynamische Aspektweber 6 Zusammenfassung}, language = {de} } @article{AdnanMatthewsHackletal.2020, author = {Adnan, Hassan Sami and Matthews, Sam and Hackl, M. and Das, P. P. and Manaswini, Manisha and Gadamsetti, S. and Filali, Maroua and Owoyele, Babajide and Santuber, Joaqu{\´i}n and Edelman, Jonathan}, title = {Human centered AI design for clinical monitoring and data management}, series = {European journal of public health : official journal of the European Health Association}, volume = {30}, journal = {European journal of public health : official journal of the European Health Association}, number = {5}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1101-1262}, doi = {10.1093/eurpub/ckaa165.225}, pages = {V86 -- V86}, year = {2020}, abstract = {In clinical settings, significant resources are spent on data collection and monitoring patients' health parameters to improve decision-making and provide better care. With increased digitization, the healthcare sector is shifting towards implementing digital technologies for data management and in administration. New technologies offer better treatment opportunities and streamline clinical workflow, but the complexity can cause ineffectiveness, frustration, and errors. To address this, we believe digital solutions alone are not sufficient. Therefore, we take a human-centred design approach for AI development, and apply systems engineering methods to identify system leverage points. We demonstrate how automation enables monitoring clinical parameters, using existing non-intrusive sensor technology, resulting in more resources toward patient care. Furthermore, we provide a framework on digitization of clinical data for integration with data management.}, language = {en} } @article{AdnanSrsicVenticichetal.2020, author = {Adnan, Hassan Sami and Srsic, Amanda and Venticich, Pete Milos and Townend, David M.R.}, title = {Using AI for mental health analysis and prediction in school surveys}, series = {European journal of public health}, volume = {30}, journal = {European journal of public health}, publisher = {Oxford Univ. Press}, address = {Oxford [u.a.]}, issn = {1101-1262}, doi = {10.1093/eurpub/ckaa165.336}, pages = {V125 -- V125}, year = {2020}, abstract = {Background: Childhood and adolescence are critical stages of life for mental health and well-being. Schools are a key setting for mental health promotion and illness prevention. One in five children and adolescents have a mental disorder, about half of mental disorders beginning before the age of 14. Beneficial and explainable artificial intelligence can replace current paper- based and online approaches to school mental health surveys. This can enhance data acquisition, interoperability, data driven analysis, trust and compliance. This paper presents a model for using chatbots for non-obtrusive data collection and supervised machine learning models for data analysis; and discusses ethical considerations pertaining to the use of these models. Methods: For data acquisition, the proposed model uses chatbots which interact with students. The conversation log acts as the source of raw data for the machine learning. Pre-processing of the data is automated by filtering for keywords and phrases. Existing survey results, obtained through current paper-based data collection methods, are evaluated by domain experts (health professionals). These can be used to create a test dataset to validate the machine learning models. Supervised learning can then be deployed to classify specific behaviour and mental health patterns. Results: We present a model that can be used to improve upon current paper-based data collection and manual data analysis methods. An open-source GitHub repository contains necessary tools and components of this model. Privacy is respected through rigorous observance of confidentiality and data protection requirements. Critical reflection on these ethics and law aspects is included in the project. Conclusions: This model strengthens mental health surveillance in schools. The same tools and components could be applied to other public health data. Future extensions of this model could also incorporate unsupervised learning to find clusters and patterns of unknown effects.}, language = {en} } @book{AlbrechtNaumann2012, author = {Albrecht, Alexander and Naumann, Felix}, title = {Understanding cryptic schemata in large extract-transform-load systems}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-201-8}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-61257}, publisher = {Universit{\"a}t Potsdam}, pages = {19}, year = {2012}, abstract = {Extract-Transform-Load (ETL) tools are used for the creation, maintenance, and evolution of data warehouses, data marts, and operational data stores. ETL workflows populate those systems with data from various data sources by specifying and executing a DAG of transformations. Over time, hundreds of individual workflows evolve as new sources and new requirements are integrated into the system. The maintenance and evolution of large-scale ETL systems requires much time and manual effort. A key problem is to understand the meaning of unfamiliar attribute labels in source and target databases and ETL transformations. Hard-to-understand attribute labels lead to frustration and time spent to develop and understand ETL workflows. We present a schema decryption technique to support ETL developers in understanding cryptic schemata of sources, targets, and ETL transformations. For a given ETL system, our recommender-like approach leverages the large number of mapped attribute labels in existing ETL workflows to produce good and meaningful decryptions. In this way we are able to decrypt attribute labels consisting of a number of unfamiliar few-letter abbreviations, such as UNP_PEN_INT, which we can decrypt to UNPAID_PENALTY_INTEREST. We evaluate our schema decryption approach on three real-world repositories of ETL workflows and show that our approach is able to suggest high-quality decryptions for cryptic attribute labels in a given schema.}, language = {en} } @misc{AlibabaieGhasemzadehMeinel2017, author = {Alibabaie, Najmeh and Ghasemzadeh, Mohammad and Meinel, Christoph}, title = {A variant of genetic algorithm for non-homogeneous population}, series = {International Conference Applied Mathematics, Computational Science and Systems Engineering 2016}, volume = {9}, journal = {International Conference Applied Mathematics, Computational Science and Systems Engineering 2016}, publisher = {EDP Sciences}, address = {Les Ulis}, issn = {2271-2097}, doi = {10.1051/itmconf/20170902001}, pages = {8}, year = {2017}, abstract = {Selection of initial points, the number of clusters and finding proper clusters centers are still the main challenge in clustering processes. In this paper, we suggest genetic algorithm based method which searches several solution spaces simultaneously. The solution spaces are population groups consisting of elements with similar structure. Elements in a group have the same size, while elements in different groups are of different sizes. The proposed algorithm processes the population in groups of chromosomes with one gene, two genes to k genes. These genes hold corresponding information about the cluster centers. In the proposed method, the crossover and mutation operators can accept parents with different sizes; this can lead to versatility in population and information transfer among sub-populations. We implemented the proposed method and evaluated its performance against some random datasets and the Ruspini dataset as well. The experimental results show that the proposed method could effectively determine the appropriate number of clusters and recognize their centers. Overall this research implies that using heterogeneous population in the genetic algorithm can lead to better results.}, language = {en} } @book{AlnemrPolyvyanyyAbuJarouretal.2010, author = {Alnemr, Rehab and Polyvyanyy, Artem and AbuJarour, Mohammed and Appeltauer, Malte and Hildebrandt, Dieter and Thomas, Ivonne and Overdick, Hagen and Sch{\"o}bel, Michael and Uflacker, Matthias and Kluth, Stephan and Menzel, Michael and Schmidt, Alexander and Hagedorn, Benjamin and Pascalau, Emilian and Perscheid, Michael and Vogel, Thomas and Hentschel, Uwe and Feinbube, Frank and Kowark, Thomas and Tr{\"u}mper, Jonas and Vogel, Tobias and Becker, Basil}, title = {Proceedings of the 4th Ph.D. Retreat of the HPI Research School on Service-oriented Systems Engineering}, editor = {Meinel, Christoph and Plattner, Hasso and D{\"o}llner, J{\"u}rgen Roland Friedrich and Weske, Mathias and Polze, Andreas and Hirschfeld, Robert and Naumann, Felix and Giese, Holger}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-036-6}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-40838}, publisher = {Universit{\"a}t Potsdam}, pages = {Getr. Z{\"a}hlung}, year = {2010}, language = {en} } @article{AlSa'dehMeinel2012, author = {AlSa'deh, Ahmad and Meinel, Christoph}, title = {Secure neighbor discovery Review, challenges, perspectives, and recommendations}, series = {IEEE security \& privacy : building confidence in a networked world}, volume = {10}, journal = {IEEE security \& privacy : building confidence in a networked world}, number = {4}, publisher = {Inst. of Electr. and Electronics Engineers}, address = {Los Alamitos}, issn = {1540-7993}, pages = {26 -- 34}, year = {2012}, abstract = {Secure Neighbor Discovery is designed as a countermeasure to Neighbor Discovery Protocol threats. The authors discuss Secure Neighbor Discovery implementation and deployment challenges and review proposals to optimize it.}, language = {en} } @article{AndreeIhdeWeskeetal.2022, author = {Andree, Kerstin and Ihde, Sven and Weske, Mathias and Pufahl, Luise}, title = {An exception handling framework for case management}, series = {Software and Systems Modeling}, volume = {21}, journal = {Software and Systems Modeling}, number = {3}, publisher = {Springer}, address = {Heidelberg}, issn = {1619-1366}, doi = {10.1007/s10270-022-00993-3}, pages = {939 -- 962}, year = {2022}, abstract = {In order to achieve their business goals, organizations heavily rely on the operational excellence of their business processes. In traditional scenarios, business processes are usually well-structured, clearly specifying when and how certain tasks have to be executed. Flexible and knowledge-intensive processes are gathering momentum, where a knowledge worker drives the execution of a process case and determines the exact process path at runtime. In the case of an exception, the knowledge worker decides on an appropriate handling. While there is initial work on exception handling in well-structured business processes, exceptions in case management have not been sufficiently researched. This paper proposes an exception handling framework for stage-oriented case management languages, namely Guard Stage Milestone Model, Case Management Model and Notation, and Fragment-based Case Management. The effectiveness of the framework is evaluated with two real-world use cases showing that it covers all relevant exceptions and proposed handling strategies.}, language = {en} } @book{AppeltauerHirschfeld2012, author = {Appeltauer, Malte and Hirschfeld, Robert}, title = {The JCop language specification : Version 1.0, April 2012}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-193-6}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-60208}, publisher = {Universit{\"a}t Potsdam}, pages = {iv, 48}, year = {2012}, abstract = {Program behavior that relies on contextual information, such as physical location or network accessibility, is common in today's applications, yet its representation is not sufficiently supported by programming languages. With context-oriented programming (COP), such context-dependent behavioral variations can be explicitly modularized and dynamically activated. In general, COP could be used to manage any context-specific behavior. However, its contemporary realizations limit the control of dynamic adaptation. This, in turn, limits the interaction of COP's adaptation mechanisms with widely used architectures, such as event-based, mobile, and distributed programming. The JCop programming language extends Java with language constructs for context-oriented programming and additionally provides a domain-specific aspect language for declarative control over runtime adaptations. As a result, these redesigned implementations are more concise and better modularized than their counterparts using plain COP. JCop's main features have been described in our previous publications. However, a complete language specification has not been presented so far. This report presents the entire JCop language including the syntax and semantics of its new language constructs.}, language = {en} } @book{AsheuerBelgassemEichornetal.2013, author = {Asheuer, Susanne and Belgassem, Joy and Eichorn, Wiete and Leipold, Rio and Licht, Lucas and Meinel, Christoph and Schanz, Anne and Schnjakin, Maxim}, title = {Akzeptanz und Nutzerfreundlichkeit der AusweisApp : eine qualitative Untersuchung ; eine Studie am Hasso-Plattner-Institut f{\"u}r Softwaresystemtechnik im Auftrag des Bundesministeriums des Innern}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-229-2}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-63971}, publisher = {Universit{\"a}t Potsdam}, pages = {83}, year = {2013}, abstract = {F{\"u}r die vorliegende Studie »Qualitative Untersuchung zur Akzeptanz des neuen Personalausweises und Erarbeitung von Vorschl{\"a}gen zur Verbesserung der Usability der Software AusweisApp« arbeitete ein Innovationsteam mit Hilfe der Design Thinking Methode an der Aufgabenstellung »Wie k{\"o}nnen wir die AusweisApp f{\"u}r Nutzer intuitiv und verst{\"a}ndlich gestalten?« Zun{\"a}chst wurde die Akzeptanz des neuen Personalausweises getestet. B{\"u}rger wurden zu ihrem Wissensstand und ihren Erwartungen hinsichtlich des neuen Personalausweises befragt, dar{\"u}ber hinaus zur generellen Nutzung des neuen Personalausweises, der Nutzung der Online-Ausweisfunktion sowie der Usability der AusweisApp. Weiterhin wurden Nutzer bei der Verwendung der aktuellen AusweisApp beobachtet und anschließend befragt. Dies erlaubte einen tiefen Einblick in ihre Bed{\"u}rfnisse. Die Ergebnisse aus der qualitativen Untersuchung wurden verwendet, um Verbesserungsvorschl{\"a}ge f{\"u}r die AusweisApp zu entwickeln, die den Bed{\"u}rfnissen der B{\"u}rger entsprechen. Die Vorschl{\"a}ge zur Optimierung der AusweisApp wurden prototypisch umgesetzt und mit potentiellen Nutzern getestet. Die Tests haben gezeigt, dass die entwickelten Neuerungen den B{\"u}rgern den Zugang zur Nutzung der Online-Ausweisfunktion deutlich vereinfachen. Im Ergebnis konnte festgestellt werden, dass der Akzeptanzgrad des neuen Personalausweises stark divergiert. Die Einstellung der Befragten reichte von Skepsis bis hin zu Bef{\"u}rwortung. Der neue Personalausweis ist ein Thema, das den B{\"u}rger polarisiert. Im Rahmen der Nutzertests konnten zahlreiche Verbesserungspotenziale des bestehenden Service Designs sowohl rund um den neuen Personalausweis, als auch im Zusammenhang mit der verwendeten Software aufgedeckt werden. W{\"a}hrend der Nutzertests, die sich an die Ideen- und Prototypenphase anschlossen, konnte das Innovtionsteam seine Vorschl{\"a}ge iterieren und auch verifizieren. Die ausgearbeiteten Vorschl{\"a}ge beziehen sich auf die AusweisApp. Die neuen Funktionen umfassen im Wesentlichen: · den direkten Zugang zu den Diensteanbietern, · umfangreiche Hilfestellungen (Tooltips, FAQ, Wizard, Video), · eine Verlaufsfunktion, · einen Beispieldienst, der die Online-Ausweisfunktion erfahrbar macht. Insbesondere gilt es, den Nutzern mit der neuen Version der AusweisApp Anwendungsfelder f{\"u}r ihren neuen Personalausweis und einen Mehrwert zu bieten. Die Ausarbeitung von weiteren Funktionen der AusweisApp kann dazu beitragen, dass der neue Personalausweis sein volles Potenzial entfalten kann.}, language = {de} } @phdthesis{Awad2010, author = {Awad, Ahmed Mahmoud Hany Aly}, title = {A compliance management framework for business process models}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-49222}, school = {Universit{\"a}t Potsdam}, year = {2010}, abstract = {Companies develop process models to explicitly describe their business operations. In the same time, business operations, business processes, must adhere to various types of compliance requirements. Regulations, e.g., Sarbanes Oxley Act of 2002, internal policies, best practices are just a few sources of compliance requirements. In some cases, non-adherence to compliance requirements makes the organization subject to legal punishment. In other cases, non-adherence to compliance leads to loss of competitive advantage and thus loss of market share. Unlike the classical domain-independent behavioral correctness of business processes, compliance requirements are domain-specific. Moreover, compliance requirements change over time. New requirements might appear due to change in laws and adoption of new policies. Compliance requirements are offered or enforced by different entities that have different objectives behind these requirements. Finally, compliance requirements might affect different aspects of business processes, e.g., control flow and data flow. As a result, it is infeasible to hard-code compliance checks in tools. Rather, a repeatable process of modeling compliance rules and checking them against business processes automatically is needed. This thesis provides a formal approach to support process design-time compliance checking. Using visual patterns, it is possible to model compliance requirements concerning control flow, data flow and conditional flow rules. Each pattern is mapped into a temporal logic formula. The thesis addresses the problem of consistency checking among various compliance requirements, as they might stem from divergent sources. Also, the thesis contributes to automatically check compliance requirements against process models using model checking. We show that extra domain knowledge, other than expressed in compliance rules, is needed to reach correct decisions. In case of violations, we are able to provide a useful feedback to the user. The feedback is in the form of parts of the process model whose execution causes the violation. In some cases, our approach is capable of providing automated remedy of the violation.}, language = {en} } @article{AwadWeidlichWeske2011, author = {Awad, Ahmed Mahmoud Hany Aly and Weidlich, Matthias and Weske, Mathias}, title = {Visually specifying compliance rules and explaining their violations for business processes}, series = {Journal of visual languages and computing}, volume = {22}, journal = {Journal of visual languages and computing}, number = {1}, publisher = {Elsevier}, address = {London}, issn = {1045-926X}, doi = {10.1016/j.jvlc.2010.11.002}, pages = {30 -- 55}, year = {2011}, abstract = {A business process is a set of steps designed to be executed in a certain order to achieve a business value. Such processes are often driven by and documented using process models. Nowadays, process models are also applied to drive process execution. Thus, correctness of business process models is a must. Much of the work has been devoted to check general, domain-independent correctness criteria, such as soundness. However, business processes must also adhere to and show compliance with various regulations and constraints, the so-called compliance requirements. These are domain-dependent requirements. In many situations, verifying compliance on a model level is of great value, since violations can be resolved in an early stage prior to execution. However, this calls for using formal verification techniques, e.g., model checking, that are too complex for business experts to apply. In this paper, we utilize a visual language. BPMN-Q to express compliance requirements visually in a way similar to that used by business experts to build process models. Still, using a pattern based approach, each BPMN-Qgraph has a formal temporal logic expression in computational tree logic (CTL). Moreover, the user is able to express constraints, i.e., compliance rules, regarding control flow and data flow aspects. In order to provide valuable feedback to a user in case of violations, we depend on temporal logic querying approaches as well as BPMN-Q to visually highlight paths in a process model whose execution causes violations.}, language = {en} } @article{AzodiChengMeinel2015, author = {Azodi, Amir and Cheng, Feng and Meinel, Christoph}, title = {Event Driven Network Topology Discovery and Inventory Listing Using REAMS}, series = {Wireless personal communications : an international journal}, volume = {94}, journal = {Wireless personal communications : an international journal}, publisher = {Springer}, address = {New York}, issn = {0929-6212}, doi = {10.1007/s11277-015-3061-3}, pages = {415 -- 430}, year = {2015}, abstract = {Network Topology Discovery and Inventory Listing are two of the primary features of modern network monitoring systems (NMS). Current NMSs rely heavily on active scanning techniques for discovering and mapping network information. Although this approach works, it introduces some major drawbacks such as the performance impact it can exact, specially in larger network environments. As a consequence, scans are often run less frequently which can result in stale information being presented and used by the network monitoring system. Alternatively, some NMSs rely on their agents being deployed on the hosts they monitor. In this article, we present a new approach to Network Topology Discovery and Network Inventory Listing using only passive monitoring and scanning techniques. The proposed techniques rely solely on the event logs produced by the hosts and network devices present within a network. Finally, we discuss some of the advantages and disadvantages of our approach.}, 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} } @article{BanoMichaelRumpeetal.2022, author = {Bano, Dorina and Michael, Judith and Rumpe, Bernhard and Varga, Simon and Weske, Mathias}, title = {Process-aware digital twin cockpit synthesis from event logs}, series = {Journal of computer languages}, volume = {70}, journal = {Journal of computer languages}, publisher = {Elsevier}, address = {Amsterdam [u.a.]}, issn = {2590-1184}, doi = {10.1016/j.cola.2022.101121}, pages = {19}, year = {2022}, abstract = {The engineering of digital twins and their user interaction parts with explicated processes, namely processaware digital twin cockpits (PADTCs), is challenging due to the complexity of the systems and the need for information from different disciplines within the engineering process. Therefore, it is interesting to investigate how to facilitate their engineering by using already existing data, namely event logs, and reducing the number of manual steps for their engineering. Current research lacks systematic, automated approaches to derive process-aware digital twin cockpits even though some helpful techniques already exist in the areas of process mining and software engineering. Within this paper, we present a low-code development approach that reduces the amount of hand-written code needed and uses process mining techniques to derive PADTCs. We describe what models could be derived from event log data, which generative steps are needed for the engineering of PADTCs, and how process mining could be incorporated into the resulting application. This process is evaluated using the MIMIC III dataset for the creation of a PADTC prototype for an automated hospital transportation system. This approach can be used for early prototyping of PADTCs as it needs no hand-written code in the first place, but it still allows for the iterative evolvement of the application. This empowers domain experts to create their PADTC prototypes.}, language = {en} } @article{BarkowskyGiese2020, author = {Barkowsky, Matthias and Giese, Holger}, title = {Hybrid search plan generation for generalized graph pattern matching}, series = {Journal of logical and algebraic methods in programming}, volume = {114}, journal = {Journal of logical and algebraic methods in programming}, publisher = {Elsevier}, address = {New York}, issn = {2352-2208}, doi = {10.1016/j.jlamp.2020.100563}, pages = {29}, year = {2020}, abstract = {In recent years, the increased interest in application areas such as social networks has resulted in a rising popularity of graph-based approaches for storing and processing large amounts of interconnected data. To extract useful information from the growing network structures, efficient querying techniques are required. In this paper, we propose an approach for graph pattern matching that allows a uniform handling of arbitrary constraints over the query vertices. Our technique builds on a previously introduced matching algorithm, which takes concrete host graph information into account to dynamically adapt the employed search plan during query execution. The dynamic algorithm is combined with an existing static approach for search plan generation, resulting in a hybrid technique which we further extend by a more sophisticated handling of filtering effects caused by constraint checks. We evaluate the presented concepts empirically based on an implementation for our graph pattern matching tool, the Story Diagram Interpreter, with queries and data provided by the LDBC Social Network Benchmark. Our results suggest that the hybrid technique may improve search efficiency in several cases, and rarely reduces efficiency.}, language = {en} } @misc{BartzYangBethgeetal.2019, author = {Bartz, Christian and Yang, Haojin and Bethge, Joseph and Meinel, Christoph}, title = {LoANs}, series = {Computer Vision - ACCV 2018 Workshops}, volume = {11367}, journal = {Computer Vision - ACCV 2018 Workshops}, publisher = {Springer}, address = {Cham}, isbn = {978-3-030-21074-8}, issn = {0302-9743}, doi = {10.1007/978-3-030-21074-8_29}, pages = {341 -- 356}, year = {2019}, abstract = {Recently, deep neural networks have achieved remarkable performance on the task of object detection and recognition. The reason for this success is mainly grounded in the availability of large scale, fully annotated datasets, but the creation of such a dataset is a complicated and costly task. In this paper, we propose a novel method for weakly supervised object detection that simplifies the process of gathering data for training an object detector. We train an ensemble of two models that work together in a student-teacher fashion. Our student (localizer) is a model that learns to localize an object, the teacher (assessor) assesses the quality of the localization and provides feedback to the student. The student uses this feedback to learn how to localize objects and is thus entirely supervised by the teacher, as we are using no labels for training the localizer. In our experiments, we show that our model is very robust to noise and reaches competitive performance compared to a state-of-the-art fully supervised approach. We also show the simplicity of creating a new dataset, based on a few videos (e.g. downloaded from YouTube) and artificially generated data.}, language = {en} } @phdthesis{Bauckmann2013, author = {Bauckmann, Jana}, title = {Dependency discovery for data integration}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-66645}, school = {Universit{\"a}t Potsdam}, year = {2013}, abstract = {Data integration aims to combine data of different sources and to provide users with a unified view on these data. This task is as challenging as valuable. In this thesis we propose algorithms for dependency discovery to provide necessary information for data integration. We focus on inclusion dependencies (INDs) in general and a special form named conditional inclusion dependencies (CINDs): (i) INDs enable the discovery of structure in a given schema. (ii) INDs and CINDs support the discovery of cross-references or links between schemas. An IND "A in B" simply states that all values of attribute A are included in the set of values of attribute B. We propose an algorithm that discovers all inclusion dependencies in a relational data source. The challenge of this task is the complexity of testing all attribute pairs and further of comparing all of each attribute pair's values. The complexity of existing approaches depends on the number of attribute pairs, while ours depends only on the number of attributes. Thus, our algorithm enables to profile entirely unknown data sources with large schemas by discovering all INDs. Further, we provide an approach to extract foreign keys from the identified INDs. We extend our IND discovery algorithm to also find three special types of INDs: (i) Composite INDs, such as "AB in CD", (ii) approximate INDs that allow a certain amount of values of A to be not included in B, and (iii) prefix and suffix INDs that represent special cross-references between schemas. Conditional inclusion dependencies are inclusion dependencies with a limited scope defined by conditions over several attributes. Only the matching part of the instance must adhere the dependency. We generalize the definition of CINDs distinguishing covering and completeness conditions and define quality measures for conditions. We propose efficient algorithms that identify covering and completeness conditions conforming to given quality thresholds. The challenge for this task is twofold: (i) Which (and how many) attributes should be used for the conditions? (ii) Which attribute values should be chosen for the conditions? Previous approaches rely on pre-selected condition attributes or can only discover conditions applying to quality thresholds of 100\%. Our approaches were motivated by two application domains: data integration in the life sciences and link discovery for linked open data. We show the efficiency and the benefits of our approaches for use cases in these domains.}, language = {en} } @book{BauckmannAbedjanLeseretal.2012, author = {Bauckmann, Jana and Abedjan, Ziawasch and Leser, Ulf and M{\"u}ller, Heiko and Naumann, Felix}, title = {Covering or complete? : Discovering conditional inclusion dependencies}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-212-4}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-62089}, publisher = {Universit{\"a}t Potsdam}, pages = {34}, year = {2012}, abstract = {Data dependencies, or integrity constraints, are used to improve the quality of a database schema, to optimize queries, and to ensure consistency in a database. In the last years conditional dependencies have been introduced to analyze and improve data quality. In short, a conditional dependency is a dependency with a limited scope defined by conditions over one or more attributes. Only the matching part of the instance must adhere to the dependency. In this paper we focus on conditional inclusion dependencies (CINDs). We generalize the definition of CINDs, distinguishing covering and completeness conditions. We present a new use case for such CINDs showing their value for solving complex data quality tasks. Further, we define quality measures for conditions inspired by precision and recall. We propose efficient algorithms that identify covering and completeness conditions conforming to given quality thresholds. Our algorithms choose not only the condition values but also the condition attributes automatically. Finally, we show that our approach efficiently provides meaningful and helpful results for our use case.}, language = {en} } @book{BauckmannLeserNaumann2010, author = {Bauckmann, Jana and Leser, Ulf and Naumann, Felix}, title = {Efficient and exact computation of inclusion dependencies for data integration}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-048-9}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-41396}, publisher = {Universit{\"a}t Potsdam}, pages = {36}, year = {2010}, abstract = {Data obtained from foreign data sources often come with only superficial structural information, such as relation names and attribute names. Other types of metadata that are important for effective integration and meaningful querying of such data sets are missing. In particular, relationships among attributes, such as foreign keys, are crucial metadata for understanding the structure of an unknown database. The discovery of such relationships is difficult, because in principle for each pair of attributes in the database each pair of data values must be compared. A precondition for a foreign key is an inclusion dependency (IND) between the key and the foreign key attributes. We present with Spider an algorithm that efficiently finds all INDs in a given relational database. It leverages the sorting facilities of DBMS but performs the actual comparisons outside of the database to save computation. Spider analyzes very large databases up to an order of magnitude faster than previous approaches. We also evaluate in detail the effectiveness of several heuristics to reduce the number of necessary comparisons. Furthermore, we generalize Spider to find composite INDs covering multiple attributes, and partial INDs, which are true INDs for all but a certain number of values. This last type is particularly relevant when integrating dirty data as is often the case in the life sciences domain - our driving motivation.}, language = {en} } @article{BaudischSilberKommanaetal.2019, author = {Baudisch, Patrick Markus and Silber, Arthur and Kommana, Yannis and Gruner, Milan and Wall, Ludwig and Reuss, Kevin and Heilman, Lukas and Kovacs, Robert and Rechlitz, Daniel and Roumen, Thijs}, title = {Kyub}, series = {Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems}, journal = {Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems}, publisher = {Association for Computing Machinery}, address = {New York}, isbn = {978-1-4503-5970-2}, doi = {10.1145/3290605.3300796}, pages = {1 -- 12}, year = {2019}, abstract = {We present an interactive editing system for laser cutting called kyub. Kyub allows users to create models efficiently in 3D, which it then unfolds into the 2D plates laser cutters expect. Unlike earlier systems, such as FlatFitFab, kyub affords construction based on closed box structures, which allows users to turn very thin material, such as 4mm plywood, into objects capable of withstanding large forces, such as chairs users can actually sit on. To afford such sturdy construction, every kyub project begins with a simple finger-joint "boxel"-a structure we found to be capable of withstanding over 500kg of load. Users then extend their model by attaching additional boxels. Boxels merge automatically, resulting in larger, yet equally strong structures. While the concept of stacking boxels allows kyub to offer the strong affordance and ease of use of a voxel-based editor, boxels are not confined to a grid and readily combine with kuyb's various geometry deformation tools. In our technical evaluation, objects built with kyub withstood hundreds of kilograms of loads. In our user study, non-engineers rated the learnability of kyub 6.1/7.}, language = {en} } @incollection{BauerMalchowMeinel2019, author = {Bauer, Matthias and Malchow, Martin and Meinel, Christoph}, title = {Full Lecture Recording Watching Behavior, or Why Students Watch 90-Min Lectures in 5 Min}, series = {IMCL 2018: Mobile Technologies and Applications for the Internet of Things}, volume = {909}, booktitle = {IMCL 2018: Mobile Technologies and Applications for the Internet of Things}, publisher = {Springer}, address = {Cham}, isbn = {978-3-030-11434-3}, issn = {2194-5357}, doi = {10.1007/978-3-030-11434-3_38}, pages = {347 -- 358}, year = {2019}, abstract = {Many universities record the lectures being held in their facilities to preserve knowledge and to make it available to their students and, at least for some universities and classes, to the broad public. The way with the least effort is to record the whole lecture, which in our case usually is 90 min long. This saves the labor and time of cutting and rearranging lectures scenes to provide short learning videos as known from Massive Open Online Courses (MOOCs), etc. Many lecturers fear that recording their lectures and providing them via an online platform might lead to less participation in the actual lecture. Also, many teachers fear that the lecture recordings are not used with the same focus and dedication as lectures in a lecture hall. In this work, we show that in our experience, full lectures have an average watching duration of just a few minutes and explain the reasons for that and why, in most cases, teachers do not have to worry about that.}, language = {en} } @article{BaumanBolzHirschfeldetal.2015, author = {Bauman, Spenser and Bolz, Carl Friedrich and Hirschfeld, Robert and Kirilichev, Vasily and Pape, Tobias and Siek, Jeremy G. and Tobin-Hochstadt, Sam}, title = {Pycket: A Tracing JIT for a Functional Language}, series = {ACM SIGPLAN notices}, volume = {50}, journal = {ACM SIGPLAN notices}, number = {9}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {0362-1340}, doi = {10.1145/2784731.2784740}, pages = {22 -- 34}, year = {2015}, abstract = {We present Pycket, a high-performance tracing JIT compiler for Racket. Pycket supports a wide variety of the sophisticated features in Racket such as contracts, continuations, classes, structures, dynamic binding, and more. On average, over a standard suite of benchmarks, Pycket outperforms existing compilers, both Racket's JIT and other highly-optimizing Scheme compilers. Further, Pycket provides much better performance for Racket proxies than existing systems, dramatically reducing the overhead of contracts and gradual typing. We validate this claim with performance evaluation on multiple existing benchmark suites. The Pycket implementation is of independent interest as an application of the RPython meta-tracing framework (originally created for PyPy), which automatically generates tracing JIT compilers from interpreters. Prior work on meta-tracing focuses on bytecode interpreters, whereas Pycket is a high-level interpreter based on the CEK abstract machine and operates directly on abstract syntax trees. Pycket supports proper tail calls and first-class continuations. In the setting of a functional language, where recursion and higher-order functions are more prevalent than explicit loops, the most significant performance challenge for a tracing JIT is identifying which control flows constitute a loop-we discuss two strategies for identifying loops and measure their impact.}, language = {en} } @phdthesis{Becker2013, author = {Becker, Basil}, title = {Architectural modelling and verification of open service-oriented systems of systems}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-70158}, school = {Universit{\"a}t Potsdam}, year = {2013}, abstract = {Systems of Systems (SoS) have received a lot of attention recently. In this thesis we will focus on SoS that are built atop the techniques of Service-Oriented Architectures and thus combine the benefits and challenges of both paradigms. For this thesis we will understand SoS as ensembles of single autonomous systems that are integrated to a larger system, the SoS. The interesting fact about these systems is that the previously isolated systems are still maintained, improved and developed on their own. Structural dynamics is an issue in SoS, as at every point in time systems can join and leave the ensemble. This and the fact that the cooperation among the constituent systems is not necessarily observable means that we will consider these systems as open systems. Of course, the system has a clear boundary at each point in time, but this can only be identified by halting the complete SoS. However, halting a system of that size is practically impossible. Often SoS are combinations of software systems and physical systems. Hence a failure in the software system can have a serious physical impact what makes an SoS of this kind easily a safety-critical system. The contribution of this thesis is a modelling approach that extends OMG's SoaML and basically relies on collaborations and roles as an abstraction layer above the components. This will allow us to describe SoS at an architectural level. We will also give a formal semantics for our modelling approach which employs hybrid graph-transformation systems. The modelling approach is accompanied by a modular verification scheme that will be able to cope with the complexity constraints implied by the SoS' structural dynamics and size. Building such autonomous systems as SoS without evolution at the architectural level --- i. e. adding and removing of components and services --- is inadequate. Therefore our approach directly supports the modelling and verification of evolution.}, language = {en} } @book{BeckerGiese2012, author = {Becker, Basil and Giese, Holger}, title = {Cyber-physical systems with dynamic structure : towards modeling and verification of inductive invariants}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-217-9}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-62437}, publisher = {Universit{\"a}t Potsdam}, pages = {iv, 27}, year = {2012}, abstract = {Cyber-physical systems achieve sophisticated system behavior exploring the tight interconnection of physical coupling present in classical engineering systems and information technology based coupling. A particular challenging case are systems where these cyber-physical systems are formed ad hoc according to the specific local topology, the available networking capabilities, and the goals and constraints of the subsystems captured by the information processing part. In this paper we present a formalism that permits to model the sketched class of cyber-physical systems. The ad hoc formation of tightly coupled subsystems of arbitrary size are specified using a UML-based graph transformation system approach. Differential equations are employed to define the resulting tightly coupled behavior. Together, both form hybrid graph transformation systems where the graph transformation rules define the discrete steps where the topology or modes may change, while the differential equations capture the continuous behavior in between such discrete changes. In addition, we demonstrate that automated analysis techniques known for timed graph transformation systems for inductive invariants can be extended to also cover the hybrid case for an expressive case of hybrid models where the formed tightly coupled subsystems are restricted to smaller local networks.}, language = {en} } @book{BeckerGieseNeumann2009, author = {Becker, Basil and Giese, Holger and Neumann, Stefan}, title = {Correct dynamic service-oriented architectures : modeling and compositional verification with dynamic collaborations}, organization = {System Analysis and Modeling Group}, isbn = {978-3-940793-91-1}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-30473}, publisher = {Universit{\"a}t Potsdam}, year = {2009}, abstract = {Service-oriented modeling employs collaborations to capture the coordination of multiple roles in form of service contracts. In case of dynamic collaborations the roles may join and leave the collaboration at runtime and therefore complex structural dynamics can result, which makes it very hard to ensure their correct and safe operation. We present in this paper our approach for modeling and verifying such dynamic collaborations. Modeling is supported using a well-defined subset of UML class diagrams, behavioral rules for the structural dynamics, and UML state machines for the role behavior. To be also able to verify the resulting service-oriented systems, we extended our former results for the automated verification of systems with structural dynamics [7, 8] and developed a compositional reasoning scheme, which enables the reuse of verification results. We outline our approach using the example of autonomous vehicles that use such dynamic collaborations via ad-hoc networking to coordinate and optimize their joint behavior.}, language = {en} } @phdthesis{Berg2013, author = {Berg, Gregor}, title = {Virtual prototypes for the model-based elicitation and validation of collaborative scenarios}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-69729}, school = {Universit{\"a}t Potsdam}, year = {2013}, abstract = {Requirements engineers have to elicit, document, and validate how stakeholders act and interact to achieve their common goals in collaborative scenarios. Only after gathering all information concerning who interacts with whom to do what and why, can a software system be designed and realized which supports the stakeholders to do their work. To capture and structure requirements of different (groups of) stakeholders, scenario-based approaches have been widely used and investigated. Still, the elicitation and validation of requirements covering collaborative scenarios remains complicated, since the required information is highly intertwined, fragmented, and distributed over several stakeholders. Hence, it can only be elicited and validated collaboratively. In times of globally distributed companies, scheduling and conducting workshops with groups of stakeholders is usually not feasible due to budget and time constraints. Talking to individual stakeholders, on the other hand, is feasible but leads to fragmented and incomplete stakeholder scenarios. Going back and forth between different individual stakeholders to resolve this fragmentation and explore uncovered alternatives is an error-prone, time-consuming, and expensive task for the requirements engineers. While formal modeling methods can be employed to automatically check and ensure consistency of stakeholder scenarios, such methods introduce additional overhead since their formal notations have to be explained in each interaction between stakeholders and requirements engineers. Tangible prototypes as they are used in other disciplines such as design, on the other hand, allow designers to feasibly validate and iterate concepts and requirements with stakeholders. This thesis proposes a model-based approach for prototyping formal behavioral specifications of stakeholders who are involved in collaborative scenarios. By simulating and animating such specifications in a remote domain-specific visualization, stakeholders can experience and validate the scenarios captured so far, i.e., how other stakeholders act and react. This interactive scenario simulation is referred to as a model-based virtual prototype. Moreover, through observing how stakeholders interact with a virtual prototype of their collaborative scenarios, formal behavioral specifications can be automatically derived which complete the otherwise fragmented scenarios. This, in turn, enables requirements engineers to elicit and validate collaborative scenarios in individual stakeholder sessions - decoupled, since stakeholders can participate remotely and are not forced to be available for a joint session at the same time. This thesis discusses and evaluates the feasibility, understandability, and modifiability of model-based virtual prototypes. Similarly to how physical prototypes are perceived, the presented approach brings behavioral models closer to being tangible for stakeholders and, moreover, combines the advantages of joint stakeholder sessions and decoupled sessions.}, language = {en} } @book{BerovHenningMattisetal.2013, author = {Berov, Leonid and Henning, Johannes and Mattis, Toni and Rein, Patrick and Schreiber, Robin and Seckler, Eric and Steinert, Bastian and Hirschfeld, Robert}, title = {Vereinfachung der Entwicklung von Gesch{\"a}ftsanwendungen durch Konsolidierung von Programmierkonzepten und -technologien}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-231-5}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64045}, publisher = {Universit{\"a}t Potsdam}, pages = {186}, year = {2013}, abstract = {Die Komplexit{\"a}t heutiger Gesch{\"a}ftsabl{\"a}ufe und die Menge der zu verwaltenden Daten stellen hohe Anforderungen an die Entwicklung und Wartung von Gesch{\"a}ftsanwendungen. Ihr Umfang entsteht unter anderem aus der Vielzahl von Modellentit{\"a}ten und zugeh{\"o}rigen Nutzeroberfl{\"a}chen zur Bearbeitung und Analyse der Daten. Dieser Bericht pr{\"a}sentiert neuartige Konzepte und deren Umsetzung zur Vereinfachung der Entwicklung solcher umfangreichen Gesch{\"a}ftsanwendungen. Erstens: Wir schlagen vor, die Datenbank und die Laufzeitumgebung einer dynamischen objektorientierten Programmiersprache zu vereinen. Hierzu organisieren wir die Speicherstruktur von Objekten auf die Weise einer spaltenorientierten Hauptspeicherdatenbank und integrieren darauf aufbauend Transaktionen sowie eine deklarative Anfragesprache nahtlos in dieselbe Laufzeitumgebung. Somit k{\"o}nnen transaktionale und analytische Anfragen in derselben objektorientierten Hochsprache implementiert werden, und dennoch nah an den Daten ausgef{\"u}hrt werden. Zweitens: Wir beschreiben Programmiersprachkonstrukte, welche es erlauben, Nutzeroberfl{\"a}chen sowie Nutzerinteraktionen generisch und unabh{\"a}ngig von konkreten Modellentit{\"a}ten zu beschreiben. Um diese abstrakte Beschreibung nutzen zu k{\"o}nnen, reichert man die Dom{\"a}nenmodelle um vormals implizite Informationen an. Neue Modelle m{\"u}ssen nur um einige Informationen erweitert werden um bereits vorhandene Nutzeroberfl{\"a}chen und -interaktionen auch f{\"u}r sie verwenden zu k{\"o}nnen. Anpassungen, die nur f{\"u}r ein Modell gelten sollen, k{\"o}nnen unabh{\"a}ngig vom Standardverhalten, inkrementell, definiert werden. Drittens: Wir erm{\"o}glichen mit einem weiteren Programmiersprachkonstrukt die zusammenh{\"a}ngende Beschreibung von Abl{\"a}ufen der Anwendung, wie z.B. Bestellprozesse. Unser Programmierkonzept kapselt Nutzerinteraktionen in synchrone Funktionsaufrufe und macht somit Prozesse als zusammenh{\"a}ngende Folge von Berechnungen und Interaktionen darstellbar. Viertens: Wir demonstrieren ein Konzept, wie Endnutzer komplexe analytische Anfragen intuitiver formulieren k{\"o}nnen. Es basiert auf der Idee, dass Endnutzer Anfragen als Konfiguration eines Diagramms sehen. Entsprechend beschreibt ein Nutzer eine Anfrage, indem er beschreibt, was sein Diagramm darstellen soll. Nach diesem Konzept beschriebene Diagramme enthalten ausreichend Informationen, um daraus eine Anfrage generieren zu k{\"o}nnen. Hinsichtlich der Ausf{\"u}hrungsdauer sind die generierten Anfragen {\"a}quivalent zu Anfragen, die mit konventionellen Anfragesprachen formuliert sind. Das Anfragemodell setzen wir in einem Prototypen um, der auf den zuvor eingef{\"u}hrten Konzepten aufsetzt.}, language = {de} } @phdthesis{Beyhl2017, author = {Beyhl, Thomas}, title = {A framework for incremental view graph maintenance}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-405929}, school = {Universit{\"a}t Potsdam}, pages = {VII, 293}, year = {2017}, abstract = {Nowadays, graph data models are employed, when relationships between entities have to be stored and are in the scope of queries. For each entity, this graph data model locally stores relationships to adjacent entities. Users employ graph queries to query and modify these entities and relationships. These graph queries employ graph patterns to lookup all subgraphs in the graph data that satisfy certain graph structures. These subgraphs are called graph pattern matches. However, this graph pattern matching is NP-complete for subgraph isomorphism. Thus, graph queries can suffer a long response time, when the number of entities and relationships in the graph data or the graph patterns increases. One possibility to improve the graph query performance is to employ graph views that keep ready graph pattern matches for complex graph queries for later retrieval. However, these graph views must be maintained by means of an incremental graph pattern matching to keep them consistent with the graph data from which they are derived, when the graph data changes. This maintenance adds subgraphs that satisfy a graph pattern to the graph views and removes subgraphs that do not satisfy a graph pattern anymore from the graph views. Current approaches for incremental graph pattern matching employ Rete networks. Rete networks are discrimination networks that enumerate and maintain all graph pattern matches of certain graph queries by employing a network of condition tests, which implement partial graph patterns that together constitute the overall graph query. Each condition test stores all subgraphs that satisfy the partial graph pattern. Thus, Rete networks suffer high memory consumptions, because they store a large number of partial graph pattern matches. But, especially these partial graph pattern matches enable Rete networks to update the stored graph pattern matches efficiently, because the network maintenance exploits the already stored partial graph pattern matches to find new graph pattern matches. However, other kinds of discrimination networks exist that can perform better in time and space than Rete networks. Currently, these other kinds of networks are not used for incremental graph pattern matching. This thesis employs generalized discrimination networks for incremental graph pattern matching. These discrimination networks permit a generalized network structure of condition tests to enable users to steer the trade-off between memory consumption and execution time for the incremental graph pattern matching. For that purpose, this thesis contributes a modeling language for the effective definition of generalized discrimination networks. Furthermore, this thesis contributes an efficient and scalable incremental maintenance algorithm, which updates the (partial) graph pattern matches that are stored by each condition test. Moreover, this thesis provides a modeling evaluation, which shows that the proposed modeling language enables the effective modeling of generalized discrimination networks. Furthermore, this thesis provides a performance evaluation, which shows that a) the incremental maintenance algorithm scales, when the graph data becomes large, and b) the generalized discrimination network structures can outperform Rete network structures in time and space at the same time for incremental graph pattern matching.}, language = {en} } @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} } @book{BeyhlGiese2015, author = {Beyhl, Thomas and Giese, Holger}, title = {Efficient and scalable graph view maintenance for deductive graph databases based on generalized discrimination networks}, number = {99}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-339-8}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-79535}, publisher = {Universit{\"a}t Potsdam}, pages = {148}, year = {2015}, abstract = {Graph databases provide a natural way of storing and querying graph data. In contrast to relational databases, queries over graph databases enable to refer directly to the graph structure of such graph data. For example, graph pattern matching can be employed to formulate queries over graph data. However, as for relational databases running complex queries can be very time-consuming and ruin the interactivity with the database. One possible approach to deal with this performance issue is to employ database views that consist of pre-computed answers to common and often stated queries. But to ensure that database views yield consistent query results in comparison with the data from which they are derived, these database views must be updated before queries make use of these database views. Such a maintenance of database views must be performed efficiently, otherwise the effort to create and maintain views may not pay off in comparison to processing the queries directly on the data from which the database views are derived. At the time of writing, graph databases do not support database views and are limited to graph indexes that index nodes and edges of the graph data for fast query evaluation, but do not enable to maintain pre-computed answers of complex queries over graph data. Moreover, the maintenance of database views in graph databases becomes even more challenging when negation and recursion have to be supported as in deductive relational databases. In this technical report, we present an approach for the efficient and scalable incremental graph view maintenance for deductive graph databases. The main concept of our approach is a generalized discrimination network that enables to model nested graph conditions including negative application conditions and recursion, which specify the content of graph views derived from graph data stored by graph databases. The discrimination network enables to automatically derive generic maintenance rules using graph transformations for maintaining graph views in case the graph data from which the graph views are derived change. We evaluate our approach in terms of a case study using multiple data sets derived from open source projects.}, language = {en} } @article{BiloLenzner2019, author = {Bil{\`o}, Davide and Lenzner, Pascal}, title = {On the tree conjecture for the network creation game}, series = {Theory of computing systems}, volume = {64}, journal = {Theory of computing systems}, number = {3}, publisher = {Springer}, address = {New York}, issn = {1432-4350}, doi = {10.1007/s00224-019-09945-9}, pages = {422 -- 443}, year = {2019}, abstract = {Selfish Network Creation focuses on modeling real world networks from a game-theoretic point of view. One of the classic models by Fabrikant et al. (2003) is the network creation game, where agents correspond to nodes in a network which buy incident edges for the price of alpha per edge to minimize their total distance to all other nodes. The model is well-studied but still has intriguing open problems. The most famous conjectures state that the price of anarchy is constant for all alpha and that for alpha >= n all equilibrium networks are trees. We introduce a novel technique for analyzing stable networks for high edge-price alpha and employ it to improve on the best known bound for the latter conjecture. In particular we show that for alpha > 4n - 13 all equilibrium networks must be trees, which implies a constant price of anarchy for this range of alpha. Moreover, we also improve the constant upper bound on the price of anarchy for equilibrium trees.}, language = {en} } @article{BirnickBlaesiusFriedrichetal.2020, author = {Birnick, Johann and Bl{\"a}sius, Thomas and Friedrich, Tobias and Naumann, Felix and Papenbrock, Thorsten and Schirneck, Friedrich Martin}, title = {Hitting set enumeration with partial information for unique column combination discovery}, series = {Proceedings of the VLDB Endowment}, volume = {13}, journal = {Proceedings of the VLDB Endowment}, number = {11}, publisher = {Association for Computing Machinery}, address = {[New York, NY]}, issn = {2150-8097}, doi = {10.14778/3407790.3407824}, pages = {2270 -- 2283}, year = {2020}, abstract = {Unique column combinations (UCCs) are a fundamental concept in relational databases. They identify entities in the data and support various data management activities. Still, UCCs are usually not explicitly defined and need to be discovered. State-of-the-art data profiling algorithms are able to efficiently discover UCCs in moderately sized datasets, but they tend to fail on large and, in particular, on wide datasets due to run time and memory limitations.
In this paper, we introduce HPIValid, a novel UCC discovery algorithm that implements a faster and more resource-saving search strategy. HPIValid models the metadata discovery as a hitting set enumeration problem in hypergraphs. In this way, it combines efficient discovery techniques from data profiling research with the most recent theoretical insights into enumeration algorithms. Our evaluation shows that HPIValid is not only orders of magnitude faster than related work, it also has a much smaller memory footprint.}, language = {en} } @misc{BjoerkHoelze2019, author = {Bj{\"o}rk, Jennie and H{\"o}lze, Katharina}, title = {Editorial}, series = {Creativity and innovation management}, volume = {28}, journal = {Creativity and innovation management}, number = {3}, publisher = {Wiley}, address = {Hoboken}, issn = {0963-1690}, doi = {10.1111/caim.12336}, pages = {289 -- 290}, year = {2019}, language = {en} } @article{BjoerkHoelzleBoer2021, author = {Bj{\"o}rk, Jennie and H{\"o}lzle, Katharina and Boer, Harry}, title = {'What will we learn from the current crisis?'}, series = {Creativity and innovation management}, volume = {30}, journal = {Creativity and innovation management}, number = {2}, publisher = {Wiley-Blackwell}, address = {Oxford [u.a.]}, issn = {0963-1690}, doi = {10.1111/caim.12442}, pages = {231 -- 232}, year = {2021}, language = {en} } @article{BlaesiusFriedrichSchirneck2021, author = {Blaesius, Thomas and Friedrich, Tobias and Schirneck, Friedrich Martin}, title = {The complexity of dependency detection and discovery in relational databases}, series = {Theoretical computer science}, volume = {900}, journal = {Theoretical computer science}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0304-3975}, doi = {10.1016/j.tcs.2021.11.020}, pages = {79 -- 96}, year = {2021}, abstract = {Multi-column dependencies in relational databases come associated with two different computational tasks. The detection problem is to decide whether a dependency of a certain type and size holds in a given database, the discovery problem asks to enumerate all valid dependencies of that type. We settle the complexity of both of these problems for unique column combinations (UCCs), functional dependencies (FDs), and inclusion dependencies (INDs). We show that the detection of UCCs and FDs is W[2]-complete when parameterized by the solution size. The discovery of inclusion-wise minimal UCCs is proven to be equivalent under parsimonious reductions to the transversal hypergraph problem of enumerating the minimal hitting sets of a hypergraph. The discovery of FDs is equivalent to the simultaneous enumeration of the hitting sets of multiple input hypergraphs. We further identify the detection of INDs as one of the first natural W[3]-complete problems. The discovery of maximal INDs is shown to be equivalent to enumerating the maximal satisfying assignments of antimonotone, 3-normalized Boolean formulas.}, language = {en} } @article{BlaesiusFreibergerFriedrichetal.2022, author = {Bl{\"a}sius, Thomas and Freiberger, Cedric and Friedrich, Tobias and Katzmann, Maximilian and Montenegro-Retana, Felix and Thieffry, Marianne}, title = {Efficient Shortest Paths in Scale-Free Networks with Underlying Hyperbolic Geometry}, series = {ACM Transactions on Algorithms}, volume = {18}, journal = {ACM Transactions on Algorithms}, number = {2}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {1549-6325}, doi = {10.1145/3516483}, pages = {1 -- 32}, year = {2022}, abstract = {A standard approach to accelerating shortest path algorithms on networks is the bidirectional search, which explores the graph from the start and the destination, simultaneously. In practice this strategy performs particularly well on scale-free real-world networks. Such networks typically have a heterogeneous degree distribution (e.g., a power-law distribution) and high clustering (i.e., vertices with a common neighbor are likely to be connected themselves). These two properties can be obtained by assuming an underlying hyperbolic geometry.
To explain the observed behavior of the bidirectional search, we analyze its running time on hyperbolic random graphs and prove that it is (O) over tilde (n(2-1/alpha) + n(1/(2 alpha)) + delta(max)) with high probability, where alpha is an element of (1/2, 1) controls the power-law exponent of the degree distribution, and dmax is the maximum degree. This bound is sublinear, improving the obvious worst-case linear bound. Although our analysis depends on the underlying geometry, the algorithm itself is oblivious to it.}, language = {en} } @book{BoeddinghausMeinelSack2011, author = {Boeddinghaus, Wilhelm and Meinel, Christoph and Sack, Harald}, title = {Einf{\"u}hrung von IPv6 in Unternehmensnetzen : ein Leitfaden}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-156-1}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-54582}, publisher = {Universit{\"a}t Potsdam}, pages = {51}, year = {2011}, language = {de} } @article{BogPlattnerZeier2011, author = {Bog, Anja and Plattner, Hasso and Zeier, Alexander}, title = {A mixed transaction processing and operational reporting benchmark}, series = {Information systems frontiers}, volume = {13}, journal = {Information systems frontiers}, number = {3}, publisher = {Springer}, address = {Dordrecht}, issn = {1387-3326}, doi = {10.1007/s10796-010-9283-8}, pages = {321 -- 335}, year = {2011}, abstract = {The importance of reporting is ever increasing in today's fast-paced market environments and the availability of up-to-date information for reporting has become indispensable. Current reporting systems are separated from the online transaction processing systems (OLTP) with periodic updates pushed in. A pre-defined and aggregated subset of the OLTP data, however, does not provide the flexibility, detail, and timeliness needed for today's operational reporting. As technology advances, this separation has to be re-evaluated and means to study and evaluate new trends in data storage management have to be provided. This article proposes a benchmark for combined OLTP and operational reporting, providing means to evaluate the performance of enterprise data management systems for mixed workloads of OLTP and operational reporting queries. Such systems offer up-to-date information and the flexibility of the entire data set for reporting. We describe how the benchmark provokes the conflicts that are the reason for separating the two workloads on different systems. In this article, we introduce the concepts, logical data schema, transactions and queries of the benchmark, which are entirely based on the original data sets and real workloads of existing, globally operating enterprises.}, language = {en} } @article{BohnKundisch2020, author = {Bohn, Nicolai and Kundisch, Dennis}, title = {What are we talking about when we talk about technology pivots?}, series = {Information \& management}, volume = {57}, journal = {Information \& management}, number = {6}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0378-7206}, doi = {10.1016/j.im.2020.103319}, pages = {20}, year = {2020}, abstract = {Technology pivots were designed to help digital startups make adjustments to the technology underpinning their products and services. While academia and the media make liberal use of the term "technology pivot," they rarely align themselves to Ries' foundational conceptualization. Recent research suggests that a more granulated conceptualization of technology pivots is required. To scientifically derive a comprehensive conceptualization, we conduct a Delphi study with a panel of 38 experts drawn from academia and practice to explore their understanding of "technology pivots." Our study thus makes an important contribution to advance the seminal work by Ries on technology pivots.}, language = {en} } @article{Boissier2021, author = {Boissier, Martin}, title = {Robust and budget-constrained encoding configurations for in-memory database systems}, series = {Proceedings of the VLDB Endowment}, volume = {15}, journal = {Proceedings of the VLDB Endowment}, number = {4}, publisher = {Association for Computing Machinery (ACM)}, address = {[New York]}, issn = {2150-8097}, doi = {10.14778/3503585.3503588}, pages = {780 -- 793}, year = {2021}, abstract = {Data encoding has been applied to database systems for decades as it mitigates bandwidth bottlenecks and reduces storage requirements. But even in the presence of these advantages, most in-memory database systems use data encoding only conservatively as the negative impact on runtime performance can be severe. Real-world systems with large parts being infrequently accessed and cost efficiency constraints in cloud environments require solutions that automatically and efficiently select encoding techniques, including heavy-weight compression. In this paper, we introduce workload-driven approaches to automaticaly determine memory budget-constrained encoding configurations using greedy heuristics and linear programming. We show for TPC-H, TPC-DS, and the Join Order Benchmark that optimized encoding configurations can reduce the main memory footprint significantly without a loss in runtime performance over state-of-the-art dictionary encoding. To yield robust selections, we extend the linear programming-based approach to incorporate query runtime constraints and mitigate unexpected performance regressions.}, language = {en} } @article{BonifatiMiorNaumannetal.2022, author = {Bonifati, Angela and Mior, Michael J. and Naumann, Felix and Noack, Nele Sina}, title = {How inclusive are we?}, series = {SIGMOD record / Association for Computing Machinery, Special Interest Group on Management of Data}, volume = {50}, journal = {SIGMOD record / Association for Computing Machinery, Special Interest Group on Management of Data}, number = {4}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {0163-5808}, doi = {10.1145/3516431.3516438}, pages = {30 -- 35}, year = {2022}, abstract = {ACM SIGMOD, VLDB and other database organizations have committed to fostering an inclusive and diverse community, as do many other scientific organizations. Recently, different measures have been taken to advance these goals, especially for underrepresented groups. One possible measure is double-blind reviewing, which aims to hide gender, ethnicity, and other properties of the authors.
We report the preliminary results of a gender diversity analysis of publications of the database community across several peer-reviewed venues, and also compare women's authorship percentages in both single-blind and double-blind venues along the years. We also obtained a cross comparison of the obtained results in data management with other relevant areas in Computer Science.}, language = {en} } @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{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 = {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/bbab134}, pages = {17}, year = {2021}, abstract = {Precision oncology is a rapidly evolving interdisciplinary medical specialty. Comprehensive cancer panels are becoming increasingly available at pathology departments worldwide, creating the urgent need for scalable cancer variant annotation and molecularly informed treatment recommendations. A wealth of mainly academia-driven knowledge bases calls for software tools supporting the multi-step diagnostic process. We derive a comprehensive list of knowledge bases relevant for variant interpretation by a review of existing literature followed by a survey among medical experts from university hospitals in Germany. In addition, we review cancer variant interpretation tools, which integrate multiple knowledge bases. We categorize the knowledge bases along the diagnostic process in precision oncology and analyze programmatic access options as well as the integration of knowledge bases into software tools. The most commonly used knowledge bases provide good programmatic access options and have been integrated into a range of software tools. For the wider set of knowledge bases, access options vary across different parts of the diagnostic process. Programmatic access is limited for information regarding clinical classifications of variants and for therapy recommendations. The main issue for databases used for biological classification of pathogenic variants and pathway context information is the lack of standardized interfaces. There is no single cancer variant interpretation tool that integrates all identified knowledge bases. Specialized tools are available and need to be further developed for different steps in the diagnostic process.}, language = {en} } @phdthesis{Brauer2010, author = {Brauer, Falk}, title = {Extraktion und Identifikation von Entit{\"a}ten in Textdaten im Umfeld der Enterprise Search}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-51409}, school = {Universit{\"a}t Potsdam}, year = {2010}, abstract = {Die automatische Informationsextraktion (IE) aus unstrukturierten Texten erm{\"o}glicht v{\"o}llig neue Wege, auf relevante Informationen zuzugreifen und deren Inhalte zu analysieren, die weit {\"u}ber bisherige Verfahren zur Stichwort-basierten Dokumentsuche hinausgehen. Die Entwicklung von Programmen zur Extraktion von maschinenlesbaren Daten aus Texten erfordert jedoch nach wie vor die Entwicklung von dom{\"a}nenspezifischen Extraktionsprogrammen. Insbesondere im Bereich der Enterprise Search (der Informationssuche im Unternehmensumfeld), in dem eine große Menge von heterogenen Dokumenttypen existiert, ist es oft notwendig ad-hoc Programm-module zur Extraktion von gesch{\"a}ftsrelevanten Entit{\"a}ten zu entwickeln, die mit generischen Modulen in monolithischen IE-Systemen kombiniert werden. Dieser Umstand ist insbesondere kritisch, da potentiell f{\"u}r jeden einzelnen Anwendungsfall ein von Grund auf neues IE-System entwickelt werden muss. Die vorliegende Dissertation untersucht die effiziente Entwicklung und Ausf{\"u}hrung von IE-Systemen im Kontext der Enterprise Search und effektive Methoden zur Ausnutzung bekannter strukturierter Daten im Unternehmenskontext f{\"u}r die Extraktion und Identifikation von gesch{\"a}ftsrelevanten Entit{\"a}ten in Doku-menten. Grundlage der Arbeit ist eine neuartige Plattform zur Komposition von IE-Systemen auf Basis der Beschreibung des Datenflusses zwischen generischen und anwendungsspezifischen IE-Modulen. Die Plattform unterst{\"u}tzt insbesondere die Entwicklung und Wiederverwendung von generischen IE-Modulen und zeichnet sich durch eine h{\"o}here Flexibilit{\"a}t und Ausdrucksm{\"a}chtigkeit im Vergleich zu vorherigen Methoden aus. Ein in der Dissertation entwickeltes Verfahren zur Dokumentverarbeitung interpretiert den Daten-austausch zwischen IE-Modulen als Datenstr{\"o}me und erm{\"o}glicht damit eine weitgehende Parallelisierung von einzelnen Modulen. Die autonome Ausf{\"u}hrung der Module f{\"u}hrt zu einer wesentlichen Beschleu-nigung der Verarbeitung von Einzeldokumenten und verbesserten Antwortzeiten, z. B. f{\"u}r Extraktions-dienste. Bisherige Ans{\"a}tze untersuchen lediglich die Steigerung des durchschnittlichen Dokumenten-durchsatzes durch verteilte Ausf{\"u}hrung von Instanzen eines IE-Systems. Die Informationsextraktion im Kontext der Enterprise Search unterscheidet sich z. B. von der Extraktion aus dem World Wide Web dadurch, dass in der Regel strukturierte Referenzdaten z. B. in Form von Unternehmensdatenbanken oder Terminologien zur Verf{\"u}gung stehen, die oft auch die Beziehungen von Entit{\"a}ten beschreiben. Entit{\"a}ten im Unternehmensumfeld haben weiterhin bestimmte Charakteristiken: Eine Klasse von relevanten Entit{\"a}ten folgt bestimmten Bildungsvorschriften, die nicht immer bekannt sind, auf die aber mit Hilfe von bekannten Beispielentit{\"a}ten geschlossen werden kann, so dass unbekannte Entit{\"a}ten extrahiert werden k{\"o}nnen. Die Bezeichner der anderen Klasse von Entit{\"a}ten haben eher umschreibenden Charakter. Die korrespondierenden Umschreibungen in Texten k{\"o}nnen variieren, wodurch eine Identifikation derartiger Entit{\"a}ten oft erschwert wird. Zur effizienteren Entwicklung von IE-Systemen wird in der Dissertation ein Verfahren untersucht, das alleine anhand von Beispielentit{\"a}ten effektive Regul{\"a}re Ausdr{\"u}cke zur Extraktion von unbekannten Entit{\"a}ten erlernt und damit den manuellen Aufwand in derartigen Anwendungsf{\"a}llen minimiert. Verschiedene Generalisierungs- und Spezialisierungsheuristiken erkennen Muster auf verschiedenen Abstraktionsebenen und schaffen dadurch einen Ausgleich zwischen Genauigkeit und Vollst{\"a}ndigkeit bei der Extraktion. Bekannte Regellernverfahren im Bereich der Informationsextraktion unterst{\"u}tzen die beschriebenen Problemstellungen nicht, sondern ben{\"o}tigen einen (annotierten) Dokumentenkorpus. Eine Methode zur Identifikation von Entit{\"a}ten, die durch Graph-strukturierte Referenzdaten vordefiniert sind, wird als dritter Schwerpunkt untersucht. Es werden Verfahren konzipiert, welche {\"u}ber einen exakten Zeichenkettenvergleich zwischen Text und Referenzdatensatz hinausgehen und Teil{\"u}bereinstimmungen und Beziehungen zwischen Entit{\"a}ten zur Identifikation und Disambiguierung heranziehen. Das in der Arbeit vorgestellte Verfahren ist bisherigen Ans{\"a}tzen hinsichtlich der Genauigkeit und Vollst{\"a}ndigkeit bei der Identifikation {\"u}berlegen.}, language = {de} } @book{BreestBoucheGrundetal.2006, author = {Breest, Martin and Bouch{\´e}, Paul and Grund, Martin and Haubrock, S{\"o}ren and H{\"u}ttenrauch, Stefan and Kylau, Uwe and Ploskonos, Anna and Queck, Tobias and Schreiter, Torben}, title = {Fundamentals of Service-Oriented Engineering}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-939469-35-3}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-33801}, publisher = {Universit{\"a}t Potsdam}, pages = {Getr. Z{\"a}hlung}, year = {2006}, abstract = {Since 2002, keywords like service-oriented engineering, service-oriented computing, and service-oriented architecture have been widely used in research, education, and enterprises. These and related terms are often misunderstood or used incorrectly. To correct these misunderstandings, a deeper knowledge of the concepts, the historical backgrounds, and an overview of service-oriented architectures is demanded and given in this paper.}, language = {en} } @article{BuchwaldWagelaarDanetal.2014, author = {Buchwald, Sebastian and Wagelaar, Dennis and Dan, Li and Hegedues, Abel and Herrmannsdoerfer, Markus and Horn, Tassilo and Kalnina, Elina and Krause, Christian and Lano, Kevin and Lepper, Markus and Rensink, Arend and Rose, Louis and Waetzoldt, Sebastian and Mazanek, Steffen}, title = {A survey and comparison of transformation tools based on the transformation tool contest}, series = {Science of computer programming}, volume = {85}, journal = {Science of computer programming}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0167-6423}, doi = {10.1016/j.scico.2013.10.009}, pages = {41 -- 99}, year = {2014}, abstract = {Model transformation is one of the key tasks in model-driven engineering and relies on the efficient matching and modification of graph-based data structures; its sibling graph rewriting has been used to successfully model problems in a variety of domains. Over the last years, a wide range of graph and model transformation tools have been developed all of them with their own particular strengths and typical application domains. In this paper, we give a survey and a comparison of the model and graph transformation tools that participated at the Transformation Tool Contest 2011. The reader gains an overview of the field and its tools, based on the illustrative solutions submitted to a Hello World task, and a comparison alongside a detailed taxonomy. The article is of interest to researchers in the field of model and graph transformation, as well as to software engineers with a transformation task at hand who have to choose a tool fitting to their needs. All solutions referenced in this article provide a SHARE demo. It supported the peer-review process for the contest, and now allows the reader to test the tools online.}, language = {en} } @inproceedings{BynensVanLanduytTruyenetal.2010, author = {Bynens, Maarten and Van Landuyt, Dimitri and Truyen, Eddy and Joosen, Wouter}, title = {Towards reusable aspects: the callback mismatch problem}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-41347}, year = {2010}, abstract = {Because software development is increasingly expensive and timeconsuming, software reuse gains importance. Aspect-oriented software development modularizes crosscutting concerns which enables their systematic reuse. Literature provides a number of AOP patterns and best practices for developing reusable aspects based on compelling examples for concerns like tracing, transactions and persistence. However, such best practices are lacking for systematically reusing invasive aspects. In this paper, we present the 'callback mismatch problem'. This problem arises in the context of abstraction mismatch, in which the aspect is required to issue a callback to the base application. As a consequence, the composition of invasive aspects is cumbersome to implement, difficult to maintain and impossible to reuse. We motivate this problem in a real-world example, show that it persists in the current state-of-the-art, and outline the need for advanced aspectual composition mechanisms to deal with this.}, language = {en} } @phdthesis{Boehm2013, author = {B{\"o}hm, Christoph}, title = {Enriching the Web of Data with topics and links}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-68624}, school = {Universit{\"a}t Potsdam}, year = {2013}, abstract = {This thesis presents novel ideas and research findings for the Web of Data - a global data space spanning many so-called Linked Open Data sources. Linked Open Data adheres to a set of simple principles to allow easy access and reuse for data published on the Web. Linked Open Data is by now an established concept and many (mostly academic) publishers adopted the principles building a powerful web of structured knowledge available to everybody. However, so far, Linked Open Data does not yet play a significant role among common web technologies that currently facilitate a high-standard Web experience. In this work, we thoroughly discuss the state-of-the-art for Linked Open Data and highlight several shortcomings - some of them we tackle in the main part of this work. First, we propose a novel type of data source meta-information, namely the topics of a dataset. This information could be published with dataset descriptions and support a variety of use cases, such as data source exploration and selection. For the topic retrieval, we present an approach coined Annotated Pattern Percolation (APP), which we evaluate with respect to topics extracted from Wikipedia portals. Second, we contribute to entity linking research by presenting an optimization model for joint entity linking, showing its hardness, and proposing three heuristics implemented in the LINked Data Alignment (LINDA) system. Our first solution can exploit multi-core machines, whereas the second and third approach are designed to run in a distributed shared-nothing environment. We discuss and evaluate the properties of our approaches leading to recommendations which algorithm to use in a specific scenario. The distributed algorithms are among the first of their kind, i.e., approaches for joint entity linking in a distributed fashion. Also, we illustrate that we can tackle the entity linking problem on the very large scale with data comprising more than 100 millions of entity representations from very many sources. Finally, we approach a sub-problem of entity linking, namely the alignment of concepts. We again target a method that looks at the data in its entirety and does not neglect existing relations. Also, this concept alignment method shall execute very fast to serve as a preprocessing for further computations. Our approach, called Holistic Concept Matching (HCM), achieves the required speed through grouping the input by comparing so-called knowledge representations. Within the groups, we perform complex similarity computations, relation conclusions, and detect semantic contradictions. The quality of our result is again evaluated on a large and heterogeneous dataset from the real Web. In summary, this work contributes a set of techniques for enhancing the current state of the Web of Data. All approaches have been tested on large and heterogeneous real-world input.}, language = {en} } @article{Boettinger2019, author = {B{\"o}ttinger, Erwin}, title = {Wendepunkt f{\"u}r Gesundheit}, series = {Die Zukunft der Medizin : Disruptive Innovationen revolutionieren Medizin und Gesundheit}, journal = {Die Zukunft der Medizin : Disruptive Innovationen revolutionieren Medizin und Gesundheit}, publisher = {Medizinisch Wissenschaftliche Verlagsgesellschaft}, address = {Berlin}, isbn = {978-3-95466-398-9}, pages = {201 -- 210}, year = {2019}, language = {de} } @article{CabalarKaminskiSchaubetal.2018, author = {Cabalar, Pedro and Kaminski, Roland and Schaub, Torsten H. and Schuhmann, Anna}, title = {Temporal answer set programming on finite traces}, series = {Theory and practice of logic programming}, volume = {18}, journal = {Theory and practice of logic programming}, number = {3-4}, publisher = {Cambridge Univ. Press}, address = {New York}, issn = {1471-0684}, doi = {10.1017/S1471068418000297}, pages = {406 -- 420}, year = {2018}, abstract = {In this paper, we introduce an alternative approach to Temporal Answer Set Programming that relies on a variation of Temporal Equilibrium Logic (TEL) for finite traces. This approach allows us to even out the expressiveness of TEL over infinite traces with the computational capacity of (incremental) Answer Set Programming (ASP). Also, we argue that finite traces are more natural when reasoning about action and change. As a result, our approach is readily implementable via multi-shot ASP systems and benefits from an extension of ASP's full-fledged input language with temporal operators. This includes future as well as past operators whose combination offers a rich temporal modeling language. For computation, we identify the class of temporal logic programs and prove that it constitutes a normal form for our approach. Finally, we outline two implementations, a generic one and an extension of the ASP system clingo. Under consideration for publication in Theory and Practice of Logic Programming (TPLP)}, language = {en} } @book{CalmezHesseSiegmundetal.2013, author = {Calmez, Conrad and Hesse, Hubert and Siegmund, Benjamin and Stamm, Sebastian and Thomschke, Astrid and Hirschfeld, Robert and Ingalls, Dan and Lincke, Jens}, title = {Explorative authoring of Active Web content in a mobile environment}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-232-2}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64054}, publisher = {Universit{\"a}t Potsdam}, pages = {132}, year = {2013}, abstract = {Developing rich Web applications can be a complex job - especially when it comes to mobile device support. Web-based environments such as Lively Webwerkstatt can help developers implement such applications by making the development process more direct and interactive. Further the process of developing software is collaborative which creates the need that the development environment offers collaboration facilities. This report describes extensions of the webbased development environment Lively Webwerkstatt such that it can be used in a mobile environment. The extensions are collaboration mechanisms, user interface adaptations but as well event processing and performance measuring on mobile devices.}, language = {en} } @article{CaruccioDeufemiaNaumannetal.2021, author = {Caruccio, Loredana and Deufemia, Vincenzo and Naumann, Felix and Polese, Giuseppe}, title = {Discovering relaxed functional dependencies based on multi-attribute dominance}, series = {IEEE transactions on knowledge and data engineering}, volume = {33}, journal = {IEEE transactions on knowledge and data engineering}, number = {9}, publisher = {Institute of Electrical and Electronics Engineers}, address = {New York, NY}, issn = {1041-4347}, doi = {10.1109/TKDE.2020.2967722}, pages = {3212 -- 3228}, year = {2021}, abstract = {With the advent of big data and data lakes, data are often integrated from multiple sources. Such integrated data are often of poor quality, due to inconsistencies, errors, and so forth. One way to check the quality of data is to infer functional dependencies (fds). However, in many modern applications it might be necessary to extract properties and relationships that are not captured through fds, due to the necessity to admit exceptions, or to consider similarity rather than equality of data values. Relaxed fds (rfds) have been introduced to meet these needs, but their discovery from data adds further complexity to an already complex problem, also due to the necessity of specifying similarity and validity thresholds. We propose Domino, a new discovery algorithm for rfds that exploits the concept of dominance in order to derive similarity thresholds of attribute values while inferring rfds. An experimental evaluation on real datasets demonstrates the discovery performance and the effectiveness of the proposed algorithm.}, language = {en} } @article{CaselFernauGaspersetal.2020, author = {Casel, Katrin and Fernau, Henning and Gaspers, Serge and Gras, Benjamin and Schmid, Markus L.}, title = {On the complexity of the smallest grammar problem over fixed alphabets}, series = {Theory of computing systems}, volume = {65}, journal = {Theory of computing systems}, number = {2}, publisher = {Springer}, address = {New York}, issn = {1432-4350}, doi = {10.1007/s00224-020-10013-w}, pages = {344 -- 409}, year = {2020}, abstract = {In the smallest grammar problem, we are given a word w and we want to compute a preferably small context-free grammar G for the singleton language {w} (where the size of a grammar is the sum of the sizes of its rules, and the size of a rule is measured by the length of its right side). It is known that, for unbounded alphabets, the decision variant of this problem is NP-hard and the optimisation variant does not allow a polynomial-time approximation scheme, unless P = NP. We settle the long-standing open problem whether these hardness results also hold for the more realistic case of a constant-size alphabet. More precisely, it is shown that the smallest grammar problem remains NP-complete (and its optimisation version is APX-hard), even if the alphabet is fixed and has size of at least 17. The corresponding reduction is robust in the sense that it also works for an alternative size-measure of grammars that is commonly used in the literature (i. e., a size measure also taking the number of rules into account), and it also allows to conclude that even computing the number of rules required by a smallest grammar is a hard problem. On the other hand, if the number of nonterminals (or, equivalently, the number of rules) is bounded by a constant, then the smallest grammar problem can be solved in polynomial time, which is shown by encoding it as a problem on graphs with interval structure. However, treating the number of rules as a parameter (in terms of parameterised complexity) yields W[1]-hardness. Furthermore, we present an O(3(vertical bar w vertical bar)) exact exponential-time algorithm, based on dynamic programming. These three main questions are also investigated for 1-level grammars, i. e., grammars for which only the start rule contains nonterminals on the right side; thus, investigating the impact of the "hierarchical depth" of grammars on the complexity of the smallest grammar problem. In this regard, we obtain for 1-level grammars similar, but slightly stronger results.}, language = {en} } @article{ChanChaudharySahaetal.2021, author = {Chan, Lili and Chaudhary, Kumardeep and Saha, Aparna and Chauhan, Kinsuk and Vaid, Akhil and Zhao, Shan and Paranjpe, Ishan and Somani, Sulaiman and Richter, Felix and Miotto, Riccardo and Lala, Anuradha and Kia, Arash and Timsina, Prem and Li, Li and Freeman, Robert and Chen, Rong and Narula, Jagat and Just, Allan C. and Horowitz, Carol and Fayad, Zahi and Cordon-Cardo, Carlos and Schadt, Eric and Levin, Matthew A. and Reich, David L. and Fuster, Valentin and Murphy, Barbara and He, John C. and Charney, Alexander W. and B{\"o}ttinger, Erwin and Glicksberg, Benjamin and Coca, Steven G. and Nadkarni, Girish N.}, title = {AKI in hospitalized patients with COVID-19}, series = {Journal of the American Society of Nephrology : JASN}, volume = {32}, journal = {Journal of the American Society of Nephrology : JASN}, number = {1}, publisher = {American Society of Nephrology}, address = {Washington}, organization = {Mt Sinai COVID Informatics Ct}, issn = {1046-6673}, doi = {10.1681/ASN.2020050615}, pages = {151 -- 160}, year = {2021}, abstract = {Background: Early reports indicate that AKI is common among patients with coronavirus disease 2019 (COVID-19) and associatedwith worse outcomes. However, AKI among hospitalized patients with COVID19 in the United States is not well described. Methods: This retrospective, observational study involved a review of data from electronic health records of patients aged >= 18 years with laboratory-confirmed COVID-19 admitted to the Mount Sinai Health System from February 27 to May 30, 2020. We describe the frequency of AKI and dialysis requirement, AKI recovery, and adjusted odds ratios (aORs) with mortality. Results: Of 3993 hospitalized patients with COVID-19, AKI occurred in 1835 (46\%) patients; 347 (19\%) of the patientswith AKI required dialysis. The proportionswith stages 1, 2, or 3 AKIwere 39\%, 19\%, and 42\%, respectively. A total of 976 (24\%) patients were admitted to intensive care, and 745 (76\%) experienced AKI. Of the 435 patients with AKI and urine studies, 84\% had proteinuria, 81\% had hematuria, and 60\% had leukocyturia. Independent predictors of severe AKI were CKD, men, and higher serum potassium at admission. In-hospital mortality was 50\% among patients with AKI versus 8\% among those without AKI (aOR, 9.2; 95\% confidence interval, 7.5 to 11.3). Of survivors with AKI who were discharged, 35\% had not recovered to baseline kidney function by the time of discharge. An additional 28 of 77 (36\%) patients who had not recovered kidney function at discharge did so on posthospital follow-up. Conclusions: AKI is common among patients hospitalized with COVID-19 and is associated with high mortality. Of all patients with AKI, only 30\% survived with recovery of kidney function by the time of discharge.}, language = {en} } @article{ChanJaladankiSomanietal.2021, author = {Chan, Lili and Jaladanki, Suraj K. and Somani, Sulaiman and Paranjpe, Ishan and Kumar, Arvind and Zhao, Shan and Kaufman, Lewis and Leisman, Staci and Sharma, Shuchita and He, John Cijiang and Murphy, Barbara and Fayad, Zahi A. and Levin, Matthew A. and B{\"o}ttinger, Erwin and Charney, Alexander W. and Glicksberg, Benjamin and Coca, Steven G. and Nadkarni, Girish N.}, title = {Outcomes of patients on maintenance dialysis hospitalized with COVID-19}, series = {Clinical journal of the American Society of Nephrology : CJASN}, volume = {16}, journal = {Clinical journal of the American Society of Nephrology : CJASN}, number = {3}, publisher = {American Society of Nephrology}, address = {Washington}, organization = {Mount Sinai Covid I}, issn = {1555-9041}, doi = {10.2215/CJN.12360720}, pages = {452 -- 455}, year = {2021}, language = {en} } @article{ChauhanFriedrichRothenberger2020, author = {Chauhan, Ankit and Friedrich, Tobias and Rothenberger, Ralf}, title = {Greed is good for deterministic scale-free networks}, series = {Algorithmica : an international journal in computer science}, volume = {82}, journal = {Algorithmica : an international journal in computer science}, number = {11}, publisher = {Springer}, address = {New York}, issn = {0178-4617}, doi = {10.1007/s00453-020-00729-z}, pages = {3338 -- 3389}, year = {2020}, abstract = {Large real-world networks typically follow a power-law degree distribution. To study such networks, numerous random graph models have been proposed. However, real-world networks are not drawn at random. Therefore, Brach et al. (27th symposium on discrete algorithms (SODA), pp 1306-1325, 2016) introduced two natural deterministic conditions: (1) a power-law upper bound on the degree distribution (PLB-U) and (2) power-law neighborhoods, that is, the degree distribution of neighbors of each vertex is also upper bounded by a power law (PLB-N). They showed that many real-world networks satisfy both properties and exploit them to design faster algorithms for a number of classical graph problems. We complement their work by showing that some well-studied random graph models exhibit both of the mentioned PLB properties. PLB-U and PLB-N hold with high probability for Chung-Lu Random Graphs and Geometric Inhomogeneous Random Graphs and almost surely for Hyperbolic Random Graphs. As a consequence, all results of Brach et al. also hold with high probability or almost surely for those random graph classes. In the second part we study three classical NP-hard optimization problems on PLB networks. It is known that on general graphs with maximum degree Delta, a greedy algorithm, which chooses nodes in the order of their degree, only achieves a Omega (ln Delta)-approximation forMinimum Vertex Cover and Minimum Dominating Set, and a Omega(Delta)-approximation forMaximum Independent Set. We prove that the PLB-U property with beta>2 suffices for the greedy approach to achieve a constant-factor approximation for all three problems. We also show that these problems are APX-hard even if PLB-U, PLB-N, and an additional power-law lower bound on the degree distribution hold. Hence, a PTAS cannot be expected unless P = NP. Furthermore, we prove that all three problems are in MAX SNP if the PLB-U property holds.}, language = {en} } @article{ChromikKirstenHerdicketal.2022, author = {Chromik, Jonas and Kirsten, Kristina and Herdick, Arne and Kappattanavar, Arpita Mallikarjuna and Arnrich, Bert}, title = {SensorHub}, series = {Sensors}, volume = {22}, journal = {Sensors}, number = {1}, publisher = {MDPI}, address = {Basel}, issn = {1424-8220}, doi = {10.3390/s22010408}, pages = {18}, year = {2022}, abstract = {Observational studies are an important tool for determining whether the findings from controlled experiments can be transferred into scenarios that are closer to subjects' real-life circumstances. A rigorous approach to observational studies involves collecting data from different sensors to comprehensively capture the situation of the subject. However, this leads to technical difficulties especially if the sensors are from different manufacturers, as multiple data collection tools have to run simultaneously. We present SensorHub, a system that can collect data from various wearable devices from different manufacturers, such as inertial measurement units, portable electrocardiographs, portable electroencephalographs, portable photoplethysmographs, and sensors for electrodermal activity. Additionally, our tool offers the possibility to include ecological momentary assessments (EMAs) in studies. Hence, SensorHub enables multimodal sensor data collection under real-world conditions and allows direct user feedback to be collected through questionnaires, enabling studies at home. In a first study with 11 participants, we successfully used SensorHub to record multiple signals with different devices and collected additional information with the help of EMAs. In addition, we evaluated SensorHub's technical capabilities in several trials with up to 21 participants recording simultaneously using multiple sensors with sampling frequencies as high as 1000 Hz. We could show that although there is a theoretical limitation to the transmissible data rate, in practice this limitation is not an issue and data loss is rare. We conclude that with modern communication protocols and with the increasingly powerful smartphones and wearables, a system like our SensorHub establishes an interoperability framework to adequately combine consumer-grade sensing hardware which enables observational studies in real life.}, language = {en} } @article{ChromikPirlBeilharzetal.2021, author = {Chromik, Jonas and Pirl, Lukas and Beilharz, Jossekin Jakob and Arnrich, Bert and Polze, Andreas}, title = {Certainty in QRS detection with artificial neural networks}, series = {Biomedical signal processing and control}, volume = {68}, journal = {Biomedical signal processing and control}, publisher = {Elsevier}, address = {Oxford}, issn = {1746-8094}, doi = {10.1016/j.bspc.2021.102628}, pages = {12}, year = {2021}, abstract = {Detection of the QRS complex is a long-standing topic in the context of electrocardiography and many algorithms build upon the knowledge of the QRS positions. Although the first solutions to this problem were proposed in the 1970s and 1980s, there is still potential for improvements. Advancements in neural network technology made in recent years also lead to the emergence of enhanced QRS detectors based on artificial neural networks. In this work, we propose a method for assessing the certainty that is in each of the detected QRS complexes, i.e. how confident the QRS detector is that there is, in fact, a QRS complex in the position where it was detected. We further show how this metric can be utilised to distinguish correctly detected QRS complexes from false detections.}, language = {en} } @article{ChujfiLaRocheMeinel2017, author = {Chujfi-La-Roche, Salim and Meinel, Christoph}, title = {Matching cognitively sympathetic individual styles to develop collective intelligence in digital communities}, series = {AI \& society : the journal of human-centred systems and machine intelligence}, volume = {35}, journal = {AI \& society : the journal of human-centred systems and machine intelligence}, number = {1}, publisher = {Springer}, address = {New York}, issn = {0951-5666}, doi = {10.1007/s00146-017-0780-x}, pages = {5 -- 15}, year = {2017}, abstract = {Creation, collection and retention of knowledge in digital communities is an activity that currently requires being explicitly targeted as a secure method of keeping intellectual capital growing in the digital era. In particular, we consider it relevant to analyze and evaluate the empathetic cognitive personalities and behaviors that individuals now have with the change from face-to-face communication (F2F) to computer-mediated communication (CMC) online. This document proposes a cyber-humanistic approach to enhance the traditional SECI knowledge management model. A cognitive perception is added to its cyclical process following design thinking interaction, exemplary for improvement of the method in which knowledge is continuously created, converted and shared. In building a cognitive-centered model, we specifically focus on the effective identification and response to cognitive stimulation of individuals, as they are the intellectual generators and multiplicators of knowledge in the online environment. Our target is to identify how geographically distributed-digital-organizations should align the individual's cognitive abilities to promote iteration and improve interaction as a reliable stimulant of collective intelligence. The new model focuses on analyzing the four different stages of knowledge processing, where individuals with sympathetic cognitive personalities can significantly boost knowledge creation in a virtual social system. For organizations, this means that multidisciplinary individuals can maximize their extensive potential, by externalizing their knowledge in the correct stage of the knowledge creation process, and by collaborating with their appropriate sympathetically cognitive remote peers.}, language = {en} } @article{CopeBaukmannKlingeretal.2021, author = {Cope, Justin L. and Baukmann, Hannes A. and Klinger, J{\"o}rn E. and Ravarani, Charles N. J. and B{\"o}ttinger, Erwin and Konigorski, Stefan and Schmidt, Marco F.}, title = {Interaction-based feature selection algorithm outperforms polygenic risk score in predicting Parkinson's Disease status}, series = {Frontiers in genetics}, volume = {12}, journal = {Frontiers in genetics}, publisher = {Frontiers Media}, address = {Lausanne}, issn = {1664-8021}, doi = {10.3389/fgene.2021.744557}, pages = {9}, year = {2021}, abstract = {Polygenic risk scores (PRS) aggregating results from genome-wide association studies are the state of the art in the prediction of susceptibility to complex traits or diseases, yet their predictive performance is limited for various reasons, not least of which is their failure to incorporate the effects of gene-gene interactions. Novel machine learning algorithms that use large amounts of data promise to find gene-gene interactions in order to build models with better predictive performance than PRS. Here, we present a data preprocessing step by using data-mining of contextual information to reduce the number of features, enabling machine learning algorithms to identify gene-gene interactions. We applied our approach to the Parkinson's Progression Markers Initiative (PPMI) dataset, an observational clinical study of 471 genotyped subjects (368 cases and 152 controls). With an AUC of 0.85 (95\% CI = [0.72; 0.96]), the interaction-based prediction model outperforms the PRS (AUC of 0.58 (95\% CI = [0.42; 0.81])). Furthermore, feature importance analysis of the model provided insights into the mechanism of Parkinson's disease. For instance, the model revealed an interaction of previously described drug target candidate genes TMEM175 and GAPDHP25. These results demonstrate that interaction-based machine learning models can improve genetic prediction models and might provide an answer to the missing heritability problem.}, language = {en} } @article{CsehFleiner2020, author = {Cseh, Agnes and Fleiner, Tamas}, title = {The complexity of cake cutting with unequal shares}, series = {ACM transactions on algorithms : TALG}, volume = {16}, journal = {ACM transactions on algorithms : TALG}, number = {3}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {1549-6325}, doi = {10.1145/3380742}, pages = {21}, year = {2020}, abstract = {An unceasing problem of our prevailing society is the fair division of goods. The problem of proportional cake cutting focuses on dividing a heterogeneous and divisible resource, the cake, among n players who value pieces according to their own measure function. The goal is to assign each player a not necessarily connected part of the cake that the player evaluates at least as much as her proportional share.
In this article, we investigate the problem of proportional division with unequal shares, where each player is entitled to receive a predetermined portion of the cake. Our main contribution is threefold. First we present a protocol for integer demands, which delivers a proportional solution in fewer queries than all known protocols. By giving a matching lower bound, we then show that our protocol is asymptotically the fastest possible. Finally, we turn to irrational demands and solve the proportional cake cutting problem by reducing it to the same problem with integer demands only. All results remain valid in a highly general cake cutting model, which can be of independent interest.}, language = {en} } @article{CsehHeeger2020, author = {Cseh, Agnes and Heeger, Klaus}, title = {The stable marriage problem with ties and restricted edges}, series = {Discrete optimization}, volume = {36}, journal = {Discrete optimization}, publisher = {Elsevier}, address = {Amsterdam}, issn = {1572-5286}, doi = {10.1016/j.disopt.2020.100571}, pages = {11}, year = {2020}, abstract = {In the stable marriage problem, a set of men and a set of women are given, each of whom has a strictly ordered preference list over the acceptable agents in the opposite class. A matching is called stable if it is not blocked by any pair of agents, who mutually prefer each other to their respective partner. Ties in the preferences allow for three different definitions for a stable matching: weak, strong and super-stability. Besides this, acceptable pairs in the instance can be restricted in their ability of blocking a matching or being part of it, which again generates three categories of restrictions on acceptable pairs. Forced pairs must be in a stable matching, forbidden pairs must not appear in it, and lastly, free pairs cannot block any matching. Our computational complexity study targets the existence of a stable solution for each of the three stability definitions, in the presence of each of the three types of restricted pairs. We solve all cases that were still open. As a byproduct, we also derive that the maximum size weakly stable matching problem is hard even in very dense graphs, which may be of independent interest.}, language = {en} } @article{DattaSachsFreitasdaCruzetal.2021, author = {Datta, Suparno and Sachs, Jan Philipp and Freitas da Cruz, Harry and Martensen, Tom and Bode, Philipp and Morassi Sasso, Ariane and Glicksberg, Benjamin S. and B{\"o}ttinger, Erwin}, title = {FIBER}, series = {JAMIA open}, volume = {4}, journal = {JAMIA open}, number = {3}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {2574-2531}, doi = {10.1093/jamiaopen/ooab048}, pages = {10}, year = {2021}, abstract = {Objectives: The development of clinical predictive models hinges upon the availability of comprehensive clinical data. Tapping into such resources requires considerable effort from clinicians, data scientists, and engineers. Specifically, these efforts are focused on data extraction and preprocessing steps required prior to modeling, including complex database queries. A handful of software libraries exist that can reduce this complexity by building upon data standards. However, a gap remains concerning electronic health records (EHRs) stored in star schema clinical data warehouses, an approach often adopted in practice. In this article, we introduce the FlexIBle EHR Retrieval (FIBER) tool: a Python library built on top of a star schema (i2b2) clinical data warehouse that enables flexible generation of modeling-ready cohorts as data frames. Materials and Methods: FIBER was developed on top of a large-scale star schema EHR database which contains data from 8 million patients and over 120 million encounters. To illustrate FIBER's capabilities, we present its application by building a heart surgery patient cohort with subsequent prediction of acute kidney injury (AKI) with various machine learning models. Results: Using FIBER, we were able to build the heart surgery cohort (n = 12 061), identify the patients that developed AKI (n = 1005), and automatically extract relevant features (n = 774). Finally, we trained machine learning models that achieved area under the curve values of up to 0.77 for this exemplary use case. Conclusion: FIBER is an open-source Python library developed for extracting information from star schema clinical data warehouses and reduces time-to-modeling, helping to streamline the clinical modeling process.}, language = {en} } @phdthesis{Dawoud2013, author = {Dawoud, Wesam}, title = {Scalability and performance management of internet applications in the cloud}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-68187}, school = {Universit{\"a}t Potsdam}, year = {2013}, abstract = {Cloud computing is a model for enabling on-demand access to a shared pool of computing resources. With virtually limitless on-demand resources, a cloud environment enables the hosted Internet application to quickly cope when there is an increase in the workload. However, the overhead of provisioning resources exposes the Internet application to periods of under-provisioning and performance degradation. Moreover, the performance interference, due to the consolidation in the cloud environment, complicates the performance management of the Internet applications. In this dissertation, we propose two approaches to mitigate the impact of the resources provisioning overhead. The first approach employs control theory to scale resources vertically and cope fast with workload. This approach assumes that the provider has knowledge and control over the platform running in the virtual machines (VMs), which limits it to Platform as a Service (PaaS) and Software as a Service (SaaS) providers. The second approach is a customer-side one that deals with the horizontal scalability in an Infrastructure as a Service (IaaS) model. It addresses the trade-off problem between cost and performance with a multi-goal optimization solution. This approach finds the scale thresholds that achieve the highest performance with the lowest increase in the cost. Moreover, the second approach employs a proposed time series forecasting algorithm to scale the application proactively and avoid under-utilization periods. Furthermore, to mitigate the interference impact on the Internet application performance, we developed a system which finds and eliminates the VMs suffering from performance interference. The developed system is a light-weight solution which does not imply provider involvement. To evaluate our approaches and the designed algorithms at large-scale level, we developed a simulator called (ScaleSim). In the simulator, we implemented scalability components acting as the scalability components of Amazon EC2. The current scalability implementation in Amazon EC2 is used as a reference point for evaluating the improvement in the scalable application performance. ScaleSim is fed with realistic models of the RUBiS benchmark extracted from the real environment. The workload is generated from the access logs of the 1998 world cup website. The results show that optimizing the scalability thresholds and adopting proactive scalability can mitigate 88\% of the resources provisioning overhead impact with only a 9\% increase in the cost.}, language = {en} } @article{DeFreitasJohnsonGoldenetal.2021, author = {De Freitas, Jessica K. and Johnson, Kipp W. and Golden, Eddye and Nadkarni, Girish N. and Dudley, Joel T. and B{\"o}ttinger, Erwin and Glicksberg, Benjamin S. and Miotto, Riccardo}, title = {Phe2vec}, series = {Patterns}, volume = {2}, journal = {Patterns}, number = {9}, publisher = {Elsevier}, address = {Amsterdam}, issn = {2666-3899}, doi = {10.1016/j.patter.2021.100337}, pages = {9}, year = {2021}, abstract = {Robust phenotyping of patients from electronic health records (EHRs) at scale is a challenge in clinical informatics. Here, we introduce Phe2vec, an automated framework for disease phenotyping from EHRs based on unsupervised learning and assess its effectiveness against standard rule-based algorithms from Phenotype KnowledgeBase (PheKB). Phe2vec is based on pre-computing embeddings of medical concepts and patients' clinical history. Disease phenotypes are then derived from a seed concept and its neighbors in the embedding space. Patients are linked to a disease if their embedded representation is close to the disease phenotype. Comparing Phe2vec and PheKB cohorts head-to-head using chart review, Phe2vec performed on par or better in nine out of ten diseases. Differently from other approaches, it can scale to any condition and was validated against widely adopted expert-based standards. Phe2vec aims to optimize clinical informatics research by augmenting current frameworks to characterize patients by condition and derive reliable disease cohorts.}, language = {en} } @article{DeckerKoppLeymannetal.2009, author = {Decker, Gero and Kopp, Oliver and Leymann, Frank and Weske, Mathias}, title = {Interacting services : from specification to execution}, issn = {0169-023X}, doi = {10.1016/j.datak.2009.04.003}, year = {2009}, abstract = {Interacting services play a key role to realize business process integration among different business partners by means of electronic message exchange. In order to provide seamless integration of these services, the messages exchanged as well as their dependencies must be well-defined. Service choreographies are a means to describe the allowed conversations. This article presents a requirements framework for service choreography languages, along which existing choreography languages are assessed. The requirements framework provides the basis for introducing the language BPEL4Chor, which extends the industry standard WS-BPEL with choreography-specific concepts. A validation is provided and integration with executable service orchestrations is discussed.}, language = {en} } @article{DeckerMendling2009, author = {Decker, Gero and Mendling, Jan}, title = {Process instantiation}, issn = {0169-023X}, doi = {10.1016/j.datak.2009.02.013}, year = {2009}, abstract = {Although several process modeling languages allow one to specify processes with multiple start elements, the precise semantics of such models are often unclear, both from a pragmatic and from a theoretical point of view. This paper addresses the lack of research on this problem and introduces the CASU framework (from Creation, Activation, subscription, Unsubscription). The contribution of this framework is a systematic description of design alternatives for the specification of instantiation semantics of process modeling languages. We classify six prominent languages by the help of this framework. We validate the relevance of the CASU framework through empirical investigations involving a large set of process models from practice. Our work provides the basis for the design of new correctness criteria as well as for the formalization of Event-driven Process Chains (EPCs) and extension of the Business Process Modeling Notation (BPMN). It complements research such as the workflow patterns.}, language = {en} } @article{DeckerWeske2011, author = {Decker, Gero and Weske, Mathias}, title = {Interaction-centric modeling of process choreographies}, series = {Information systems}, volume = {36}, journal = {Information systems}, number = {2}, publisher = {Elsevier}, address = {Oxford}, issn = {0306-4379}, doi = {10.1016/j.is.2010.06.005}, pages = {292 -- 312}, year = {2011}, abstract = {With the rise of electronic integration between organizations, the need for a precise specification of interaction behavior increases. Information systems, replacing interaction previously carried out by humans via phone, faxes and emails, require a precise specification for handling all possible situations. Such interaction behavior is described in process choreographies. While many proposals for choreography languages have already been made, most of them fall into the category of interconnection models, where the observable behavior of the different partners is described and then related via message flow. As this article will show, this modeling approach fails to support fundamental design principles of choreographies and typically leads to modeling errors. This motivates an alternative modeling style, namely interaction modeling, for overcoming these limitations. While the main concepts are independent of a concrete modeling language, iBPMN is introduced as novel interaction modeling language. Formal execution semantics are provided and a comprehensive toolset implementing the approach is presented.}, language = {en} } @article{DellepianeVaidJaladankietal.2021, author = {Dellepiane, Sergio and Vaid, Akhil and Jaladanki, Suraj K. and Coca, Steven and Fayad, Zahi A. and Charney, Alexander W. and B{\"o}ttinger, Erwin and He, John Cijiang and Glicksberg, Benjamin S. and Chan, Lili and Nadkarni, Girish}, title = {Acute kidney injury in patients hospitalized with COVID-19 in New York City}, series = {Kidney medicine}, volume = {3}, journal = {Kidney medicine}, number = {5}, publisher = {Elsevier}, address = {Amsterdam}, issn = {2590-0595}, doi = {10.1016/j.xkme.2021.06.008}, pages = {877 -- 879}, year = {2021}, language = {en} } @article{DischerRichterDoellner2019, author = {Discher, S{\"o}ren and Richter, Rico and D{\"o}llner, J{\"u}rgen Roland Friedrich}, title = {Concepts and techniques for web-based visualization and processing of massive 3D point clouds with semantics}, series = {Graphical Models}, volume = {104}, journal = {Graphical Models}, publisher = {Elsevier}, address = {San Diego}, issn = {1524-0703}, doi = {10.1016/j.gmod.2019.101036}, pages = {11}, year = {2019}, abstract = {3D point cloud technology facilitates the automated and highly detailed acquisition of real-world environments such as assets, sites, and countries. We present a web-based system for the interactive exploration and inspection of arbitrary large 3D point clouds. Our approach is able to render 3D point clouds with billions of points using spatial data structures and level-of-detail representations. Point-based rendering techniques and post-processing effects are provided to enable task-specific and data-specific filtering, e.g., based on semantics. A set of interaction techniques allows users to collaboratively work with the data (e.g., measuring distances and annotating). Additional value is provided by the system's ability to display additional, context-providing geodata alongside 3D point clouds and to integrate processing and analysis operations. We have evaluated the presented techniques and in case studies and with different data sets from aerial, mobile, and terrestrial acquisition with up to 120 billion points to show their practicality and feasibility.}, language = {en} } @article{DischerRichterDoellner2016, author = {Discher, S{\"o}ren and Richter, Rico and D{\"o}llner, J{\"u}rgen Roland Friedrich}, title = {Interactive and View-Dependent See-Through Lenses for Massive 3D Point Clouds}, series = {Advances in 3D Geoinformation}, journal = {Advances in 3D Geoinformation}, publisher = {Springer}, address = {Cham}, isbn = {978-3-319-25691-7}, issn = {1863-2246}, doi = {10.1007/978-3-319-25691-7_3}, pages = {49 -- 62}, year = {2016}, abstract = {3D point clouds are a digital representation of our world and used in a variety of applications. They are captured with LiDAR or derived by image-matching approaches to get surface information of objects, e.g., indoor scenes, buildings, infrastructures, cities, and landscapes. We present novel interaction and visualization techniques for heterogeneous, time variant, and semantically rich 3D point clouds. Interactive and view-dependent see-through lenses are introduced as exploration tools to enhance recognition of objects, semantics, and temporal changes within 3D point cloud depictions. We also develop filtering and highlighting techniques that are used to dissolve occlusion to give context-specific insights. All techniques can be combined with an out-of-core real-time rendering system for massive 3D point clouds. We have evaluated the presented approach with 3D point clouds from different application domains. The results show the usability and how different visualization and exploration tasks can be improved for a variety of domain-specific applications.}, language = {en} } @article{DoerrKrejca2020, author = {Doerr, Benjamin and Krejca, Martin S.}, title = {Significance-based estimation-of-distribution algorithms}, series = {IEEE transactions on evolutionary computation}, volume = {24}, journal = {IEEE transactions on evolutionary computation}, number = {6}, publisher = {Institute of Electrical and Electronics Engineers}, address = {New York, NY}, issn = {1089-778X}, doi = {10.1109/TEVC.2019.2956633}, pages = {1025 -- 1034}, year = {2020}, abstract = {Estimation-of-distribution algorithms (EDAs) are randomized search heuristics that create a probabilistic model of the solution space, which is updated iteratively, based on the quality of the solutions sampled according to the model. As previous works show, this iteration-based perspective can lead to erratic updates of the model, in particular, to bit-frequencies approaching a random boundary value. In order to overcome this problem, we propose a new EDA based on the classic compact genetic algorithm (cGA) that takes into account a longer history of samples and updates its model only with respect to information which it classifies as statistically significant. We prove that this significance-based cGA (sig-cGA) optimizes the commonly regarded benchmark functions OneMax (OM), LeadingOnes, and BinVal all in quasilinear time, a result shown for no other EDA or evolutionary algorithm so far. For the recently proposed stable compact genetic algorithm-an EDA that tries to prevent erratic model updates by imposing a bias to the uniformly distributed model-we prove that it optimizes OM only in a time exponential in its hypothetical population size. Similarly, we show that the convex search algorithm cannot optimize OM in polynomial time.}, language = {en} } @article{DoerrKrejca2021, author = {Doerr, Benjamin and Krejca, Martin Stefan}, title = {A simplified run time analysis of the univariate marginal distribution algorithm on LeadingOnes}, series = {Theoretical computer science}, volume = {851}, journal = {Theoretical computer science}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0304-3975}, doi = {10.1016/j.tcs.2020.11.028}, pages = {121 -- 128}, year = {2021}, abstract = {With elementary means, we prove a stronger run time guarantee for the univariate marginal distribution algorithm (UMDA) optimizing the LEADINGONES benchmark function in the desirable regime with low genetic drift. If the population size is at least quasilinear, then, with high probability, the UMDA samples the optimum in a number of iterations that is linear in the problem size divided by the logarithm of the UMDA's selection rate. This improves over the previous guarantee, obtained by Dang and Lehre (2015) via the deep level-based population method, both in terms of the run time and by demonstrating further run time gains from small selection rates. Under similar assumptions, we prove a lower bound that matches our upper bound up to constant factors.}, language = {en} } @article{DoerrKoetzing2022, author = {Doerr, Benjamin and K{\"o}tzing, Timo}, title = {Lower bounds from fitness levels made easy}, series = {Algorithmica}, journal = {Algorithmica}, publisher = {Springer}, address = {New York}, issn = {0178-4617}, doi = {10.1007/s00453-022-00952-w}, pages = {29}, year = {2022}, abstract = {One of the first and easy to use techniques for proving run time bounds for evolutionary algorithms is the so-called method of fitness levels by Wegener. It uses a partition of the search space into a sequence of levels which are traversed by the algorithm in increasing order, possibly skipping levels. An easy, but often strong upper bound for the run time can then be derived by adding the reciprocals of the probabilities to leave the levels (or upper bounds for these). Unfortunately, a similarly effective method for proving lower bounds has not yet been established. The strongest such method, proposed by Sudholt (2013), requires a careful choice of the viscosity parameters gamma(i), j, 0 <= i < j <= n. In this paper we present two new variants of the method, one for upper and one for lower bounds. Besides the level leaving probabilities, they only rely on the probabilities that levels are visited at all. We show that these can be computed or estimated without greater difficulties and apply our method to reprove the following known results in an easy and natural way. (i) The precise run time of the (1+1) EA on LEADINGONES. (ii) A lower bound for the run time of the (1+1) EA on ONEMAX, tight apart from an O(n) term. (iii) A lower bound for the run time of the (1+1) EA on long k-paths (which differs slightly from the previous result due to a small error in the latter). We also prove a tighter lower bound for the run time of the (1+1) EA on jump functions by showing that, regardless of the jump size, only with probability O(2(-n)) the algorithm can avoid to jump over the valley of low fitness.}, language = {en} } @article{DoerrKoetzingLagodzinskietal.2020, author = {Doerr, Benjamin and K{\"o}tzing, Timo and Lagodzinski, Gregor J. A. and Lengler, Johannes}, title = {The impact of lexicographic parsimony pressure for ORDER/MAJORITY on the run time}, series = {Theoretical computer science : the journal of the EATCS}, volume = {816}, journal = {Theoretical computer science : the journal of the EATCS}, publisher = {Elsevier}, address = {Amsterdam [u.a.]}, issn = {0304-3975}, doi = {10.1016/j.tcs.2020.01.011}, pages = {144 -- 168}, year = {2020}, abstract = {While many optimization problems work with a fixed number of decision variables and thus a fixed-length representation of possible solutions, genetic programming (GP) works on variable-length representations. A naturally occurring problem is that of bloat, that is, the unnecessary growth of solution lengths, which may slow down the optimization process. So far, the mathematical runtime analysis could not deal well with bloat and required explicit assumptions limiting bloat. In this paper, we provide the first mathematical runtime analysis of a GP algorithm that does not require any assumptions on the bloat. Previous performance guarantees were only proven conditionally for runs in which no strong bloat occurs. Together with improved analyses for the case with bloat restrictions our results show that such assumptions on the bloat are not necessary and that the algorithm is efficient without explicit bloat control mechanism. More specifically, we analyzed the performance of the (1 + 1) GP on the two benchmark functions ORDER and MAJORITY. When using lexicographic parsimony pressure as bloat control, we show a tight runtime estimate of O(T-init + nlogn) iterations both for ORDER and MAJORITY. For the case without bloat control, the bounds O(T-init logT(i)(nit) + n(logn)(3)) and Omega(T-init + nlogn) (and Omega(T-init log T-init) for n = 1) hold for MAJORITY(1).}, language = {en} } @article{DoerrNeumannSutton2016, author = {Doerr, Benjamin and Neumann, Frank and Sutton, Andrew M.}, title = {Time Complexity Analysis of Evolutionary Algorithms on Random Satisfiable k-CNF Formulas}, series = {Algorithmica : an international journal in computer science}, volume = {78}, journal = {Algorithmica : an international journal in computer science}, publisher = {Springer}, address = {New York}, issn = {0178-4617}, doi = {10.1007/s00453-016-0190-3}, pages = {561 -- 586}, year = {2016}, abstract = {We contribute to the theoretical understanding of randomized search heuristics by investigating their optimization behavior on satisfiable random k-satisfiability instances both in the planted solution model and the uniform model conditional on satisfiability. Denoting the number of variables by n, our main technical result is that the simple () evolutionary algorithm with high probability finds a satisfying assignment in time when the clause-variable density is at least logarithmic. For low density instances, evolutionary algorithms seem to be less effective, and all we can show is a subexponential upper bound on the runtime for densities below . We complement these mathematical results with numerical experiments on a broader density spectrum. They indicate that, indeed, the () EA is less efficient on lower densities. Our experiments also suggest that the implicit constants hidden in our main runtime guarantee are low. Our main result extends and considerably improves the result obtained by Sutton and Neumann (Lect Notes Comput Sci 8672:942-951, 2014) in terms of runtime, minimum density, and clause length. These improvements are made possible by establishing a close fitness-distance correlation in certain parts of the search space. This approach might be of independent interest and could be useful for other average-case analyses of randomized search heuristics. While the notion of a fitness-distance correlation has been around for a long time, to the best of our knowledge, this is the first time that fitness-distance correlation is explicitly used to rigorously prove a performance statement for an evolutionary algorithm.}, language = {en} } @article{DraisbachChristenNaumann2019, author = {Draisbach, Uwe and Christen, Peter and Naumann, Felix}, title = {Transforming pairwise duplicates to entity clusters for high-quality duplicate detection}, series = {ACM Journal of Data and Information Quality}, volume = {12}, journal = {ACM Journal of Data and Information Quality}, number = {1}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {1936-1955}, doi = {10.1145/3352591}, pages = {1 -- 30}, year = {2019}, abstract = {Duplicate detection algorithms produce clusters of database records, each cluster representing a single real-world entity. As most of these algorithms use pairwise comparisons, the resulting (transitive) clusters can be inconsistent: Not all records within a cluster are sufficiently similar to be classified as duplicate. Thus, one of many subsequent clustering algorithms can further improve the result.
We explain in detail, compare, and evaluate many of these algorithms and introduce three new clustering algorithms in the specific context of duplicate detection. Two of our three new algorithms use the structure of the input graph to create consistent clusters. Our third algorithm, and many other clustering algorithms, focus on the edge weights, instead. For evaluation, in contrast to related work, we experiment on true real-world datasets, and in addition examine in great detail various pair-selection strategies used in practice. While no overall winner emerges, we are able to identify best approaches for different situations. In scenarios with larger clusters, our proposed algorithm, Extended Maximum Clique Clustering (EMCC), and Markov Clustering show the best results. EMCC especially outperforms Markov Clustering regarding the precision of the results and additionally has the advantage that it can also be used in scenarios where edge weights are not available.}, language = {en} } @book{DraisbachNaumannSzottetal.2012, author = {Draisbach, Uwe and Naumann, Felix and Szott, Sascha and Wonneberg, Oliver}, title = {Adaptive windows for duplicate detection}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-143-1}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-53007}, publisher = {Universit{\"a}t Potsdam}, pages = {41}, year = {2012}, abstract = {Duplicate detection is the task of identifying all groups of records within a data set that represent the same real-world entity, respectively. This task is difficult, because (i) representations might differ slightly, so some similarity measure must be defined to compare pairs of records and (ii) data sets might have a high volume making a pair-wise comparison of all records infeasible. To tackle the second problem, many algorithms have been suggested that partition the data set and compare all record pairs only within each partition. One well-known such approach is the Sorted Neighborhood Method (SNM), which sorts the data according to some key and then advances a window over the data comparing only records that appear within the same window. We propose several variations of SNM that have in common a varying window size and advancement. The general intuition of such adaptive windows is that there might be regions of high similarity suggesting a larger window size and regions of lower similarity suggesting a smaller window size. We propose and thoroughly evaluate several adaption strategies, some of which are provably better than the original SNM in terms of efficiency (same results with fewer comparisons).}, 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{DrimallaLandwehrHessetal.2019, author = {Drimalla, Hanna and Landwehr, Niels and Hess, Ursula and Dziobek, Isabel}, title = {From face to face}, series = {Cognition and Emotion}, volume = {33}, journal = {Cognition and Emotion}, number = {8}, publisher = {Routledge, Taylor \& Francis Group}, address = {Abingdon}, issn = {0269-9931}, doi = {10.1080/02699931.2019.1596068}, pages = {1672 -- 1686}, year = {2019}, abstract = {Despite advances in the conceptualisation of facial mimicry, its role in the processing of social information is a matter of debate. In the present study, we investigated the relationship between mimicry and cognitive and emotional empathy. To assess mimicry, facial electromyography was recorded for 70 participants while they completed the Multifaceted Empathy Test, which presents complex context-embedded emotional expressions. As predicted, inter-individual differences in emotional and cognitive empathy were associated with the level of facial mimicry. For positive emotions, the intensity of the mimicry response scaled with the level of state emotional empathy. Mimicry was stronger for the emotional empathy task compared to the cognitive empathy task. The specific empathy condition could be successfully detected from facial muscle activity at the level of single individuals using machine learning techniques. These results support the view that mimicry occurs depending on the social context as a tool to affiliate and it is involved in cognitive as well as emotional empathy.}, language = {en} } @book{DyckGiese2015, author = {Dyck, Johannes and Giese, Holger}, title = {Inductive invariant checking with partial negative application conditions}, number = {98}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-333-6}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-77748}, publisher = {Universit{\"a}t Potsdam}, pages = {43}, year = {2015}, abstract = {Graph transformation systems are a powerful formal model to capture model transformations or systems with infinite state space, among others. However, this expressive power comes at the cost of rather limited automated analysis capabilities. The general case of unbounded many initial graphs or infinite state spaces is only supported by approaches with rather limited scalability or expressiveness. In this report we improve an existing approach for the automated verification of inductive invariants for graph transformation systems. By employing partial negative application conditions to represent and check many alternative conditions in a more compact manner, we can check examples with rules and constraints of substantially higher complexity. We also substantially extend the expressive power by supporting more complex negative application conditions and provide higher accuracy by employing advanced implication checks. The improvements are evaluated and compared with another applicable tool by considering three case studies.}, language = {en} } @book{DyckGiese2017, author = {Dyck, Johannes and Giese, Holger}, title = {k-Inductive invariant checking for graph transformation systems}, number = {119}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-406-7}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-397044}, publisher = {Universit{\"a}t Potsdam}, pages = {45}, year = {2017}, abstract = {While offering significant expressive power, graph transformation systems often come with rather limited capabilities for automated analysis, particularly if systems with many possible initial graphs and large or infinite state spaces are concerned. One approach that tries to overcome these limitations is inductive invariant checking. However, the verification of inductive invariants often requires extensive knowledge about the system in question and faces the approach-inherent challenges of locality and lack of context. To address that, this report discusses k-inductive invariant checking for graph transformation systems as a generalization of inductive invariants. The additional context acquired by taking multiple (k) steps into account is the key difference to inductive invariant checking and is often enough to establish the desired invariants without requiring the iterative development of additional properties. To analyze possibly infinite systems in a finite fashion, we introduce a symbolic encoding for transformation traces using a restricted form of nested application conditions. As its central contribution, this report then presents a formal approach and algorithm to verify graph constraints as k-inductive invariants. We prove the approach's correctness and demonstrate its applicability by means of several examples evaluated with a prototypical implementation of our algorithm.}, language = {en} } @book{DyckGieseLambers2017, author = {Dyck, Johannes and Giese, Holger and Lambers, Leen}, title = {Automatic verification of behavior preservation at the transformation level for relational model transformation}, number = {112}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-391-6}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-100279}, publisher = {Universit{\"a}t Potsdam}, pages = {viii, 112}, year = {2017}, abstract = {The correctness of model transformations is a crucial element for model-driven engineering of high quality software. In particular, behavior preservation is the most important correctness property avoiding the introduction of semantic errors during the model-driven engineering process. Behavior preservation verification techniques either show that specific properties are preserved, or more generally and complex, they show some kind of behavioral equivalence or refinement between source and target model of the transformation. Both kinds of behavior preservation verification goals have been presented with automatic tool support for the instance level, i.e. for a given source and target model specified by the model transformation. However, up until now there is no automatic verification approach available at the transformation level, i.e. for all source and target models specified by the model transformation. In this report, we extend our results presented in [27] and outline a new sophisticated approach for the automatic verification of behavior preservation captured by bisimulation resp. simulation for model transformations specified by triple graph grammars and semantic definitions given by graph transformation rules. In particular, we show that the behavior preservation problem can be reduced to invariant checking for graph transformation and that the resulting checking problem can be addressed by our own invariant checker even for a complex example where a sequence chart is transformed into communicating automata. We further discuss today's limitations of invariant checking for graph transformation and motivate further lines of future work in this direction.}, language = {en} } @article{Doellner2020, author = {D{\"o}llner, J{\"u}rgen Roland Friedrich}, title = {Geospatial artificial intelligence}, series = {Journal of photogrammetry, remote sensing and geoinformation science : PFG : Photogrammetrie, Fernerkundung, Geoinformation}, volume = {88}, journal = {Journal of photogrammetry, remote sensing and geoinformation science : PFG : Photogrammetrie, Fernerkundung, Geoinformation}, number = {1}, publisher = {Springer International Publishing}, address = {Cham}, issn = {2512-2789}, doi = {10.1007/s41064-020-00102-3}, pages = {15 -- 24}, year = {2020}, abstract = {Artificial intelligence (AI) is changing fundamentally the way how IT solutions are implemented and operated across all application domains, including the geospatial domain. This contribution outlines AI-based techniques for 3D point clouds and geospatial digital twins as generic components of geospatial AI. First, we briefly reflect on the term "AI" and outline technology developments needed to apply AI to IT solutions, seen from a software engineering perspective. Next, we characterize 3D point clouds as key category of geodata and their role for creating the basis for geospatial digital twins; we explain the feasibility of machine learning (ML) and deep learning (DL) approaches for 3D point clouds. In particular, we argue that 3D point clouds can be seen as a corpus with similar properties as natural language corpora and formulate a "Naturalness Hypothesis" for 3D point clouds. In the main part, we introduce a workflow for interpreting 3D point clouds based on ML/DL approaches that derive domain-specific and application-specific semantics for 3D point clouds without having to create explicit spatial 3D models or explicit rule sets. Finally, examples are shown how ML/DL enables us to efficiently build and maintain base data for geospatial digital twins such as virtual 3D city models, indoor models, or building information models.}, language = {en} } @book{DoellnerKirschNienhaus2005, author = {D{\"o}llner, J{\"u}rgen Roland Friedrich and Kirsch, Florian and Nienhaus, Marc}, title = {Visualizing Design and Spatial Assembly of Interactive CSG}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-937786-56-2}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-33771}, publisher = {Universit{\"a}t Potsdam}, pages = {8}, year = {2005}, abstract = {For interactive construction of CSG models understanding the layout of a model is essential for its efficient manipulation. To understand position and orientation of aggregated components of a CSG model, we need to realize its visible and occluded parts as a whole. Hence, transparency and enhanced outlines are key techniques to assist comprehension. We present a novel real-time rendering technique for visualizing design and spatial assembly of CSG models. As enabling technology we combine an image-space CSG rendering algorithm with blueprint rendering. Blueprint rendering applies depth peeling for extracting layers of ordered depth from polygonal models and then composes them in sorted order facilitating a clear insight of the models. We develop a solution for implementing depth peeling for CSG models considering their depth complexity. Capturing surface colors of each layer and later combining the results allows for generating order-independent transparency as one major rendering technique for CSG models. We further define visually important edges for CSG models and integrate an image-space edgeenhancement technique for detecting them in each layer. In this way, we extract visually important edges that are directly and not directly visible to outline a model's layout. Combining edges with transparency rendering, finally, generates edge-enhanced depictions of image-based CSG models and allows us to realize their complex, spatial assembly.}, language = {en} } @article{EhrigGolasHabeletal.2012, author = {Ehrig, Hartmut and Golas, Ulrike and Habel, Annegret and Lambers, Leen and Orejas, Fernando}, title = {M-Adhesive Transformation Systems with Nested Application Conditions Part 2: Embedding, Critical Pairs and Local Confluence}, series = {Fundamenta informaticae}, volume = {118}, journal = {Fundamenta informaticae}, number = {1-2}, publisher = {IOS Press}, address = {Amsterdam}, issn = {0169-2968}, doi = {10.3233/FI-2012-705}, pages = {35 -- 63}, year = {2012}, abstract = {Graph transformation systems have been studied extensively and applied to several areas of computer science like formal language theory, the modeling of databases, concurrent or distributed systems, and visual, logical, and functional programming. In most kinds of applications it is necessary to have the possibility of restricting the applicability of rules. This is usually done by means of application conditions. In this paper, we continue the work of extending the fundamental theory of graph transformation to the case where rules may use arbitrary (nested) application conditions. More precisely, we generalize the Embedding theorem, and we study how local confluence can be checked in this context. In particular, we define a new notion of critical pair which allows us to formulate and prove a Local Confluence Theorem for the general case of rules with nested application conditions. All our results are presented, not for a specific class of graphs, but for any arbitrary M-adhesive category, which means that our results apply to most kinds of graphical structures. We demonstrate our theory on the modeling of an elevator control by a typed graph transformation system with positive and negative application conditions.}, language = {en} } @article{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. Part 1: parallelism, concurrency and amalgamation}, series = {Mathematical structures in computer science : a journal in the applications of categorical, algebraic and geometric methods in computer science}, volume = {24}, journal = {Mathematical structures in computer science : a journal in the applications of categorical, algebraic and geometric methods in computer science}, number = {4}, publisher = {Cambridge Univ. Press}, address = {New York}, issn = {0960-1295}, doi = {10.1017/S0960129512000357}, pages = {48}, 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{EidSabbagh2015, author = {Eid-Sabbagh, Rami-Habib}, title = {Business process architectures}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-79719}, school = {Universit{\"a}t Potsdam}, pages = {xvii, 256}, year = {2015}, abstract = {Business Process Management has become an integral part of modern organizations in the private and public sector for improving their operations. In the course of Business Process Management efforts, companies and organizations assemble large process model repositories with many hundreds and thousands of business process models bearing a large amount of information. With the advent of large business process model collections, new challenges arise as structuring and managing a large amount of process models, their maintenance, and their quality assurance. This is covered by business process architectures that have been introduced for organizing and structuring business process model collections. A variety of business process architecture approaches have been proposed that align business processes along aspects of interest, e. g., goals, functions, or objects. They provide a high level categorization of single processes ignoring their interdependencies, thus hiding valuable information. The production of goods or the delivery of services are often realized by a complex system of interdependent business processes. Hence, taking a holistic view at business processes interdependencies becomes a major necessity to organize, analyze, and assess the impact of their re-/design. Visualizing business processes interdependencies reveals hidden and implicit information from a process model collection. In this thesis, we present a novel Business Process Architecture approach for representing and analyzing business process interdependencies on an abstract level. We propose a formal definition of our Business Process Architecture approach, design correctness criteria, and develop analysis techniques for assessing their quality. We describe a methodology for applying our Business Process Architecture approach top-down and bottom-up. This includes techniques for Business Process Architecture extraction from, and decomposition to process models while considering consistency issues between business process architecture and process model level. Using our extraction algorithm, we present a novel technique to identify and visualize data interdependencies in Business Process Data Architectures. Our Business Process Architecture approach provides business process experts,managers, and other users of a process model collection with an overview that allows reasoning about a large set of process models, understanding, and analyzing their interdependencies in a facilitated way. In this regard we evaluated our Business Process Architecture approach in an experiment and provide implementations of selected techniques.}, language = {en} } @book{EidSabbaghHeweltWeske2013, author = {Eid-Sabbagh, Rami-Habib and Hewelt, Marcin and Weske, Mathias}, title = {Business process architectures with multiplicities : transformation and correctness}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-257-5}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-66780}, publisher = {Universit{\"a}t Potsdam}, pages = {18}, year = {2013}, abstract = {Business processes are instrumental to manage work in organisations. To study the interdependencies between business processes, Business Process Architectures have been introduced. These express trigger and message ow relations between business processes. When we investigate real world Business Process Architectures, we find complex interdependencies, involving multiple process instances. These aspects have not been studied in detail so far, especially concerning correctness properties. In this paper, we propose a modular transformation of BPAs to open nets for the analysis of behavior involving multiple business processes with multiplicities. For this purpose we introduce intermediary nets to portray semantics of multiplicity specifications. We evaluate our approach on a use case from the public sector.}, language = {en} } @inproceedings{FanMasuharaAotanietal.2010, author = {Fan, Yang and Masuhara, Hidehiko and Aotani, Tomoyuki and Nielson, Flemming and Nielson, Hanne Riis}, title = {AspectKE*: Security aspects with program analysis for distributed systems}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-41369}, year = {2010}, abstract = {Enforcing security policies to distributed systems is difficult, in particular, when a system contains untrusted components. We designed AspectKE*, a distributed AOP language based on a tuple space, to tackle this issue. In AspectKE*, aspects can enforce access control policies that depend on future behavior of running processes. One of the key language features is the predicates and functions that extract results of static program analysis, which are useful for defining security aspects that have to know about future behavior of a program. AspectKE* also provides a novel variable binding mechanism for pointcuts, so that pointcuts can uniformly specify join points based on both static and dynamic information about the program. Our implementation strategy performs fundamental static analysis at load-time, so as to retain runtime overheads minimal. We implemented a compiler for AspectKE*, and demonstrate usefulness of AspectKE* through a security aspect for a distributed chat system.}, language = {en} } @book{FeinbubeRichterGerstenbergetal.2016, author = {Feinbube, Lena and Richter, Daniel and Gerstenberg, Sebastian and Siegler, Patrick and Haller, Angelo and Polze, Andreas}, title = {Software-Fehlerinjektion}, number = {109}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-386-2}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-97435}, publisher = {Universit{\"a}t Potsdam}, pages = {viii, 47}, year = {2016}, abstract = {Fehlerinjektion ist ein essentielles Werkzeug, um die Fehlertoleranz komplexer Softwaresysteme experimentell zu evaluieren. Wir berichten {\"u}ber das Seminar zum Thema Software-Fehlerinjektion, das am Fachgebiet f{\"u}r Betriebssysteme und Middleware am Hasso-Plattner-Institut der Universit{\"a}t Potsdam im Sommersemester 2015 stattfand. In dem Seminar ging es darum, verschiedene Fehlerinjektionsans{\"a}tze und -werkzeuge anzuwenden und hinsichtlich ihrer Anwendbarkeit in verschiedenen Szenarien zu bewerten. In diesem Bericht werden die studierten Ans{\"a}tze vorgestellt und verglichen.}, language = {de} } @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{FelgentreffHirschfeldMillsteinetal.2015, author = {Felgentreff, Tim and Hirschfeld, Robert and Millstein, Todd and Borning, Alan}, title = {Babelsberg/RML}, number = {103}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-348-0}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-83826}, publisher = {Universit{\"a}t Potsdam}, pages = {68}, year = {2015}, abstract = {New programming language designs are often evaluated on concrete implementations. However, in order to draw conclusions about the language design from the evaluation of concrete programming languages, these implementations need to be verified against the formalism of the design. To that end, we also have to ensure that the design actually meets its stated goals. A useful tool for the latter has been to create an executable semantics from a formalism that can execute a test suite of examples. However, this mechanism so far did not allow to verify an implementation against the design. Babelsberg is a new design for a family of object-constraint languages. Recently, we have developed a formal semantics to clarify some issues in the design of those languages. Supplementing this work, we report here on how this formalism is turned into an executable operational semantics using the RML system. Furthermore, we show how we extended the executable semantics to create a framework that can generate test suites for the concrete Babelsberg implementations that provide traceability from the design to the language. Finally, we discuss how these test suites helped us find and correct mistakes in the Babelsberg implementation for JavaScript.}, language = {en} } @article{FelgentreffPerscheidHirschfeld2017, author = {Felgentreff, Tim and Perscheid, Michael and Hirschfeld, Robert}, title = {Implementing record and refinement for debugging timing-dependent communication}, series = {Science of computer programming}, volume = {134}, journal = {Science of computer programming}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0167-6423}, doi = {10.1016/j.scico.2015.11.006}, pages = {4 -- 18}, year = {2017}, abstract = {Distributed applications are hard to debug because timing-dependent network communication is a source of non-deterministic behavior. Current approaches to debug non deterministic failures include post-mortem debugging as well as record and replay. However, the first impairs system performance to gather data, whereas the latter requires developers to understand the timing-dependent communication at a lower level of abstraction than they develop at. Furthermore, both approaches require intrusive core library modifications to gather data from live systems. In this paper, we present the Peek-At-Talk debugger for investigating non-deterministic failures with low overhead in a systematic, top-down method, with a particular focus on tool-building issues in the following areas: First, we show how our debugging framework Path Tools guides developers from failures to their root causes and gathers run-time data with low overhead. Second, we present Peek-At-Talk, an extension to our Path Tools framework to record non-deterministic communication and refine behavioral data that connects source code with network events. Finally, we scope changes to the core library to record network communication without impacting other network applications.}, language = {en} } @misc{Fink2009, author = {Fink, Hans-Peter}, title = {Von Biopolymeren und Biokunststoffen : Antrittsvorlesung 2009-06-04}, publisher = {Univ.-Bibl.}, address = {Potsdam}, year = {2009}, abstract = {Prof. Fink wird zum einen auf die industriell schon lange genutzten nat{\"u}rlichen Polymere wie Cellulose, St{\"a}rke und Lignin eingehen, zum anderen auf neue Entwicklungen bei biobasierten Kunststoffen. Von besonderer Bedeutung ist dabei die Aufkl{\"a}rung von Zusammenh{\"a}ngen zwischen Prozessparametern, Strukturen und Eigenschaften.}, language = {de} } @unpublished{FishLambers2013, author = {Fish, Andrew and Lambers, Leen}, title = {Special issue on graph transformation and visual modeling techniques - guest editors' introduction}, series = {Journal of visual languages and computing}, volume = {24}, journal = {Journal of visual languages and computing}, number = {6}, publisher = {Elsevier}, address = {London}, issn = {1045-926X}, doi = {10.1016/j.jvlc.2013.08.004}, pages = {419 -- 420}, year = {2013}, language = {en} }