@article{BollMeinhardtGronewoldetal.2010, author = {Boll, Susanne and Meinhardt, Rolf and Gronewold, Sabine and Krekeler, Larissa}, title = {Informatik f{\"u}r Migratinnen und Migranten Einf{\"u}hrung eines neuen Studienprogramms an der Universit{\"a}t Oldenburg}, series = {Commentarii informaticae didacticae : (CID)}, journal = {Commentarii informaticae didacticae : (CID)}, number = {4}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, issn = {1868-0844}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64370}, pages = {79 -- 86}, year = {2010}, abstract = {F{\"u}r die Integration und den Bedarf der hochqualifizierten Migranten auf dem Arbeitsmarkt in Deutschland gibt es viele {\"U}berlegungen, aber noch keine ausreichenden L{\"o}sungen. Dieser Artikel beschreibt eine praktische L{\"o}sung {\"u}ber die Umsetzung des Konzepts f{\"u}r die Qualifizierung der akademischen Migranten am Beispiel eines Studienprogramms in Informatik an der Universit{\"a}t Oldenburg.}, language = {de} } @article{LaroqueSchulteUrban2010, author = {Laroque, Christoph and Schulte, Jonas and Urban, Diana}, title = {KoProV}, series = {Commentarii informaticae didacticae : (CID)}, journal = {Commentarii informaticae didacticae : (CID)}, number = {4}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, issn = {1868-0844}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64445}, pages = {99 -- 105}, year = {2010}, abstract = {In der universit{\"a}ren Lehre {\"a}ndert sich der Leitgedanke von einer qualifikationsorientierten hin zu einer kompetenzorientierten Ausbildung. Der Begriff Kompetenz l{\"a}sst sich dabei grob in die fachlichen und die {\"u}berfachlichen Kompetenzen unterteilen. Insbesondere die Vermittlung von Schl{\"u}sselqualifikationen hat in der Lehre von naturwissenschaftlichen Fachrichtungen nur unzureichend Einzug erhalten. W{\"a}hrend der klassische Vorlesungsbetrieb auf den Erwerb von Fachkompetenz zielt, stoßen ausschließlich projektorientierte Veranstaltungen schnell an ihre Grenzen hinsichtlich der Teilnehmergr{\"o}ße oder Umfang der Lerninhalte. Um auf geeignete Art und Weise den Erwerb von {\"u}berfachlichen Kompetenzen zu erm{\"o}glichen, bedarf es neuer didaktischer Konzepte, die eine engere Verkn{\"u}pfung von klassischen Vorlesungen und dem projektorientierten Lernen vorsehen. In diesem Sinne versucht der skizzierte Ansatz der koordinierten Projektvorlesung(KoProV) Wissensvermittlung im Rahmen von Vorlesungseinheiten mit koordinierten Praxisphasen in Teilgruppen zu verbinden. F{\"u}r eine erfolgreiche Durchf{\"u}hrung und Erarbeitung des begleitenden Praxisprojektes durch mehrere Teilgruppen sind organisatorische und technische Randbedingungen zu beachten.}, language = {de} } @article{Kiss2010, author = {Kiss, G{\´a}bor}, title = {Analyse der Studienleistungen von Studierenden an der Universit{\"a}t {\´O}buda und deren Implikationen f{\"u}r die Informatikausbildung}, series = {Commentarii informaticae didacticae : (CID)}, journal = {Commentarii informaticae didacticae : (CID)}, number = {4}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, issn = {1868-0844}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64364}, pages = {71 -- 77}, year = {2010}, abstract = {In der letzten Jahren ist die Zahl der erfolgreichen Pr{\"u}fungen von Studierenden im Informatikkurs des ersten Studienjahres f{\"u}r verschiedene Studieng{\"a}nge an der Universit{\"a}t {\´O}buda stark gesunken. Dies betrifft Pr{\"u}fungen in den Teilgebieten Rechnerarchitektur, Betrieb von Peripherieger{\"a}ten, Bin{\"a}re Codierung und logische Operationen, Computerviren, Computernetze und das Internet, Steganographie und Kryptographie, Betriebsysteme. Mehr als der H{\"a}lfte der Studenten konnte die Pr{\"u}fungen der ersten Semester nicht erfolgreich absolvieren. Die hier vorgelegte Analyse der Studienleistungen zielt darauf ab, Gr{\"u}nde f{\"u}r diese Entwicklung zu identifizieren, die Zahl der Abbrecher zu reduzieren und die Leistungen der Studenten zu verbessern. Die Analyse zeigt, dass die Studenten die erforderlichen Lehrmaterialen erst ein bis zwei Tage vor oder sogar erst am Tag der Klausuren vom Server downloaden, so dass sie nicht mehr hinreichend Zeit zum Lernen haben. Diese Tendenz zeigt sich bei allen Teilgebieten des Studiengangs. Ein Mangel an kontinuierlicher Mitarbeit scheint einer der Gr{\"u}nde f{\"u}r ein fr{\"u}hes Scheitern zu sein. Ferner zeigt sich die Notwendigkeit, dass bei den Lehrangeboten in Informatik auf eine kontinuierliche Kommunikation mit den Studierenden und R{\"u}ckmeldung zu aktuellen Unterrichtsinhalten zu achten ist. Dies kann durch motivierende Maßnahmen zur Teilnahme an den {\"U}bungen oder durch kleine w{\"o}chentliche schriftliche Tests geschehen.}, language = {de} } @phdthesis{Seibel2012, author = {Seibel, Andreas}, title = {Traceability and model management with executable and dynamic hierarchical megamodels}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64222}, school = {Universit{\"a}t Potsdam}, year = {2012}, abstract = {Nowadays, model-driven engineering (MDE) promises to ease software development by decreasing the inherent complexity of classical software development. In order to deliver on this promise, MDE increases the level of abstraction and automation, through a consideration of domain-specific models (DSMs) and model operations (e.g. model transformations or code generations). DSMs conform to domain-specific modeling languages (DSMLs), which increase the level of abstraction, and model operations are first-class entities of software development because they increase the level of automation. Nevertheless, MDE has to deal with at least two new dimensions of complexity, which are basically caused by the increased linguistic and technological heterogeneity. The first dimension of complexity is setting up an MDE environment, an activity comprised of the implementation or selection of DSMLs and model operations. Setting up an MDE environment is both time-consuming and error-prone because of the implementation or adaptation of model operations. The second dimension of complexity is concerned with applying MDE for actual software development. Applying MDE is challenging because a collection of DSMs, which conform to potentially heterogeneous DSMLs, are required to completely specify a complex software system. A single DSML can only be used to describe a specific aspect of a software system at a certain level of abstraction and from a certain perspective. Additionally, DSMs are usually not independent but instead have inherent interdependencies, reflecting (partial) similar aspects of a software system at different levels of abstraction or from different perspectives. A subset of these dependencies are applications of various model operations, which are necessary to keep the degree of automation high. This becomes even worse when addressing the first dimension of complexity. Due to continuous changes, all kinds of dependencies, including the applications of model operations, must also be managed continuously. This comprises maintaining the existence of these dependencies and the appropriate (re-)application of model operations. The contribution of this thesis is an approach that combines traceability and model management to address the aforementioned challenges of configuring and applying MDE for software development. The approach is considered as a traceability approach because it supports capturing and automatically maintaining dependencies between DSMs. The approach is considered as a model management approach because it supports managing the automated (re-)application of heterogeneous model operations. In addition, the approach is considered as a comprehensive model management. Since the decomposition of model operations is encouraged to alleviate the first dimension of complexity, the subsequent composition of model operations is required to counteract their fragmentation. A significant portion of this thesis concerns itself with providing a method for the specification of decoupled yet still highly cohesive complex compositions of heterogeneous model operations. The approach supports two different kinds of compositions - data-flow compositions and context compositions. Data-flow composition is used to define a network of heterogeneous model operations coupled by sharing input and output DSMs alone. Context composition is related to a concept used in declarative model transformation approaches to compose individual model transformation rules (units) at any level of detail. In this thesis, context composition provides the ability to use a collection of dependencies as context for the composition of other dependencies, including model operations. In addition, the actual implementation of model operations, which are going to be composed, do not need to implement any composition concerns. The approach is realized by means of a formalism called an executable and dynamic hierarchical megamodel, based on the original idea of megamodels. This formalism supports specifying compositions of dependencies (traceability and model operations). On top of this formalism, traceability is realized by means of a localization concept, and model management by means of an execution concept.}, language = {en} } @book{SchwalbKruegerPlattner2013, author = {Schwalb, David and Kr{\"u}ger, Jens and Plattner, Hasso}, title = {Cache conscious column organization in in-memory column stores}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-228-5}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-63890}, publisher = {Universit{\"a}t Potsdam}, pages = {v, 84}, year = {2013}, abstract = {Cost models are an essential part of database systems, as they are the basis of query performance optimization. Based on predictions made by cost models, the fastest query execution plan can be chosen and executed or algorithms can be tuned and optimised. In-memory databases shifts the focus from disk to main memory accesses and CPU costs, compared to disk based systems where input and output costs dominate the overall costs and other processing costs are often neglected. However, modelling memory accesses is fundamentally different and common models do not apply anymore. This work presents a detailed parameter evaluation for the plan operators scan with equality selection, scan with range selection, positional lookup and insert in in-memory column stores. Based on this evaluation, a cost model based on cache misses for estimating the runtime of the considered plan operators using different data structures is developed. Considered are uncompressed columns, bit compressed and dictionary encoded columns with sorted and unsorted dictionaries. Furthermore, tree indices on the columns and dictionaries are discussed. Finally, partitioned columns consisting of one partition with a sorted and one with an unsorted dictionary are investigated. New values are inserted in the unsorted dictionary partition and moved periodically by a merge process to the sorted partition. An efficient attribute merge algorithm is described, supporting the update performance required to run enterprise applications on read-optimised databases. Further, a memory traffic based cost model for the merge process is provided.}, language = {en} } @book{VogelGiese2013, author = {Vogel, Thomas and Giese, Holger}, title = {Model-driven engineering of adaptation engines for self-adaptive software : executable runtime megamodels}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-227-8}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-63825}, publisher = {Universit{\"a}t Potsdam}, pages = {vi, 59}, year = {2013}, abstract = {The development of self-adaptive software requires the engineering of an adaptation engine that controls and adapts the underlying adaptable software by means of feedback loops. The adaptation engine often describes the adaptation by using runtime models representing relevant aspects of the adaptable software and particular activities such as analysis and planning that operate on these runtime models. To systematically address the interplay between runtime models and adaptation activities in adaptation engines, runtime megamodels have been proposed for self-adaptive software. A runtime megamodel is a specific runtime model whose elements are runtime models and adaptation activities. Thus, a megamodel captures the interplay between multiple models and between models and activities as well as the activation of the activities. In this article, we go one step further and present a modeling language for ExecUtable RuntimE MegAmodels (EUREMA) that considerably eases the development of adaptation engines by following a model-driven engineering approach. We provide a domain-specific modeling language and a runtime interpreter for adaptation engines, in particular for feedback loops. Megamodels are kept explicit and alive at runtime and by interpreting them, they are directly executed to run feedback loops. Additionally, they can be dynamically adjusted to adapt feedback loops. Thus, EUREMA supports development by making feedback loops, their runtime models, and adaptation activities explicit at a higher level of abstraction. Moreover, it enables complex solutions where multiple feedback loops interact or even operate on top of each other. Finally, it leverages the co-existence of self-adaptation and off-line adaptation for evolution.}, language = {en} } @article{HeinischRomeike2013, author = {Heinisch, Isabelle and Romeike, Ralf}, title = {Outcome-orientierte Neuausrichtung in der Hochschullehre Informatik}, series = {Commentarii informaticae didacticae : (CID)}, journal = {Commentarii informaticae didacticae : (CID)}, number = {5}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, issn = {1868-0844}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64831}, pages = {9 -- 20}, year = {2013}, abstract = {Die Orientierung am Outcome eines Lernprozesses stellt einen wichtigen Pfeiler einer kompetenzorientierten Informatiklehre dar. Im Beitrag werden Konzeption und Erfahrungen eines Projekts zur outcome-orientierten Neuausrichtung der Informatiklehre unter Ber{\"u}cksichtigung der Theorie des Constructive Alignment beschrieben. Nach der theoretischen Fundierung der Kompetenzproblematik wird anhand eines Formulierungsmodells ein Prozess zur Erarbeitung beobachtbarer Lernergebnisse dargestellt. Die Diskussion der Projektziele und Erfahrungen in der Umsetzung und Evaluierung unterstreichen die Chancen und Herausforderungen f{\"u}r eine Steigerung der Studienqualit{\"a}t.}, language = {de} } @article{HolzBergerSchroeder2013, author = {Holz, Jan and Berger, Nadine and Schroeder, Ulrike}, title = {Anwendungsorientierte Gestaltung eines Informatik-Vorkurses als Studienmotivator}, series = {Commentarii informaticae didacticae : (CID)}, journal = {Commentarii informaticae didacticae : (CID)}, number = {5}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, issn = {1868-0844}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64871}, pages = {56 -- 66}, year = {2013}, abstract = {Zur Unterst{\"u}tzung von Studierenden in der Studieneingangsphase wurde an der RWTH Aachen ein neuartiger und motivierender Einstieg in den Vorkurs Informatik entwickelt und zum Wintersemester 2011/12 erprobt. Dabei wurde die grafische Programmierung mittels App Inventor eingef{\"u}hrt, die zur Umsetzung anwendungsbezogener Projekte genutzt wurde. In diesem Beitrag werden die Motivation f{\"u}r die Neugestaltung, das Konzept und die Evaluation des Testlaufs beschrieben. Diese dienen als Grundlage f{\"u}r eine vollst{\"a}ndige Neukonzeption des Vorkurses f{\"u}r das Wintersemester 2012/2013.}, language = {de} } @book{BeyhlBlouinGieseetal.2016, author = {Beyhl, Thomas and Blouin, Dominique and Giese, Holger and Lambers, Leen}, title = {On the operationalization of graph queries with generalized discrimination networks}, number = {106}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-372-5}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-96279}, publisher = {Universit{\"a}t Potsdam}, pages = {33}, year = {2016}, abstract = {Graph queries have lately gained increased interest due to application areas such as social networks, biological networks, or model queries. For the relational database case the relational algebra and generalized discrimination networks have been studied to find appropriate decompositions into subqueries and ordering of these subqueries for query evaluation or incremental updates of query results. For graph database queries however there is no formal underpinning yet that allows us to find such suitable operationalizations. Consequently, we suggest a simple operational concept for the decomposition of arbitrary complex queries into simpler subqueries and the ordering of these subqueries in form of generalized discrimination networks for graph queries inspired by the relational case. The approach employs graph transformation rules for the nodes of the network and thus we can employ the underlying theory. We further show that the proposed generalized discrimination networks have the same expressive power as nested graph conditions.}, language = {en} } @unpublished{GrapentinHeidlerKorschetal.2014, author = {Grapentin, Andreas and Heidler, Kirstin and Korsch, Dimitri and Kumar Sah, Rakesh and Kunzmann, Nicco and Henning, Johannes and Mattis, Toni and Rein, Patrick and Seckler, Eric and Groneberg, Bj{\"o}rn and Zimmermann, Florian}, title = {Embedded operating system projects}, number = {90}, editor = {Hentschel, Uwe and Richter, Daniel and Polze, Andreas}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-296-4}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-69154}, pages = {xi, 87}, year = {2014}, abstract = {In today's life, embedded systems are ubiquitous. But they differ from traditional desktop systems in many aspects - these include predictable timing behavior (real-time), the management of scarce resources (memory, network), reliable communication protocols, energy management, special purpose user-interfaces (headless operation), system configuration, programming languages (to support software/hardware co-design), and modeling techniques. Within this technical report, authors present results from the lecture "Operating Systems for Embedded Computing" that has been offered by the "Operating Systems and Middleware" group at HPI in Winter term 2013/14. Focus of the lecture and accompanying projects was on principles of real-time computing. Students had the chance to gather practical experience with a number of different OSes and applications and present experiences with near-hardware programming. Projects address the entire spectrum, from bare-metal programming to harnessing a real-time OS to exercising the full software/hardware co-design cycle. Three outstanding projects are at the heart of this technical report. Project 1 focuses on the development of a bare-metal operating system for LEGO Mindstorms EV3. While still a toy, it comes with a powerful ARM processor, 64 MB of main memory, standard interfaces, such as Bluetooth and network protocol stacks. EV3 runs a version of 1 1 Introduction Linux. Sources are available from Lego's web site. However, many devices and their driver software are proprietary and not well documented. Developing a new, bare-metal OS for the EV3 requires an understanding of the EV3 boot process. Since no standard input/output devices are available, initial debugging steps are tedious. After managing these initial steps, the project was able to adapt device drivers for a few Lego devices to an extent that a demonstrator (the Segway application) could be successfully run on the new OS. Project 2 looks at the EV3 from a different angle. The EV3 is running a pretty decent version of Linux- in principle, the RT_PREEMPT patch can turn any Linux system into a real-time OS by modifying the behavior of a number of synchronization constructs at the heart of the OS. Priority inversion is a problem that is solved by protocols such as priority inheritance or priority ceiling. Real-time OSes implement at least one of the protocols. The central idea of the project was the comparison of non-real-time and real-time variants of Linux on the EV3 hardware. A task set that showed effects of priority inversion on standard EV3 Linux would operate flawlessly on the Linux version with the RT_PREEMPT-patch applied. If only patching Lego's version of Linux was that easy... Project 3 takes the notion of real-time computing more seriously. The application scenario was centered around our Carrera Digital 132 racetrack. Obtaining position information from the track, controlling individual cars, detecting and modifying the Carrera Digital protocol required design and implementation of custom controller hardware. What to implement in hardware, firmware, and what to implement in application software - this was the central question addressed by the project.}, language = {en} } @phdthesis{Polyvyanyy2012, author = {Polyvyanyy, Artem}, title = {Structuring process models}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-59024}, school = {Universit{\"a}t Potsdam}, year = {2012}, abstract = {One can fairly adopt the ideas of Donald E. Knuth to conclude that process modeling is both a science and an art. Process modeling does have an aesthetic sense. Similar to composing an opera or writing a novel, process modeling is carried out by humans who undergo creative practices when engineering a process model. Therefore, the very same process can be modeled in a myriad number of ways. Once modeled, processes can be analyzed by employing scientific methods. Usually, process models are formalized as directed graphs, with nodes representing tasks and decisions, and directed arcs describing temporal constraints between the nodes. Common process definition languages, such as Business Process Model and Notation (BPMN) and Event-driven Process Chain (EPC) allow process analysts to define models with arbitrary complex topologies. The absence of structural constraints supports creativity and productivity, as there is no need to force ideas into a limited amount of available structural patterns. Nevertheless, it is often preferable that models follow certain structural rules. A well-known structural property of process models is (well-)structuredness. A process model is (well-)structured if and only if every node with multiple outgoing arcs (a split) has a corresponding node with multiple incoming arcs (a join), and vice versa, such that the set of nodes between the split and the join induces a single-entry-single-exit (SESE) region; otherwise the process model is unstructured. The motivations for well-structured process models are manifold: (i) Well-structured process models are easier to layout for visual representation as their formalizations are planar graphs. (ii) Well-structured process models are easier to comprehend by humans. (iii) Well-structured process models tend to have fewer errors than unstructured ones and it is less probable to introduce new errors when modifying a well-structured process model. (iv) Well-structured process models are better suited for analysis with many existing formal techniques applicable only for well-structured process models. (v) Well-structured process models are better suited for efficient execution and optimization, e.g., when discovering independent regions of a process model that can be executed concurrently. Consequently, there are process modeling languages that encourage well-structured modeling, e.g., Business Process Execution Language (BPEL) and ADEPT. However, the well-structured process modeling implies some limitations: (i) There exist processes that cannot be formalized as well-structured process models. (ii) There exist processes that when formalized as well-structured process models require a considerable duplication of modeling constructs. Rather than expecting well-structured modeling from start, we advocate for the absence of structural constraints when modeling. Afterwards, automated methods can suggest, upon request and whenever possible, alternative formalizations that are "better" structured, preferably well-structured. In this thesis, we study the problem of automatically transforming process models into equivalent well-structured models. The developed transformations are performed under a strong notion of behavioral equivalence which preserves concurrency. The findings are implemented in a tool, which is publicly available.}, language = {en} } @phdthesis{Meier2017, author = {Meier, Sebastian}, title = {Personal Big Data}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-406696}, school = {Universit{\"a}t Potsdam}, pages = {xxiv, 133}, year = {2017}, abstract = {Many users of cloud-based services are concerned about questions of data privacy. At the same time, they want to benefit from smart data-driven services, which require insight into a person's individual behaviour. The modus operandi of user modelling is that data is sent to a remote server where the model is constructed and merged with other users' data. This thesis proposes selective cloud computing, an alternative approach, in which the user model is constructed on the client-side and only an abstracted generalised version of the model is shared with the remote services. In order to demonstrate the applicability of this approach, the thesis builds an exemplary client-side user modelling technique. As this thesis is carried out in the area of Geoinformatics and spatio-temporal data is particularly sensitive, the application domain for this experiment is the analysis and prediction of a user's spatio-temporal behaviour. The user modelling technique is grounded in an innovative conceptual model, which builds upon spatial network theory combined with time-geography. The spatio-temporal constraints of time-geography are applied to the network structure in order to create individual spatio-temporal action spaces. This concept is translated into a novel algorithmic user modelling approach which is solely driven by the user's own spatio-temporal trajectory data that is generated by the user's smartphone. While modern smartphones offer a rich variety of sensory data, this thesis only makes use of spatio-temporal trajectory data, enriched by activity classification, as the input and foundation for the algorithmic model. The algorithmic model consists of three basal components: locations (vertices), trips (edges), and clusters (neighbourhoods). After preprocessing the incoming trajectory data in order to identify locations, user feedback is used to train an artificial neural network to learn temporal patterns for certain location types (e.g. work, home, bus stop, etc.). This Artificial Neural Network (ANN) is used to automatically detect future location types by their spatio-temporal patterns. The same is done in order to predict the duration of stay at a certain location. Experiments revealed that neural nets were the most successful statistical and machine learning tool to detect those patterns. The location type identification algorithm reached an accuracy of 87.69\%, the duration prediction on binned data was less successful and deviated by an average of 0.69 bins. A challenge for the location type classification, as well as for the subsequent components, was the imbalance of trips and connections as well as the low accuracy of the trajectory data. The imbalance is grounded in the fact that most users exhibit strong habitual patterns (e.g. home > work), while other patterns are rather rare by comparison. The accuracy problem derives from the energy-saving location sampling mode, which creates less accurate results. Those locations are then used to build a network that represents the user's spatio-temporal behaviour. An initial untrained ANN to predict movement on the network only reached 46\% average accuracy. Only lowering the number of included edges, focusing on more common trips, increased the performance. In order to further improve the algorithm, the spatial trajectories were introduced into the predictions. To overcome the accuracy problem, trips between locations were clustered into so-called spatial corridors, which were intersected with the user's current trajectory. The resulting intersected trips were ranked through a k-nearest-neighbour algorithm. This increased the performance to 56\%. In a final step, a combination of a network and spatial clustering algorithm was built in order to create clusters, therein reducing the variety of possible trips. By only predicting the destination cluster instead of the exact location, it is possible to increase the performance to 75\% including all classes. A final set of components shows in two exemplary ways how to deduce additional inferences from the underlying spatio-temporal data. The first example presents a novel concept for predicting the 'potential memorisation index' for a certain location. The index is based on a cognitive model which derives the index from the user's activity data in that area. The second example embeds each location in its urban fabric and thereby enriches its cluster's metadata by further describing the temporal-semantic activity in an area (e.g. going to restaurants at noon). The success of the client-side classification and prediction approach, despite the challenges of inaccurate and imbalanced data, supports the claimed benefits of the client-side modelling concept. Since modern data-driven services at some point do need to receive user data, the thesis' computational model concludes with a concept for applying generalisation to semantic, temporal, and spatial data before sharing it with the remote service in order to comply with the overall goal to improve data privacy. In this context, the potentials of ensemble training (in regards to ANNs) are discussed in order to highlight the potential of only sharing the trained ANN instead of the raw input data. While the results of our evaluation support the assets of the proposed framework, there are two important downsides of our approach compared to server-side modelling. First, both of these server-side advantages are rooted in the server's access to multiple users' data. This allows a remote service to predict spatio-in the user-specific data, which represents the second downside. While minor classes will likely be minor classes in a bigger dataset as well, for each class, there will still be more variety than in the user-specific dataset. The author emphasises that the approach presented in this work holds the potential to change the privacy paradigm in modern data-driven services. Finding combinations of client- and server-side modelling could prove a promising new path for data-driven innovation. Beyond the technological perspective, throughout the thesis the author also offers a critical view on the data- and technology-driven development of this work. By introducing the client-side modelling with user-specific artificial neural networks, users generate their own algorithm. Those user-specific algorithms are influenced less by generalised biases or developers' prejudices. Therefore, the user develops a more diverse and individual perspective through his or her user model. This concept picks up the idea of critical cartography, which questions the status quo of how space is perceived and represented.}, language = {en} } @misc{GebserKaufmannSchaub2012, author = {Gebser, Martin and Kaufmann, Benjamin and Schaub, Torsten H.}, title = {Multi-threaded ASP solving with clasp}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, number = {586}, issn = {1866-8372}, doi = {10.25932/publishup-41397}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-413977}, pages = {21}, year = {2012}, abstract = {We present the new multi-threaded version of the state-of-the-art answer set solver clasp. We detail its component and communication architecture and illustrate how they support the principal functionalities of clasp. Also, we provide some insights into the data representation used for different constraint types handled by clasp. All this is accompanied by an extensive experimental analysis of the major features related to multi-threading in clasp.}, language = {en} } @misc{HoosKaminskiLindaueretal.2015, author = {Hoos, Holger and Kaminski, Roland and Lindauer, Marius and Schaub, Torsten H.}, title = {aspeed}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, number = {588}, issn = {1866-8372}, doi = {10.25932/publishup-41474}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-414743}, pages = {26}, year = {2015}, abstract = {Although Boolean Constraint Technology has made tremendous progress over the last decade, the efficacy of state-of-the-art solvers is known to vary considerably across different types of problem instances, and is known to depend strongly on algorithm parameters. This problem was addressed by means of a simple, yet effective approach using handmade, uniform, and unordered schedules of multiple solvers in ppfolio, which showed very impressive performance in the 2011 Satisfiability Testing (SAT) Competition. Inspired by this, we take advantage of the modeling and solving capacities of Answer Set Programming (ASP) to automatically determine more refined, that is, nonuniform and ordered solver schedules from the existing benchmarking data. We begin by formulating the determination of such schedules as multi-criteria optimization problems and provide corresponding ASP encodings. The resulting encodings are easily customizable for different settings, and the computation of optimum schedules can mostly be done in the blink of an eye, even when dealing with large runtime data sets stemming from many solvers on hundreds to thousands of instances. Also, the fact that our approach can be customized easily enabled us to swiftly adapt it to generate parallel schedules for multi-processor machines.}, language = {en} } @misc{GebserHarrisonKaminskietal.2015, author = {Gebser, Martin and Harrison, Amelia and Kaminski, Roland and Lifschitz, Vladimir and Schaub, Torsten H.}, title = {Abstract gringo}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, number = {592}, issn = {1866-8372}, doi = {10.25932/publishup-41475}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-414751}, pages = {15}, year = {2015}, abstract = {This paper defines the syntax and semantics of the input language of the ASP grounder gringo. The definition covers several constructs that were not discussed in earlier work on the semantics of that language, including intervals, pools, division of integers, aggregates with non-numeric values, and lparse-style aggregate expressions. The definition is abstract in the sense that it disregards some details related to representing programs by strings of ASCII characters. It serves as a specification for gringo from Version 4.5 on.}, language = {en} } @misc{GebserLeeLierler2011, author = {Gebser, Martin and Lee, Joohyung and Lierler, Yuliya}, title = {On elementary loops of logic programs}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, number = {566}, issn = {1866-8372}, doi = {10.25932/publishup-41309}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-413091}, pages = {36}, year = {2011}, abstract = {Using the notion of an elementary loop, Gebser and Schaub (2005. Proceedings of the Eighth International Conference on Logic Programming and Nonmonotonic Reasoning (LPNMR'05 ), 53-65) refined the theorem on loop formulas attributable to Lin and Zhao (2004) by considering loop formulas of elementary loops only. In this paper, we reformulate the definition of an elementary loop, extend it to disjunctive programs, and study several properties of elementary loops, including how maximal elementary loops are related to minimal unfounded sets. The results provide useful insights into the stable model semantics in terms of elementary loops. For a nondisjunctive program, using a graph-theoretic characterization of an elementary loop, we show that the problem of recognizing an elementary loop is tractable. On the other hand, we also show that the corresponding problem is coNP-complete for a disjunctive program. Based on the notion of an elementary loop, we present the class of Head-Elementary-loop-Free (HEF) programs, which strictly generalizes the class of Head-Cycle-Free (HCF) programs attributable to Ben-Eliyahu and Dechter (1994. Annals of Mathematics and Artificial Intelligence 12, 53-87). Like an HCF program, an HEF program can be turned into an equivalent nondisjunctive program in polynomial time by shifting head atoms into the body.}, language = {en} } @article{KaitouaRablMarkl2020, author = {Kaitoua, Abdulrahman and Rabl, Tilmann and Markl, Volker}, title = {A distributed data exchange engine for polystores}, series = {Information technology : methods and applications of informatics and information technology}, volume = {62}, journal = {Information technology : methods and applications of informatics and information technology}, number = {3-4}, publisher = {De Gruyter}, address = {Berlin}, issn = {1611-2776}, doi = {10.1515/itit-2019-0037}, pages = {145 -- 156}, year = {2020}, abstract = {There is an increasing interest in fusing data from heterogeneous sources. Combining data sources increases the utility of existing datasets, generating new information and creating services of higher quality. A central issue in working with heterogeneous sources is data migration: In order to share and process data in different engines, resource intensive and complex movements and transformations between computing engines, services, and stores are necessary. Muses is a distributed, high-performance data migration engine that is able to interconnect distributed data stores by forwarding, transforming, repartitioning, or broadcasting data among distributed engines' instances in a resource-, cost-, and performance-adaptive manner. As such, it performs seamless information sharing across all participating resources in a standard, modular manner. We show an overall improvement of 30 \% for pipelining jobs across multiple engines, even when we count the overhead of Muses in the execution time. This performance gain implies that Muses can be used to optimise large pipelines that leverage multiple engines.}, language = {en} } @article{DreselerBoissierRabletal.2020, author = {Dreseler, Markus and Boissier, Martin and Rabl, Tilmann and Uflacker, Matthias}, title = {Quantifying TPC-H choke points and their optimizations}, series = {Proceedings of the VLDB Endowment}, volume = {13}, journal = {Proceedings of the VLDB Endowment}, number = {8}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {2150-8097}, doi = {10.14778/3389133.3389138}, pages = {1206 -- 1220}, year = {2020}, abstract = {TPC-H continues to be the most widely used benchmark for relational OLAP systems. It poses a number of challenges, also known as "choke points", which database systems have to solve in order to achieve good benchmark results. Examples include joins across multiple tables, correlated subqueries, and correlations within the TPC-H data set. Knowing the impact of such optimizations helps in developing optimizers as well as in interpreting TPC-H results across database systems. This paper provides a systematic analysis of choke points and their optimizations. It complements previous work on TPC-H choke points by providing a quantitative discussion of their relevance. It focuses on eleven choke points where the optimizations are beneficial independently of the database system. Of these, the flattening of subqueries and the placement of predicates have the biggest impact. Three queries (Q2, Q17, and Q21) are strongly ifluenced by the choice of an efficient query plan; three others (Q1, Q13, and Q18) are less influenced by plan optimizations and more dependent on an efficient execution engine.}, language = {en} } @article{NavarroOrejasPinoetal.2021, author = {Navarro, Marisa and Orejas, Fernando and Pino, Elvira and Lambers, Leen}, title = {A navigational logic for reasoning about graph properties}, series = {Journal of logical and algebraic methods in programming}, volume = {118}, journal = {Journal of logical and algebraic methods in programming}, publisher = {Elsevier Science}, address = {Amsterdam [u.a.]}, issn = {2352-2208}, doi = {10.1016/j.jlamp.2020.100616}, pages = {33}, year = {2021}, abstract = {Graphs play an important role in many areas of Computer Science. In particular, our work is motivated by model-driven software development and by graph databases. For this reason, it is very important to have the means to express and to reason about the properties that a given graph may satisfy. With this aim, in this paper we present a visual logic that allows us to describe graph properties, including navigational properties, i.e., properties about the paths in a graph. The logic is equipped with a deductive tableau method that we have proved to be sound and complete.}, language = {en} } @phdthesis{Makowski2021, author = {Makowski, Silvia}, title = {Discriminative Models for Biometric Identification using Micro- and Macro-Movements of the Eyes}, school = {Universit{\"a}t Potsdam}, pages = {xi, 91}, year = {2021}, abstract = {Human visual perception is an active process. Eye movements either alternate between fixations and saccades or follow a smooth pursuit movement in case of moving targets. Besides these macroscopic gaze patterns, the eyes perform involuntary micro-movements during fixations which are commonly categorized into micro-saccades, drift and tremor. Eye movements are frequently studied in cognitive psychology, because they reflect a complex interplay of perception, attention and oculomotor control. A common insight of psychological research is that macro-movements are highly individual. Inspired by this finding, there has been a considerable amount of prior research on oculomotoric biometric identification. However, the accuracy of known approaches is too low and the time needed for identification is too long for any practical application. This thesis explores discriminative models for the task of biometric identification. Discriminative models optimize a quality measure of the predictions and are usually superior to generative approaches in discriminative tasks. However, using discriminative models requires to select a suitable form of data representation for sequential eye gaze data; i.e., by engineering features or constructing a sequence kernel and the performance of the classification model strongly depends on the data representation. We study two fundamentally different ways of representing eye gaze within a discriminative framework. In the first part of this thesis, we explore the integration of data and psychological background knowledge in the form of generative models to construct representations. To this end, we first develop generative statistical models of gaze behavior during reading and scene viewing that account for viewer-specific distributional properties of gaze patterns. In a second step, we develop a discriminative identification model by deriving Fisher kernel functions from these and several baseline models. We find that an SVM with Fisher kernel is able to reliably identify users based on their eye gaze during reading and scene viewing. However, since the generative models are constrained to use low-frequency macro-movements, they discard a significant amount of information contained in the raw eye tracking signal at a high cost: identification requires about one minute of input recording, which makes it inapplicable for real world biometric systems. In the second part of this thesis, we study a purely data-driven modeling approach. Here, we aim at automatically discovering the individual pattern hidden in the raw eye tracking signal. To this end, we develop a deep convolutional neural network DeepEyedentification that processes yaw and pitch gaze velocities and learns a representation end-to-end. Compared to prior work, this model increases the identification accuracy by one order of magnitude and the time to identification decreases to only seconds. The DeepEyedentificationLive model further improves upon the identification performance by processing binocular input and it also detects presentation-attacks. We find that by learning a representation, the performance of oculomotoric identification and presentation-attack detection can be driven close to practical relevance for biometric applications. Eye tracking devices with high sampling frequency and precision are expensive and the applicability of eye movement as a biometric feature heavily depends on cost of recording devices. In the last part of this thesis, we therefore study the requirements on data quality by evaluating the performance of the DeepEyedentificationLive network under reduced spatial and temporal resolution. We find that the method still attains a high identification accuracy at a temporal resolution of only 250 Hz and a precision of 0.03 degrees. Reducing both does not have an additive deteriorating effect.}, language = {en} }