@phdthesis{Brueckner2012,
  author    = {Br{\"u}ckner, Michael},
  title     = {Prediction games : machine learning in the presence of an adversary},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-203-2},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-60375},
  school      = {Universit{\"a}t Potsdam},
  pages     = {x, 121},
  year      = {2012},
  abstract  = {In many applications one is faced with the problem of inferring some functional relation between input and output variables from given data. Consider, for instance, the task of email spam filtering where one seeks to find a model which automatically assigns new, previously unseen emails to class spam or non-spam. Building such a predictive model based on observed training inputs (e.g., emails) with corresponding outputs (e.g., spam labels) is a major goal of machine learning. Many learning methods assume that these training data are governed by the same distribution as the test data which the predictive model will be exposed to at application time. That assumption is violated when the test data are generated in response to the presence of a predictive model. This becomes apparent, for instance, in the above example of email spam filtering. Here, email service providers employ spam filters and spam senders engineer campaign templates such as to achieve a high rate of successful deliveries despite any filters. Most of the existing work casts such situations as learning robust models which are unsusceptible against small changes of the data generation process. The models are constructed under the worst-case assumption that these changes are performed such to produce the highest possible adverse effect on the performance of the predictive model. However, this approach is not capable to realistically model the true dependency between the model-building process and the process of generating future data. We therefore establish the concept of prediction games: We model the interaction between a learner, who builds the predictive model, and a data generator, who controls the process of data generation, as an one-shot game. The game-theoretic framework enables us to explicitly model the players' interests, their possible actions, their level of knowledge about each other, and the order at which they decide for an action. We model the players' interests as minimizing their own cost function which both depend on both players' actions. The learner's action is to choose the model parameters and the data generator's action is to perturbate the training data which reflects the modification of the data generation process with respect to the past data. We extensively study three instances of prediction games which differ regarding the order in which the players decide for their action. We first assume that both player choose their actions simultaneously, that is, without the knowledge of their opponent's decision. We identify conditions under which this Nash prediction game has a meaningful solution, that is, a unique Nash equilibrium, and derive algorithms that find the equilibrial prediction model. As a second case, we consider a data generator who is potentially fully informed about the move of the learner. This setting establishes a Stackelberg competition. We derive a relaxed optimization criterion to determine the solution of this game and show that this Stackelberg prediction game generalizes existing prediction models. Finally, we study the setting where the learner observes the data generator's action, that is, the (unlabeled) test data, before building the predictive model. As the test data and the training data may be governed by differing probability distributions, this scenario reduces to learning under covariate shift. We derive a new integrated as well as a two-stage method to account for this data set shift. In case studies on email spam filtering we empirically explore properties of all derived models as well as several existing baseline methods. We show that spam filters resulting from the Nash prediction game as well as the Stackelberg prediction game in the majority of cases outperform other existing baseline methods.},
  language  = {en}
}
@phdthesis{Thiele2011,
  author    = {Thiele, Sven},
  title     = {Modeling biological systems with Answer Set Programming},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-59383},
  school      = {Universit{\"a}t Potsdam},
  year      = {2011},
  abstract  = {Biology has made great progress in identifying and measuring the building blocks of life. The availability of high-throughput methods in molecular biology has dramatically accelerated the growth of biological knowledge for various organisms. The advancements in genomic, proteomic and metabolomic technologies allow for constructing complex models of biological systems. An increasing number of biological repositories is available on the web, incorporating thousands of biochemical reactions and genetic regulations. Systems Biology is a recent research trend in life science, which fosters a systemic view on biology. In Systems Biology one is interested in integrating the knowledge from all these different sources into models that capture the interaction of these entities. By studying these models one wants to understand the emerging properties of the whole system, such as robustness. However, both measurements as well as biological networks are prone to considerable incompleteness, heterogeneity and mutual inconsistency, which makes it highly non-trivial to draw biologically meaningful conclusions in an automated way. Therefore, we want to promote Answer Set Programming (ASP) as a tool for discrete modeling in Systems Biology. ASP is a declarative problem solving paradigm, in which a problem is encoded as a logic program such that its answer sets represent solutions to the problem. ASP has intrinsic features to cope with incompleteness, offers a rich modeling language and highly efficient solving technology. We present ASP solutions, for the analysis of genetic regulatory networks, determining consistency with observed measurements and identifying minimal causes for inconsistency. We extend this approach for computing minimal repairs on model and data that restore consistency. This method allows for predicting unobserved data even in case of inconsistency. Further, we present an ASP approach to metabolic network expansion. This approach exploits the easy characterization of reachability in ASP and its various reasoning methods, to explore the biosynthetic capabilities of metabolic reaction networks and generate hypotheses for extending the network. Finally, we present the BioASP library, a Python library which encapsulates our ASP solutions into the imperative programming paradigm. The library allows for an easy integration of ASP solution into system rich environments, as they exist in Systems Biology.},
  language  = {en}
}
@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}
}
@phdthesis{Sawade2012,
  author    = {Sawade, Christoph},
  title     = {Active evaluation of predictive models},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-255-1},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-65583},
  school      = {Universit{\"a}t Potsdam},
  pages     = {ix, 157},
  year      = {2012},
  abstract  = {The field of machine learning studies algorithms that infer predictive models from data. Predictive models are applicable for many practical tasks such as spam filtering, face and handwritten digit recognition, and personalized product recommendation. In general, they are used to predict a target label for a given data instance. In order to make an informed decision about the deployment of a predictive model, it is crucial to know the model's approximate performance. To evaluate performance, a set of labeled test instances is required that is drawn from the distribution the model will be exposed to at application time. In many practical scenarios, unlabeled test instances are readily available, but the process of labeling them can be a time- and cost-intensive task and may involve a human expert. This thesis addresses the problem of evaluating a given predictive model accurately with minimal labeling effort. We study an active model evaluation process that selects certain instances of the data according to an instrumental sampling distribution and queries their labels. We derive sampling distributions that minimize estimation error with respect to different performance measures such as error rate, mean squared error, and F-measures. An analysis of the distribution that governs the estimator leads to confidence intervals, which indicate how precise the error estimation is. Labeling costs may vary across different instances depending on certain characteristics of the data. For instance, documents differ in their length, comprehensibility, and technical requirements; these attributes affect the time a human labeler needs to judge relevance or to assign topics. To address this, the sampling distribution is extended to incorporate instance-specific costs. We empirically study conditions under which the active evaluation processes are more accurate than a standard estimate that draws equally many instances from the test distribution. We also address the problem of comparing the risks of two predictive models. The standard approach would be to draw instances according to the test distribution, label the selected instances, and apply statistical tests to identify significant differences. Drawing instances according to an instrumental distribution affects the power of a statistical test. We derive a sampling procedure that maximizes test power when used to select instances, and thereby minimizes the likelihood of choosing the inferior model. Furthermore, we investigate the task of comparing several alternative models; the objective of an evaluation could be to rank the models according to the risk that they incur or to identify the model with lowest risk. An experimental study shows that the active procedure leads to higher test power than the standard test in many application domains. Finally, we study the problem of evaluating the performance of ranking functions, which are used for example for web search. In practice, ranking performance is estimated by applying a given ranking model to a representative set of test queries and manually assessing the relevance of all retrieved items for each query. We apply the concepts of active evaluation and active comparison to ranking functions and derive optimal sampling distributions for the commonly used performance measures Discounted Cumulative Gain and Expected Reciprocal Rank. Experiments on web search engine data illustrate significant reductions in labeling costs.},
  language  = {en}
}
@phdthesis{Lindauer2014,
  author    = {Lindauer, T. Marius},
  title     = {Algorithm selection, scheduling and configuration of Boolean constraint solvers},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-71260},
  school      = {Universit{\"a}t Potsdam},
  pages     = {ii, 130},
  year      = {2014},
  abstract  = {Boolean constraint solving technology has made tremendous progress over the last decade, leading to industrial-strength solvers, for example, in the areas of answer set programming (ASP), the constraint satisfaction problem (CSP), propositional satisfiability (SAT) and satisfiability of quantified Boolean formulas (QBF). However, in all these areas, there exist multiple solving strategies that work well on different applications; no strategy dominates all other strategies. Therefore, no individual solver shows robust state-of-the-art performance in all kinds of applications. Additionally, the question arises how to choose a well-performing solving strategy for a given application; this is a challenging question even for solver and domain experts. One way to address this issue is the use of portfolio solvers, that is, a set of different solvers or solver configurations. We present three new automatic portfolio methods: (i) automatic construction of parallel portfolio solvers (ACPP) via algorithm configuration,(ii) solving the \$NP\$-hard problem of finding effective algorithm schedules with Answer Set Programming (aspeed), and (iii) a flexible algorithm selection framework (claspfolio2) allowing for fair comparison of different selection approaches. All three methods show improved performance and robustness in comparison to individual solvers on heterogeneous instance sets from many different applications. Since parallel solvers are important to effectively solve hard problems on parallel computation systems (e.g., multi-core processors), we extend all three approaches to be effectively applicable in parallel settings. We conducted extensive experimental studies different instance sets from ASP, CSP, MAXSAT, Operation Research (OR), SAT and QBF that indicate an improvement in the state-of-the-art solving heterogeneous instance sets. Last but not least, from our experimental studies, we deduce practical advice regarding the question when to apply which of our methods.},
  language  = {en}
}
@phdthesis{Ishebabi2010,
  author    = {Ishebabi, Harold},
  title     = {Architecture synthesis for adaptive multiprocessor systems on chip},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-41316},
  school      = {Universit{\"a}t Potsdam},
  year      = {2010},
  abstract  = {This thesis presents methods for automated synthesis of flexible chip multiprocessor systems from parallel programs targeted at FPGAs to exploit both task-level parallelism and architecture customization. Automated synthesis is necessitated by the complexity of the design space. A detailed description of the design space is provided in order to determine which parameters should be modeled to facilitate automated synthesis by optimizing a cost function, the emphasis being placed on inclusive modeling of parameters from application, architectural and physical subspaces, as well as their joint coverage in order to avoid pre-constraining the design space. Given a parallel program and a set of an IP library, the automated synthesis problem is to simultaneously (i) select processors (ii) map and schedule tasks to them, and (iii) select one or several networks for inter-task communications such that design constraints and optimization objectives are met. The research objective in this thesis is to find a suitable model for automated synthesis, and to evaluate methods of using the model for architectural optimizations. Our contributions are a holistic approach for the design of such systems, corresponding models to facilitate automated synthesis, evaluation of optimization methods using state of the art integer linear and answer set programming, as well as the development of synthesis heuristics to solve runtime challenges.},
  language  = {en}
}
@phdthesis{Harmeling2004,
  author    = {Harmeling, Stefan},
  title     = {Independent component analysis and beyond},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-0001540},
  school      = {Universit{\"a}t Potsdam},
  year      = {2004},
  abstract  = {'Independent component analysis' (ICA) ist ein Werkzeug der statistischen Datenanalyse und Signalverarbeitung, welches multivariate Signale in ihre Quellkomponenten zerlegen kann. Obwohl das klassische ICA Modell sehr n{\"u}tzlich ist, gibt es viele Anwendungen, die Erweiterungen von ICA erfordern. In dieser Dissertation pr{\"a}sentieren wir neue Verfahren, die die Funktionalit{\"a}t von ICA erweitern: (1) Zuverl{\"a}ssigkeitsanalyse und Gruppierung von unabh{\"a}ngigen Komponenten durch Hinzuf{\"u}gen von Rauschen, (2) robuste und {\"u}berbestimmte ('over-complete') ICA durch Ausreissererkennung, und (3) nichtlineare ICA mit Kernmethoden.},
  language  = {en}
}
@phdthesis{Dietze2004,
  author    = {Dietze, Stefan},
  title     = {Modell und Optimierungsansatz f{\"u}r Open Source Softwareentwicklungsprozesse},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-0001594},
  school      = {Universit{\"a}t Potsdam},
  year      = {2004},
  abstract  = {Gerade in den letzten Jahren erfuhr Open Source Software (OSS) eine zunehmende Verbreitung und Popularit{\"a}t und hat sich in verschiedenen Anwendungsdom{\"a}nen etabliert. Die Prozesse, welche sich im Kontext der OSS-Entwicklung (auch: OSSD \– Open Source Software-Development) evolution{\"a}r herausgebildet haben, weisen in den verschiedenen OSS-Entwicklungsprojekten z.T. {\"a}hnliche Eigenschaften und Strukturen auf und auch die involvierten Entit{\"a}ten, wie z.B. Artefakte, Rollen oder Software-Werkzeuge sind weitgehend miteinander vergleichbar. Dies motiviert den Gedanken, ein verallgemeinerbares Modell zu entwickeln, welches die generalisierbaren Entwicklungsprozesse im Kontext von OSS zu einem {\"u}bertragbaren Modell abstrahiert. Auch in der Wissenschaftsdisziplin des Software Engineering (SE) wurde bereits erkannt, dass sich der OSSD-Ansatz in verschiedenen Aspekten erheblich von klassischen (propriet{\"a}ren) Modellen des SE unterscheidet und daher diese Methoden einer eigenen wissenschaftlichen Betrachtung bed{\"u}rfen. In verschiedenen Publikationen wurden zwar bereits einzelne Aspekte der OSS-Entwicklung analysiert und Theorien {\"u}ber die zugrundeliegenden Entwicklungsmethoden formuliert, aber es existiert noch keine umfassende Beschreibung der typischen Prozesse der OSSD-Methodik, die auf einer empirischen Untersuchung existierender OSS-Entwicklungsprojekte basiert. Da dies eine Voraussetzung f{\"u}r die weitere wissenschaftliche Auseinandersetzung mit OSSD-Prozessen darstellt, wird im Rahmen dieser Arbeit auf der Basis vergleichender Fallstudien ein deskriptives Modell der OSSD-Prozesse hergeleitet und mit Modellierungselementen der UML formalisiert beschrieben. Das Modell generalisiert die identifizierten Prozesse, Prozessentit{\"a}ten und Software-Infrastrukturen der untersuchten OSSD-Projekte. Es basiert auf einem eigens entwickelten Metamodell, welches die zu analysierenden Entit{\"a}ten identifiziert und die Modellierungssichten und -elemente beschreibt, die zur UML-basierten Beschreibung der Entwicklungsprozesse verwendet werden. In einem weiteren Arbeitsschritt wird eine weiterf{\"u}hrende Analyse des identifizierten Modells durchgef{\"u}hrt, um Implikationen, und Optimierungspotentiale aufzuzeigen. Diese umfassen beispielsweise die ungen{\"u}gende Plan- und Terminierbarkeit von Prozessen oder die beobachtete Tendenz von OSSD-Akteuren, verschiedene Aktivit{\"a}ten mit unterschiedlicher Intensit{\"a}t entsprechend der subjektiv wahrgenommenen Anreize auszu{\"u}ben, was zur Vernachl{\"a}ssigung einiger Prozesse f{\"u}hrt. Anschließend werden Optimierungszielstellungen dargestellt, die diese Unzul{\"a}nglichkeiten adressieren, und ein Optimierungsansatz zur Verbesserung des OSSD-Modells wird beschrieben. Dieser Ansatz umfasst die Erweiterung der identifizierten Rollen, die Einf{\"u}hrung neuer oder die Erweiterung bereits identifizierter Prozesse und die Modifikation oder Erweiterung der Artefakte des generalisierten OSS-Entwicklungsmodells. Die vorgestellten Modellerweiterungen dienen vor allem einer gesteigerten Qualit{\"a}tssicherung und der Kompensation von vernachl{\"a}ssigten Prozessen, um sowohl die entwickelte Software- als auch die Prozessqualit{\"a}t im OSSD-Kontext zu verbessern. Desweiteren werden Softwarefunktionalit{\"a}ten beschrieben, welche die identifizierte bestehende Software-Infrastruktur erweitern und eine gesamtheitlichere, softwaretechnische Unterst{\"u}tzung der OSSD-Prozesse erm{\"o}glichen sollen. Abschließend werden verschiedene Anwendungsszenarien der Methoden des OSS-Entwicklungsmodells, u.a. auch im kommerziellen SE, identifiziert und ein Implementierungsansatz basierend auf der OSS GENESIS vorgestellt, der zur Implementierung und Unterst{\"u}tzung des OSSD-Modells verwendet werden kann.},
  language  = {de}
}
@phdthesis{Konczak2007,
  author    = {Konczak, Kathrin},
  title     = {Preferences in answer set programming},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-12058},
  school      = {Universit{\"a}t Potsdam},
  year      = {2007},
  abstract  = {Answer Set Programming (ASP) emerged in the late 1990s as a new logic programming paradigm, having its roots in nonmonotonic reasoning, deductive databases, and logic programming with negation as failure. The basic idea of ASP is to represent a computational problem as a logic program whose answer sets correspond to solutions, and then to use an answer set solver for finding answer sets of the program. ASP is particularly suited for solving NP-complete search problems. Among these, we find applications to product configuration, diagnosis, and graph-theoretical problems, e.g. finding Hamiltonian cycles. On different lines of ASP research, many extensions of the basic formalism have been proposed. The most intensively studied one is the modelling of preferences in ASP. They constitute a natural and effective way of selecting preferred solutions among a plethora of solutions for a problem. For example, preferences have been successfully used for timetabling, auctioning, and product configuration. In this thesis, we concentrate on preferences within answer set programming. Among several formalisms and semantics for preference handling in ASP, we concentrate on ordered logic programs with the underlying D-, W-, and B-semantics. In this setting, preferences are defined among rules of a logic program. They select preferred answer sets among (standard) answer sets of the underlying logic program. Up to now, those preferred answer sets have been computed either via a compilation method or by meta-interpretation. Hence, the question comes up, whether and how preferences can be integrated into an existing ASP solver. To solve this question, we develop an operational graph-based framework for the computation of answer sets of logic programs. Then, we integrate preferences into this operational approach. We empirically observe that our integrative approach performs in most cases better than the compilation method or meta-interpretation. Another research issue in ASP are optimization methods that remove redundancies, as also found in database query optimizers. For these purposes, the rather recently suggested notion of strong equivalence for ASP can be used. If a program is strongly equivalent to a subprogram of itself, then one can always use the subprogram instead of the original program, a technique which serves as an effective optimization method. Up to now, strong equivalence has not been considered for logic programs with preferences. In this thesis, we tackle this issue and generalize the notion of strong equivalence to ordered logic programs. We give necessary and sufficient conditions for the strong equivalence of two ordered logic programs. Furthermore, we provide program transformations for ordered logic programs and show in how far preferences can be simplified. Finally, we present two new applications for preferences within answer set programming. First, we define new procedures for group decision making, which we apply to the problem of scheduling a group meeting. As a second new application, we reconstruct a linguistic problem appearing in German dialects within ASP. Regarding linguistic studies, there is an ongoing debate about how unique the rule systems of language are in human cognition. The reconstruction of grammatical regularities with tools from computer science has consequences for this debate: if grammars can be modelled this way, then they share core properties with other non-linguistic rule systems.},
  language  = {en}
}
@phdthesis{Knoepfel2004,
  author    = {Kn{\"o}pfel, Andreas},
  title     = {Konzepte der Beschreibung interaktiver Systeme},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-2898},
  school      = {Universit{\"a}t Potsdam},
  year      = {2004},
  abstract  = {Interaktive System sind dynamische Systeme mit einem zumeist informationellen Kern, die {\"u}ber eine Benutzungsschnittstelle von einem oder mehreren Benutzern bedient werden k{\"o}nnen. Grundlage f{\"u}r die Benutzung interaktiver Systeme ist das Verst{\"a}ndnis von Zweck und Funktionsweise. Allein aus Form und Gestalt der Benutzungsschnittstelle ergibt sich ein solches Verst{\"a}ndnis nur in einfachen F{\"a}llen. Mit steigender Komplexit{\"a}t ist daher eine verst{\"a}ndliche Beschreibung solcher Systeme f{\"u}r deren Entwicklung und Benutzung unverzichtbar. Abh{\"a}ngig von ihrem Zweck variieren die Formen vorgefundener Beschreibungen in der Literatur sehr stark. Ausschlaggebend f{\"u}r die Verst{\"a}ndlichkeit einer Beschreibung ist jedoch prim{\"a}r die ihr zugrundeliegende Begriffswelt. Zur Beschreibung allgemeiner komplexer diskreter Systeme - aufbauend auf einer getrennten Betrachtung von Aufbau-, Ablauf- und Wertestrukturen - existiert eine bew{\"a}hrte Begriffswelt. Eine Spezialisierung dieser Begriffs- und Vorstellungswelt, die den unterschiedlichen Betrachtungsebenen interaktiver Systeme gerecht wird und die als Grundlage beliebiger Beschreibungsans{\"a}tze interaktiver Systeme dienen kann, gibt es bisher nicht. Ziel dieser Arbeit ist die Bereitstellung einer solchen Begriffswelt zur effizienten Kommunikation der Strukturen interaktiver Systeme. Dadurch soll die Grundlage f{\"u}r eine sinnvolle Erg{\"a}nzung bestehender Beschreibungs- und Entwicklungsans{\"a}tze geschaffen werden. Prinzipien der Gestaltung von Benutzungsschnittstellen, Usability- oder Ergonomiebetrachtungen stehen nicht im Mittelpunkt der Arbeit. Ausgehend von der informationellen Komponente einer Benutzungsschnittstelle werden drei Modellebenen abgegrenzt, die bei der Betrachtung eines interaktiven Systems zu unterscheiden sind. Jede Modellebene ist durch eine typische Begriffswelt gekennzeichnet, die ihren Ursprung in einer aufbauverwurzelten Vorstellung hat. Der durchg{\"a}ngige Bezug auf eine Systemvorstellung unterscheidet diesen Ansatz von dem bereits bekannten Konzept der Abgrenzung unterschiedlicher Ebenen verschiedenartiger Entwurfsentscheidungen. Die Fundamental Modeling Concepts (FMC) bilden dabei die Grundlage f{\"u}r die Findung und die Darstellung von Systemstrukturen. Anhand bestehender Systembeschreibungen wird gezeigt, wie die vorgestellte Begriffswelt zur Modellfindung genutzt werden kann. Dazu wird eine repr{\"a}sentative Auswahl vorgefundener Systembeschreibungen aus der einschl{\"a}gigen Literatur daraufhin untersucht, in welchem Umfang durch sie die Vorstellungswelt dynamischer Systeme zum Ausdruck kommt. Defizite in der urspr{\"u}nglichen Darstellung werden identifiziert. Anhand von Alternativmodellen zu den betrachteten Systemen wird der Nutzen der vorgestellten Begriffswelt und Darstellungsweise demonstriert.},
  subject      = {Systementwurf},
  language  = {de}
}
@phdthesis{RobinsonMallett2005,
  author    = {Robinson-Mallett, Christopher},
  title     = {Modellbasierte Modulpr{\"u}fung f{\"u}r die Entwicklung technischer, softwareintensiver Systeme mit Real-Time Object-Oriented Modeling},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-6045},
  school      = {Universit{\"a}t Potsdam},
  year      = {2005},
  abstract  = {Mit zunehmender Komplexit{\"a}t technischer Softwaresysteme ist die Nachfrage an produktiveren Methoden und Werkzeugen auch im sicherheitskritischen Umfeld gewachsen. Da insbesondere objektorientierte und modellbasierte Ans{\"a}tze und Methoden ausgezeichnete Eigenschaften zur Entwicklung großer und komplexer Systeme besitzen, ist zu erwarten, dass diese in naher Zukunft selbst bis in sicherheitskritische Bereiche der Softwareentwicklung vordringen. Mit der Unified Modeling Language Real-Time (UML-RT) wird eine Softwareentwicklungsmethode f{\"u}r technische Systeme durch die Object Management Group (OMG) propagiert. F{\"u}r den praktischen Einsatz im technischen und sicherheitskritischen Umfeld muss diese Methode nicht nur bestimmte technische Eigenschaften, beispielsweise temporale Analysierbarkeit, besitzen, sondern auch in einen bestehenden Qualit{\"a}tssicherungsprozess integrierbar sein. Ein wichtiger Aspekt der Integration der UML-RT in ein qualit{\"a}tsorientiertes Prozessmodell, beispielsweise in das V-Modell, ist die Verf{\"u}gbarkeit von ausgereiften Konzepten und Methoden f{\"u}r einen systematischen Modultest. Der Modultest dient als erste Qualitit{\"a}tssicherungsphase nach der Implementierung der Fehlerfindung und dem Qualit{\"a}tsnachweis f{\"u}r jede separat pr{\"u}fbare Softwarekomponente eines Systems. W{\"a}hrend dieser Phase stellt die Durchf{\"u}hrung von systematischen Tests die wichtigste Qualit{\"a}tssicherungsmaßnahme dar. W{\"a}hrend zum jetzigen Zeitpunkt zwar ausgereifte Methoden und Werkzeuge f{\"u}r die modellbasierte Softwareentwicklung zur Verf{\"u}gung stehen, existieren nur wenig {\"u}berzeugende L{\"o}sungen f{\"u}r eine systematische modellbasierte Modulpr{\"u}fung. Die durchg{\"a}ngige Verwendung ausf{\"u}hrbarer Modelle und Codegenerierung stellen wesentliche Konzepte der modellbasierten Softwareentwicklung dar. Sie dienen der konstruktiven Fehlerreduktion durch Automatisierung ansonsten fehlertr{\"a}chtiger, manueller Vorg{\"a}nge. Im Rahmen einer modellbasierten Qualit{\"a}tssicherung sollten diese Konzepte konsequenterweise in die sp{\"a}teren Qualit{\"a}tssicherungsphasen transportiert werden. Daher ist eine wesentliche Forderung an ein Verfahren zur modellbasierten Modulpr{\"u}fung ein m{\"o}glichst hoher Grad an Automatisierung. In aktuellen Entwicklungen hat sich f{\"u}r die Generierung von Testf{\"a}llen auf Basis von Zustandsautomaten die Verwendung von Model Checking als effiziente und an die vielf{\"a}ltigsten Testprobleme anpassbare Methode bew{\"a}hrt. Der Ansatz des Model Checking stammt urspr{\"u}nglich aus dem Entwurf von Kommunikationsprotokollen und wurde bereits erfolgreich auf verschiedene Probleme der Modellierung technischer Software angewendet. Insbesondere in der Gegenwart ausf{\"u}hrbarer, automatenbasierter Modelle erscheint die Verwendung von Model Checking sinnvoll, das die Existenz einer formalen, zustandsbasierten Spezifikation voraussetzt. Ein ausf{\"u}hrbares, zustandsbasiertes Modell erf{\"u}llt diese Anforderungen in der Regel. Aus diesen Gr{\"u}nden ist die Wahl eines Model Checking Ansatzes f{\"u}r die Generierung von Testf{\"a}llen im Rahmen eines modellbasierten Modultestverfahrens eine logische Konsequenz. Obwohl in der aktuellen Spezifikation der UML-RT keine eindeutigen Aussagen {\"u}ber den zur Verhaltensbeschreibung zu verwendenden Formalismus gemacht werden, ist es wahrscheinlich, dass es sich bei der UML-RT um eine zu Real-Time Object-Oriented Modeling (ROOM) kompatible Methode handelt. Alle in dieser Arbeit pr{\"a}sentierten Methoden und Ergebnisse sind somit auf die kommende UML-RT {\"u}bertragbar und von sehr aktueller Bedeutung. Aus den genannten Gr{\"u}nden verfolgt diese Arbeit das Ziel, die analytische Qualit{\"a}tssicherung in der modellbasierten Softwareentwicklung mittels einer modellbasierten Methode f{\"u}r den Modultest zu verbessern. Zu diesem Zweck wird eine neuartige Testmethode pr{\"a}sentiert, die auf automatenbasierten Verhaltensmodellen und CTL Model Checking basiert. Die Testfallgenerierung kann weitgehend automatisch erfolgen, um Fehler durch menschlichen Einfluss auszuschließen. Das entwickelte Modultestverfahren ist in die technischen Konzepte Model Driven Architecture und ROOM, beziehungsweise UML-RT, sowie in die organisatorischen Konzepte eines qualit{\"a}tsorientierten Prozessmodells, beispielsweise das V-Modell, integrierbar.},
  subject      = {Software},
  language  = {de}
}
@phdthesis{Ziehe2005,
  author    = {Ziehe, Andreas},
  title     = {Blind source separation based on joint diagonalization of matrices with applications in biomedical signal processing},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-5694},
  school      = {Universit{\"a}t Potsdam},
  year      = {2005},
  abstract  = {This thesis is concerned with the solution of the blind source separation problem (BSS). The BSS problem occurs frequently in various scientific and technical applications. In essence, it consists in separating meaningful underlying components out of a mixture of a multitude of superimposed signals. In the recent research literature there are two related approaches to the BSS problem: The first is known as Independent Component Analysis (ICA), where the goal is to transform the data such that the components become as independent as possible. The second is based on the notion of diagonality of certain characteristic matrices derived from the data. Here the goal is to transform the matrices such that they become as diagonal as possible. In this thesis we study the latter method of approximate joint diagonalization (AJD) to achieve a solution of the BSS problem. After an introduction to the general setting, the thesis provides an overview on particular choices for the set of target matrices that can be used for BSS by joint diagonalization. As the main contribution of the thesis, new algorithms for approximate joint diagonalization of several matrices with non-orthogonal transformations are developed. These newly developed algorithms will be tested on synthetic benchmark datasets and compared to other previous diagonalization algorithms. Applications of the BSS methods to biomedical signal processing are discussed and exemplified with real-life data sets of multi-channel biomagnetic recordings.},
  subject      = {Signaltrennung},
  language  = {en}
}
@phdthesis{Groene2004,
  author    = {Gr{\"o}ne, Bernhard},
  title     = {Konzeptionelle Patterns und ihre Darstellung},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-2302},
  school      = {Universit{\"a}t Potsdam},
  pages     = {vii ; 120},
  year      = {2004},
  abstract  = {Zur Beherrschung großer Systeme, insbesondere zur Weitergabe und Nutzung von Erfahrungswissen in der fr{\"u}hen Entwurfs- und Planungsphase, ben{\"o}tigt man Abstraktionen f{\"u}r deren Strukturen. Trennt man Software- von Systemstrukturen, kann man mit letzteren Systeme auf ausreichend hohem Abstraktionsgrad beschreiben.Software-Patterns dienen dazu, Erfahrungswissen bez{\"u}glich programmierter Systeme strukturiert weiterzugeben. Dabei wird unterschieden zwischen Idiomen, die sich auf L{\"o}sungen mit einer bestimmten Programmiersprache beziehen, Design-Patterns, die nur einen kleinen Teil des Programms betreffen und Architektur-Patterns, deren Einfluss {\"u}ber einen gr{\"o}ßeren Teil oder gar das komplette Programm reicht. Eine Untersuchung von existierenden Patterns zeigt, dass deren Konzepte n{\"u}tzlich zum Finden von Systemstrukturen sind. Die grafische Darstellung dieser Patterns ist dagegen oft auf Software-Strukturen eingeschr{\"a}nkt und ist f{\"u}r die Vermittlung von Erfahrungen zum Finden von Systemstrukturen meist nicht geeignet. Daher wird die Kategorie der konzeptionellen Patterns mit einer darauf abgestimmten grafischen Darstellungsform vorgeschlagen, bei denen Problem und L{\"o}sungsvorschlag im Bereich der Systemstrukturen liegen. Sie betreffen informationelle Systeme, sind aber nicht auf L{\"o}sungen mit Software beschr{\"a}nkt. Die Systemstrukturen werden grafisch dargestellt, wobei daf{\"u}r die Fundamental Modeling Concepts (FMC) verwendet werden, die zur Darstellung von Systemstrukturen entwickelt wurden.},
  language  = {de}
}
@phdthesis{Floeter2005,
  author    = {Fl{\"o}ter, Andr{\´e}},
  title     = {Analyzing biological expression data based on decision tree induction},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-6416},
  school      = {Universit{\"a}t Potsdam},
  year      = {2005},
  abstract  = {Modern biological analysis techniques supply scientists with various forms of data. One category of such data are the so called "expression data". These data indicate the quantities of biochemical compounds present in tissue samples. Recently, expression data can be generated at a high speed. This leads in turn to amounts of data no longer analysable by classical statistical techniques. Systems biology is the new field that focuses on the modelling of this information. At present, various methods are used for this purpose. One superordinate class of these meth­ods is machine learning. Methods of this kind had, until recently, predominantly been used for classification and prediction tasks. This neglected a powerful secondary benefit: the ability to induce interpretable models. Obtaining such models from data has become a key issue within Systems biology. Numerous approaches have been proposed and intensively discussed. This thesis focuses on the examination and exploitation of one basic technique: decision trees. The concept of comparing sets of decision trees is developed. This method offers the pos­sibility of identifying significant thresholds in continuous or discrete valued attributes through their corresponding set of decision trees. Finding significant thresholds in attributes is a means of identifying states in living organisms. Knowing about states is an invaluable clue to the un­derstanding of dynamic processes in organisms. Applied to metabolite concentration data, the proposed method was able to identify states which were not found with conventional techniques for threshold extraction. A second approach exploits the structure of sets of decision trees for the discovery of com­binatorial dependencies between attributes. Previous work on this issue has focused either on expensive computational methods or the interpretation of single decision trees ­ a very limited exploitation of the data. This has led to incomplete or unstable results. That is why a new method is developed that uses sets of decision trees to overcome these limitations. Both the introduced methods are available as software tools. They can be applied consecu­tively or separately. That way they make up a package of analytical tools that usefully supplement existing methods. By means of these tools, the newly introduced methods were able to confirm existing knowl­edge and to suggest interesting and new relationships between metabolites.},
  subject      = {Molekulare Bioinformatik},
  language  = {en}
}
@phdthesis{Hagedorn2016,
  author    = {Hagedorn, Benjamin},
  title     = {Konzepte und Techniken zur servicebasierten Visualisierung von geovirtuellen 3D-Umgebungen},
  school      = {Universit{\"a}t Potsdam},
  pages     = {140},
  year      = {2016},
  language  = {de}
}
@phdthesis{Semmo2016,
  author    = {Semmo, Amir},
  title     = {Design and implementation of non-photorealistic rendering techniques for 3D geospatial data},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-99525},
  school      = {Universit{\"a}t Potsdam},
  pages     = {XVI, 155},
  year      = {2016},
  abstract  = {Geospatial data has become a natural part of a growing number of information systems and services in the economy, society, and people's personal lives. In particular, virtual 3D city and landscape models constitute valuable information sources within a wide variety of applications such as urban planning, navigation, tourist information, and disaster management. Today, these models are often visualized in detail to provide realistic imagery. However, a photorealistic rendering does not automatically lead to high image quality, with respect to an effective information transfer, which requires important or prioritized information to be interactively highlighted in a context-dependent manner. Approaches in non-photorealistic renderings particularly consider a user's task and camera perspective when attempting optimal expression, recognition, and communication of important or prioritized information. However, the design and implementation of non-photorealistic rendering techniques for 3D geospatial data pose a number of challenges, especially when inherently complex geometry, appearance, and thematic data must be processed interactively. Hence, a promising technical foundation is established by the programmable and parallel computing architecture of graphics processing units. This thesis proposes non-photorealistic rendering techniques that enable both the computation and selection of the abstraction level of 3D geospatial model contents according to user interaction and dynamically changing thematic information. To achieve this goal, the techniques integrate with hardware-accelerated rendering pipelines using shader technologies of graphics processing units for real-time image synthesis. The techniques employ principles of artistic rendering, cartographic generalization, and 3D semiotics—unlike photorealistic rendering—to synthesize illustrative renditions of geospatial feature type entities such as water surfaces, buildings, and infrastructure networks. In addition, this thesis contributes a generic system that enables to integrate different graphic styles—photorealistic and non-photorealistic—and provide their seamless transition according to user tasks, camera view, and image resolution. Evaluations of the proposed techniques have demonstrated their significance to the field of geospatial information visualization including topics such as spatial perception, cognition, and mapping. In addition, the applications in illustrative and focus+context visualization have reflected their potential impact on optimizing the information transfer regarding factors such as cognitive load, integration of non-realistic information, visualization of uncertainty, and visualization on small displays.},
  language  = {en}
}
@phdthesis{Kyprianidis2013,
  author    = {Kyprianidis, Jan Eric},
  title     = {Structure adaptive stylization of images and video},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64104},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {In the early days of computer graphics, research was mainly driven by the goal to create realistic synthetic imagery. By contrast, non-photorealistic computer graphics, established as its own branch of computer graphics in the early 1990s, is mainly motivated by concepts and principles found in traditional art forms, such as painting, illustration, and graphic design, and it investigates concepts and techniques that abstract from reality using expressive, stylized, or illustrative rendering techniques. This thesis focuses on the artistic stylization of two-dimensional content and presents several novel automatic techniques for the creation of simplified stylistic illustrations from color images, video, and 3D renderings. Primary innovation of these novel techniques is that they utilize the smooth structure tensor as a simple and efficient way to obtain information about the local structure of an image. More specifically, this thesis contributes to knowledge in this field in the following ways. First, a comprehensive review of the structure tensor is provided. In particular, different methods for integrating the minor eigenvector field of the smoothed structure tensor are developed, and the superiority of the smoothed structure tensor over the popular edge tangent flow is demonstrated. Second, separable implementations of the popular bilateral and difference of Gaussians filters that adapt to the local structure are presented. These filters avoid artifacts while being computationally highly efficient. Taken together, both provide an effective way to create a cartoon-style effect. Third, a generalization of the Kuwahara filter is presented that avoids artifacts by adapting the shape, scale, and orientation of the filter to the local structure. This causes directional image features to be better preserved and emphasized, resulting in overall sharper edges and a more feature-abiding painterly effect. In addition to the single-scale variant, a multi-scale variant is presented, which is capable of performing a highly aggressive abstraction. Fourth, a technique that builds upon the idea of combining flow-guided smoothing with shock filtering is presented, allowing for an aggressive exaggeration and an emphasis of directional image features. All presented techniques are suitable for temporally coherent per-frame filtering of video or dynamic 3D renderings, without requiring expensive extra processing, such as optical flow. Moreover, they can be efficiently implemented to process content in real-time on a GPU.},
  language  = {en}
}
@phdthesis{Prohaska2007,
  author    = {Prohaska, Steffen},
  title     = {Skeleton-based visualization of massive voxel objects with network-like architecture},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-14888},
  school      = {Universit{\"a}t Potsdam},
  year      = {2007},
  abstract  = {This work introduces novel internal and external memory algorithms for computing voxel skeletons of massive voxel objects with complex network-like architecture and for converting these voxel skeletons to piecewise linear geometry, that is triangle meshes and piecewise straight lines. The presented techniques help to tackle the challenge of visualizing and analyzing 3d images of increasing size and complexity, which are becoming more and more important in, for example, biological and medical research. Section 2.3.1 contributes to the theoretical foundations of thinning algorithms with a discussion of homotopic thinning in the grid cell model. The grid cell model explicitly represents a cell complex built of faces, edges, and vertices shared between voxels. A characterization of pairs of cells to be deleted is much simpler than characterizations of simple voxels were before. The grid cell model resolves topologically unclear voxel configurations at junctions and locked voxel configurations causing, for example, interior voxels in sets of non-simple voxels. A general conclusion is that the grid cell model is superior to indecomposable voxels for algorithms that need detailed control of topology. Section 2.3.2 introduces a noise-insensitive measure based on the geodesic distance along the boundary to compute two-dimensional skeletons. The measure is able to retain thin object structures if they are geometrically important while ignoring noise on the object's boundary. This combination of properties is not known of other measures. The measure is also used to guide erosion in a thinning process from the boundary towards lines centered within plate-like structures. Geodesic distance based quantities seem to be well suited to robustly identify one- and two-dimensional skeletons. Chapter 6 applies the method to visualization of bone micro-architecture. Chapter 3 describes a novel geometry generation scheme for representing voxel skeletons, which retracts voxel skeletons to piecewise linear geometry per dual cube. The generated triangle meshes and graphs provide a link to geometry processing and efficient rendering of voxel skeletons. The scheme creates non-closed surfaces with boundaries, which contain fewer triangles than a representation of voxel skeletons using closed surfaces like small cubes or iso-surfaces. A conclusion is that thinking specifically about voxel skeleton configurations instead of generic voxel configurations helps to deal with the topological implications. The geometry generation is one foundation of the applications presented in Chapter 6. Chapter 5 presents a novel external memory algorithm for distance ordered homotopic thinning. The presented method extends known algorithms for computing chamfer distance transformations and thinning to execute I/O-efficiently when input is larger than the available main memory. The applied block-wise decomposition schemes are quite simple. Yet it was necessary to carefully analyze effects of block boundaries to devise globally correct external memory variants of known algorithms. In general, doing so is superior to naive block-wise processing ignoring boundary effects. Chapter 6 applies the algorithms in a novel method based on confocal microscopy for quantitative study of micro-vascular networks in the field of microcirculation.},
  language  = {en}
}
@phdthesis{AbdelwahabHusseinAbdelwahabElsayed2019,
  author    = {Abdelwahab Hussein Abdelwahab Elsayed, Ahmed},
  title     = {Probabilistic, deep, and metric learning for biometric identification from eye movements},
  doi       = {10.25932/publishup-46798},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-467980},
  school      = {Universit{\"a}t Potsdam},
  pages     = {vi, 65},
  year      = {2019},
  abstract  = {A central insight from psychological studies on human eye movements is that eye movement patterns are highly individually characteristic. They can, therefore, be used as a biometric feature, that is, subjects can be identified based on their eye movements. This thesis introduces new machine learning methods to identify subjects based on their eye movements while viewing arbitrary content. The thesis focuses on probabilistic modeling of the problem, which has yielded the best results in the most recent literature. The thesis studies the problem in three phases by proposing a purely probabilistic, probabilistic deep learning, and probabilistic deep metric learning approach. In the first phase, the thesis studies models that rely on psychological concepts about eye movements. Recent literature illustrates that individual-specific distributions of gaze patterns can be used to accurately identify individuals. In these studies, models were based on a simple parametric family of distributions. Such simple parametric models can be robustly estimated from sparse data, but have limited flexibility to capture the differences between individuals. Therefore, this thesis proposes a semiparametric model of gaze patterns that is flexible yet robust for individual identification. These patterns can be understood as domain knowledge derived from psychological literature. Fixations and saccades are examples of simple gaze patterns. The proposed semiparametric densities are drawn under a Gaussian process prior centered at a simple parametric distribution. Thus, the model will stay close to the parametric class of densities if little data is available, but it can also deviate from this class if enough data is available, increasing the flexibility of the model. The proposed method is evaluated on a large-scale dataset, showing significant improvements over the state-of-the-art. Later, the thesis replaces the model based on gaze patterns derived from psychological concepts with a deep neural network that can learn more informative and complex patterns from raw eye movement data. As previous work has shown that the distribution of these patterns across a sequence is informative, a novel statistical aggregation layer called the quantile layer is introduced. It explicitly fits the distribution of deep patterns learned directly from the raw eye movement data. The proposed deep learning approach is end-to-end learnable, such that the deep model learns to extract informative, short local patterns while the quantile layer learns to approximate the distributions of these patterns. Quantile layers are a generic approach that can converge to standard pooling layers or have a more detailed description of the features being pooled, depending on the problem. The proposed model is evaluated in a large-scale study using the eye movements of subjects viewing arbitrary visual input. The model improves upon the standard pooling layers and other statistical aggregation layers proposed in the literature. It also improves upon the state-of-the-art eye movement biometrics by a wide margin. Finally, for the model to identify any subject — not just the set of subjects it is trained on — a metric learning approach is developed. Metric learning learns a distance function over instances. The metric learning model maps the instances into a metric space, where sequences of the same individual are close, and sequences of different individuals are further apart. This thesis introduces a deep metric learning approach with distributional embeddings. The approach represents sequences as a set of continuous distributions in a metric space; to achieve this, a new loss function based on Wasserstein distances is introduced. The proposed method is evaluated on multiple domains besides eye movement biometrics. This approach outperforms the state of the art in deep metric learning in several domains while also outperforming the state of the art in eye movement biometrics.},
  language  = {en}
}
@phdthesis{Yang2013,
  author    = {Yang, Haojin},
  title     = {Automatic video indexing and retrieval using video ocr technology},
  address   = {Potsdam},
  pages     = {182 S.},
  year      = {2013},
  language  = {en}
}