@phdthesis{Reinke2003,
author = {Reinke, Thomas},
title = {Architekturbasierte Konstruktion von Multiagentensystemen},
pages = {166 S.},
year = {2003},
language = {de}
}
@phdthesis{Otscheretnij2003,
author = {Otscheretnij, Vitalij},
title = {Entwurf von fehlertoleranten kompinatorischen Schaltungen},
pages = {80 S.},
year = {2003},
language = {de}
}
@phdthesis{Dmitriev2003,
author = {Dmitriev, Alexej},
title = {Anwendung alternierender Signale zum Entwurf von Fehlererkennungsschaltungen und Kompaktoren},
pages = {97 S.},
year = {2003},
language = {de}
}
@phdthesis{Frank2003,
author = {Frank, Keller},
title = {{\"U}ber die Rolle von Architekturbeschreibungen im Software-Entwicklungsprozess},
pages = {X, 160 S. : graph. Darst.},
year = {2003},
language = {de}
}
@phdthesis{Raetsch2001,
author = {R{\"a}tsch, Gunnar},
title = {Robust boosting via convex optimization},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-0000399},
school = {Universit{\"a}t Potsdam},
year = {2001},
abstract = {In dieser Arbeit werden statistische Lernprobleme betrachtet. Lernmaschinen extrahieren Informationen aus einer gegebenen Menge von Trainingsmustern, so daß sie in der Lage sind, Eigenschaften von bisher ungesehenen Mustern - z.B. eine Klassenzugeh{\"o}rigkeit - vorherzusagen. Wir betrachten den Fall, bei dem die resultierende Klassifikations- oder Regressionsregel aus einfachen Regeln - den Basishypothesen - zusammengesetzt ist. Die sogenannten Boosting Algorithmen erzeugen iterativ eine gewichtete Summe von Basishypothesen, die gut auf ungesehenen Mustern vorhersagen. Die Arbeit behandelt folgende Sachverhalte: o Die zur Analyse von Boosting-Methoden geeignete Statistische Lerntheorie. Wir studieren lerntheoretische Garantien zur Absch{\"a}tzung der Vorhersagequalit{\"a}t auf ungesehenen Mustern. K{\"u}rzlich haben sich sogenannte Klassifikationstechniken mit großem Margin als ein praktisches Ergebnis dieser Theorie herausgestellt - insbesondere Boosting und Support-Vektor-Maschinen. Ein großer Margin impliziert eine hohe Vorhersagequalit{\"a}t der Entscheidungsregel. Deshalb wird analysiert, wie groß der Margin bei Boosting ist und ein verbesserter Algorithmus vorgeschlagen, der effizient Regeln mit maximalem Margin erzeugt. o Was ist der Zusammenhang von Boosting und Techniken der konvexen Optimierung? Um die Eigenschaften der entstehenden Klassifikations- oder Regressionsregeln zu analysieren, ist es sehr wichtig zu verstehen, ob und unter welchen Bedingungen iterative Algorithmen wie Boosting konvergieren. Wir zeigen, daß solche Algorithmen benutzt werden koennen, um sehr große Optimierungsprobleme mit Nebenbedingungen zu l{\"o}sen, deren L{\"o}sung sich gut charakterisieren laesst. Dazu werden Verbindungen zum Wissenschaftsgebiet der konvexen Optimierung aufgezeigt und ausgenutzt, um Konvergenzgarantien f{\"u}r eine große Familie von Boosting-{\"a}hnlichen Algorithmen zu geben. o Kann man Boosting robust gegen{\"u}ber Meßfehlern und Ausreissern in den Daten machen? Ein Problem bisheriger Boosting-Methoden ist die relativ hohe Sensitivit{\"a}t gegen{\"u}ber Messungenauigkeiten und Meßfehlern in der Trainingsdatenmenge. Um dieses Problem zu beheben, wird die sogenannte 'Soft-Margin' Idee, die beim Support-Vector Lernen schon benutzt wird, auf Boosting {\"u}bertragen. Das f{\"u}hrt zu theoretisch gut motivierten, regularisierten Algorithmen, die ein hohes Maß an Robustheit aufweisen. o Wie kann man die Anwendbarkeit von Boosting auf Regressionsprobleme erweitern? Boosting-Methoden wurden urspr{\"u}nglich f{\"u}r Klassifikationsprobleme entwickelt. Um die Anwendbarkeit auf Regressionsprobleme zu erweitern, werden die vorherigen Konvergenzresultate benutzt und neue Boosting-{\"a}hnliche Algorithmen zur Regression entwickelt. Wir zeigen, daß diese Algorithmen gute theoretische und praktische Eigenschaften haben. o Ist Boosting praktisch anwendbar? Die dargestellten theoretischen Ergebnisse werden begleitet von Simulationsergebnissen, entweder, um bestimmte Eigenschaften von Algorithmen zu illustrieren, oder um zu zeigen, daß sie in der Praxis tats{\"a}chlich gut funktionieren und direkt einsetzbar sind. Die praktische Relevanz der entwickelten Methoden wird in der Analyse chaotischer Zeitreihen und durch industrielle Anwendungen wie ein Stromverbrauch-{\"U}berwachungssystem und bei der Entwicklung neuer Medikamente illustriert.},
language = {en}
}
@phdthesis{Dornhege2006,
author = {Dornhege, Guido},
title = {Increasing information transfer rates for brain-computer interfacing},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-7690},
school = {Universit{\"a}t Potsdam},
year = {2006},
abstract = {The goal of a Brain-Computer Interface (BCI) consists of the development of a unidirectional interface between a human and a computer to allow control of a device only via brain signals. While the BCI systems of almost all other groups require the user to be trained over several weeks or even months, the group of Prof. Dr. Klaus-Robert M{\"u}ller in Berlin and Potsdam, which I belong to, was one of the first research groups in this field which used machine learning techniques on a large scale. The adaptivity of the processing system to the individual brain patterns of the subject confers huge advantages for the user. Thus BCI research is considered a hot topic in machine learning and computer science. It requires interdisciplinary cooperation between disparate fields such as neuroscience, since only by combining machine learning and signal processing techniques based on neurophysiological knowledge will the largest progress be made. In this work I particularly deal with my part of this project, which lies mainly in the area of computer science. I have considered the following three main points: Establishing a performance measure based on information theory: I have critically illuminated the assumptions of Shannon's information transfer rate for application in a BCI context. By establishing suitable coding strategies I was able to show that this theoretical measure approximates quite well to what is practically achieveable. Transfer and development of suitable signal processing and machine learning techniques: One substantial component of my work was to develop several machine learning and signal processing algorithms to improve the efficiency of a BCI. Based on the neurophysiological knowledge that several independent EEG features can be observed for some mental states, I have developed a method for combining different and maybe independent features which improved performance. In some cases the performance of the combination algorithm outperforms the best single performance by more than 50 \%. Furthermore, I have theoretically and practically addressed via the development of suitable algorithms the question of the optimal number of classes which should be used for a BCI. It transpired that with BCI performances reported so far, three or four different mental states are optimal. For another extension I have combined ideas from signal processing with those of machine learning since a high gain can be achieved if the temporal filtering, i.e., the choice of frequency bands, is automatically adapted to each subject individually. Implementation of the Berlin brain computer interface and realization of suitable experiments: Finally a further substantial component of my work was to realize an online BCI system which includes the developed methods, but is also flexible enough to allow the simple realization of new algorithms and ideas. So far, bitrates of up to 40 bits per minute have been achieved with this system by absolutely untrained users which, compared to results of other groups, is highly successful.},
subject = {Kybernetik},
language = {en}
}
@phdthesis{Scholz2006,
author = {Scholz, Matthias},
title = {Approaches to analyse and interpret biological profile data},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-7839},
school = {Universit{\"a}t Potsdam},
year = {2006},
abstract = {Advances in biotechnologies rapidly increase the number of molecules of a cell which can be observed simultaneously. This includes expression levels of thousands or ten-thousands of genes as well as concentration levels of metabolites or proteins. Such Profile data, observed at different times or at different experimental conditions (e.g., heat or dry stress), show how the biological experiment is reflected on the molecular level. This information is helpful to understand the molecular behaviour and to identify molecules or combination of molecules that characterise specific biological condition (e.g., disease). This work shows the potentials of component extraction algorithms to identify the major factors which influenced the observed data. This can be the expected experimental factors such as the time or temperature as well as unexpected factors such as technical artefacts or even unknown biological behaviour. Extracting components means to reduce the very high-dimensional data to a small set of new variables termed components. Each component is a combination of all original variables. The classical approach for that purpose is the principal component analysis (PCA). It is shown that, in contrast to PCA which maximises the variance only, modern approaches such as independent component analysis (ICA) are more suitable for analysing molecular data. The condition of independence between components of ICA fits more naturally our assumption of individual (independent) factors which influence the data. This higher potential of ICA is demonstrated by a crossing experiment of the model plant Arabidopsis thaliana (Thale Cress). The experimental factors could be well identified and, in addition, ICA could even detect a technical artefact. However, in continuously observations such as in time experiments, the data show, in general, a nonlinear distribution. To analyse such nonlinear data, a nonlinear extension of PCA is used. This nonlinear PCA (NLPCA) is based on a neural network algorithm. The algorithm is adapted to be applicable to incomplete molecular data sets. Thus, it provides also the ability to estimate the missing data. The potential of nonlinear PCA to identify nonlinear factors is demonstrated by a cold stress experiment of Arabidopsis thaliana. The results of component analysis can be used to build a molecular network model. Since it includes functional dependencies it is termed functional network. Applied to the cold stress data, it is shown that functional networks are appropriate to visualise biological processes and thereby reveals molecular dynamics.},
subject = {Bioinformatik},
language = {en}
}
@phdthesis{Weigend2007,
author = {Weigend, Michael},
title = {Intuitive Modelle der Informatik},
publisher = {Universit{\"a}tsverlag Potsdam},
address = {Potsdam},
isbn = {978-3-940793-08-9},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-15787},
school = {Universit{\"a}t Potsdam},
pages = {331},
year = {2007},
abstract = {Intuitive Modelle der Informatik sind gedankliche Vorstellungen {\"u}ber informatische Konzepte, die mit subjektiver Gewissheit verbunden sind. Menschen verwenden sie, wenn sie die Arbeitsweise von Computerprogrammen nachvollziehen oder anderen erkl{\"a}ren, die logische Korrektheit eines Programms pr{\"u}fen oder in einem kreativen Prozess selbst Programme entwickeln. Intuitive Modelle k{\"o}nnen auf verschiedene Weise repr{\"a}sentiert und kommuniziert werden, etwa verbal-abstrakt, durch ablauf- oder strukturorientierte Abbildungen und Filme oder konkrete Beispiele. Diskutiert werden in dieser Arbeit grundlegende intuitive Modelle f{\"u}r folgende inhaltliche Aspekte einer Programmausf{\"u}hrung: Allokation von Aktivit{\"a}t bei einer Programmausf{\"u}hrung, Benennung von Entit{\"a}ten, Daten, Funktionen, Verarbeitung, Kontrollstrukturen zur Steuerung von Programml{\"a}ufen, Rekursion, Klassen und Objekte. Mit Hilfe eines Systems von Online-Spielen, der Python Visual Sandbox, werden die psychische Realit{\"a}t verschiedener intuitiver Modelle bei Programmieranf{\"a}ngern nachgewiesen und fehlerhafte Anwendungen (Fehlvorstellungen) identifiziert.},
language = {de}
}
@phdthesis{Blum2010,
author = {Blum, Niklas},
title = {Formalization of a converged internet and telecommunications service environment},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-51146},
school = {Universit{\"a}t Potsdam},
year = {2010},
abstract = {The programmable network envisioned in the 1990s within standardization and research for the Intelligent Network is currently coming into reality using IPbased Next Generation Networks (NGN) and applying Service-Oriented Architecture (SOA) principles for service creation, execution, and hosting. SOA is the foundation for both next-generation telecommunications and middleware architectures, which are rapidly converging on top of commodity transport services. Services such as triple/quadruple play, multimedia messaging, and presence are enabled by the emerging service-oriented IPMultimedia Subsystem (IMS), and allow telecommunications service providers to maintain, if not improve, their position in the marketplace. SOA becomes the de facto standard in next-generation middleware systems as the system model of choice to interconnect service consumers and providers within and between enterprises. We leverage previous research activities in overlay networking technologies along with recent advances in network abstraction, service exposure, and service creation to develop a paradigm for a service environment providing converged Internet and Telecommunications services that we call Service Broker. Such a Service Broker provides mechanisms to combine and mediate between different service paradigms from the two domains Internet/WWW and telecommunications. Furthermore, it enables the composition of services across these domains and is capable of defining and applying temporal constraints during creation and execution time. By adding network-awareness into the service fabric, such a Service Broker may also act as a next generation network-to-service element allowing the composition of crossdomain and cross-layer network and service resources. The contribution of this research is threefold: first, we analyze and classify principles and technologies from Information Technologies (IT) and telecommunications to identify and discuss issues allowing cross-domain composition in a converging service layer. Second, we discuss service composition methods allowing the creation of converged services on an abstract level; in particular, we present a formalized method for model-checking of such compositions. Finally, we propose a Service Broker architecture converging Internet and Telecom services. This environment enables cross-domain feature interaction in services through formalized obligation policies acting as constraints during service discovery, creation, and execution time.},
language = {en}
}
@phdthesis{Brauer2010,
author = {Brauer, Falk},
title = {Extraktion und Identifikation von Entit{\"a}ten in Textdaten im Umfeld der Enterprise Search},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-51409},
school = {Universit{\"a}t Potsdam},
year = {2010},
abstract = {Die automatische Informationsextraktion (IE) aus unstrukturierten Texten erm{\"o}glicht v{\"o}llig neue Wege, auf relevante Informationen zuzugreifen und deren Inhalte zu analysieren, die weit {\"u}ber bisherige Verfahren zur Stichwort-basierten Dokumentsuche hinausgehen. Die Entwicklung von Programmen zur Extraktion von maschinenlesbaren Daten aus Texten erfordert jedoch nach wie vor die Entwicklung von dom{\"a}nenspezifischen Extraktionsprogrammen. Insbesondere im Bereich der Enterprise Search (der Informationssuche im Unternehmensumfeld), in dem eine große Menge von heterogenen Dokumenttypen existiert, ist es oft notwendig ad-hoc Programm-module zur Extraktion von gesch{\"a}ftsrelevanten Entit{\"a}ten zu entwickeln, die mit generischen Modulen in monolithischen IE-Systemen kombiniert werden. Dieser Umstand ist insbesondere kritisch, da potentiell f{\"u}r jeden einzelnen Anwendungsfall ein von Grund auf neues IE-System entwickelt werden muss. Die vorliegende Dissertation untersucht die effiziente Entwicklung und Ausf{\"u}hrung von IE-Systemen im Kontext der Enterprise Search und effektive Methoden zur Ausnutzung bekannter strukturierter Daten im Unternehmenskontext f{\"u}r die Extraktion und Identifikation von gesch{\"a}ftsrelevanten Entit{\"a}ten in Doku-menten. Grundlage der Arbeit ist eine neuartige Plattform zur Komposition von IE-Systemen auf Basis der Beschreibung des Datenflusses zwischen generischen und anwendungsspezifischen IE-Modulen. Die Plattform unterst{\"u}tzt insbesondere die Entwicklung und Wiederverwendung von generischen IE-Modulen und zeichnet sich durch eine h{\"o}here Flexibilit{\"a}t und Ausdrucksm{\"a}chtigkeit im Vergleich zu vorherigen Methoden aus. Ein in der Dissertation entwickeltes Verfahren zur Dokumentverarbeitung interpretiert den Daten-austausch zwischen IE-Modulen als Datenstr{\"o}me und erm{\"o}glicht damit eine weitgehende Parallelisierung von einzelnen Modulen. Die autonome Ausf{\"u}hrung der Module f{\"u}hrt zu einer wesentlichen Beschleu-nigung der Verarbeitung von Einzeldokumenten und verbesserten Antwortzeiten, z. B. f{\"u}r Extraktions-dienste. Bisherige Ans{\"a}tze untersuchen lediglich die Steigerung des durchschnittlichen Dokumenten-durchsatzes durch verteilte Ausf{\"u}hrung von Instanzen eines IE-Systems. Die Informationsextraktion im Kontext der Enterprise Search unterscheidet sich z. B. von der Extraktion aus dem World Wide Web dadurch, dass in der Regel strukturierte Referenzdaten z. B. in Form von Unternehmensdatenbanken oder Terminologien zur Verf{\"u}gung stehen, die oft auch die Beziehungen von Entit{\"a}ten beschreiben. Entit{\"a}ten im Unternehmensumfeld haben weiterhin bestimmte Charakteristiken: Eine Klasse von relevanten Entit{\"a}ten folgt bestimmten Bildungsvorschriften, die nicht immer bekannt sind, auf die aber mit Hilfe von bekannten Beispielentit{\"a}ten geschlossen werden kann, so dass unbekannte Entit{\"a}ten extrahiert werden k{\"o}nnen. Die Bezeichner der anderen Klasse von Entit{\"a}ten haben eher umschreibenden Charakter. Die korrespondierenden Umschreibungen in Texten k{\"o}nnen variieren, wodurch eine Identifikation derartiger Entit{\"a}ten oft erschwert wird. Zur effizienteren Entwicklung von IE-Systemen wird in der Dissertation ein Verfahren untersucht, das alleine anhand von Beispielentit{\"a}ten effektive Regul{\"a}re Ausdr{\"u}cke zur Extraktion von unbekannten Entit{\"a}ten erlernt und damit den manuellen Aufwand in derartigen Anwendungsf{\"a}llen minimiert. Verschiedene Generalisierungs- und Spezialisierungsheuristiken erkennen Muster auf verschiedenen Abstraktionsebenen und schaffen dadurch einen Ausgleich zwischen Genauigkeit und Vollst{\"a}ndigkeit bei der Extraktion. Bekannte Regellernverfahren im Bereich der Informationsextraktion unterst{\"u}tzen die beschriebenen Problemstellungen nicht, sondern ben{\"o}tigen einen (annotierten) Dokumentenkorpus. Eine Methode zur Identifikation von Entit{\"a}ten, die durch Graph-strukturierte Referenzdaten vordefiniert sind, wird als dritter Schwerpunkt untersucht. Es werden Verfahren konzipiert, welche {\"u}ber einen exakten Zeichenkettenvergleich zwischen Text und Referenzdatensatz hinausgehen und Teil{\"u}bereinstimmungen und Beziehungen zwischen Entit{\"a}ten zur Identifikation und Disambiguierung heranziehen. Das in der Arbeit vorgestellte Verfahren ist bisherigen Ans{\"a}tzen hinsichtlich der Genauigkeit und Vollst{\"a}ndigkeit bei der Identifikation {\"u}berlegen.},
language = {de}
}
@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}
}