@phdthesis{Kluth2011,
  author    = {Kluth, Stephan},
  title     = {Quantitative modeling and analysis with FMC-QE},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-52987},
  school      = {Universit{\"a}t Potsdam},
  year      = {2011},
  abstract  = {The modeling and evaluation calculus FMC-QE, the Fundamental Modeling Concepts for Quanti-tative Evaluation [1], extends the Fundamental Modeling Concepts (FMC) for performance modeling and prediction. In this new methodology, the hierarchical service requests are in the main focus, because they are the origin of every service provisioning process. Similar to physics, these service requests are a tuple of value and unit, which enables hierarchical service request transformations at the hierarchical borders and therefore the hierarchical modeling. Through reducing the model complexity of the models by decomposing the system in different hierarchical views, the distinction between operational and control states and the calculation of the performance values on the assumption of the steady state, FMC-QE has a scalable applica-bility on complex systems. According to FMC, the system is modeled in a 3-dimensional hierarchical representation space, where system performance parameters are described in three arbitrarily fine-grained hierarchi-cal bipartite diagrams. The hierarchical service request structures are modeled in Entity Relationship Diagrams. The static server structures, divided into logical and real servers, are de-scribed as Block Diagrams. The dynamic behavior and the control structures are specified as Petri Nets, more precisely Colored Time Augmented Petri Nets. From the structures and pa-rameters of the performance model, a hierarchical set of equations is derived. The calculation of the performance values is done on the assumption of stationary processes and is based on fundamental laws of the performance analysis: Little's Law and the Forced Traffic Flow Law. Little's Law is used within the different hierarchical levels (horizontal) and the Forced Traffic Flow Law is the key to the dependencies among the hierarchical levels (vertical). This calculation is suitable for complex models and allows a fast (re-)calculation of different performance scenarios in order to support development and configuration decisions. Within the Research Group Zorn at the Hasso Plattner Institute, the work is embedded in a broader research in the development of FMC-QE. While this work is concentrated on the theoretical background, description and definition of the methodology as well as the extension and validation of the applicability, other topics are in the development of an FMC-QE modeling and evaluation tool and the usage of FMC-QE in the design of an adaptive transport layer in order to fulfill Quality of Service and Service Level Agreements in volatile service based environments. This thesis contains a state-of-the-art, the description of FMC-QE as well as extensions of FMC-QE in representative general models and case studies. In the state-of-the-art part of the thesis in chapter 2, an overview on existing Queueing Theory and Time Augmented Petri Net models and other quantitative modeling and evaluation languages and methodologies is given. Also other hierarchical quantitative modeling frameworks will be considered. The description of FMC-QE in chapter 3 consists of a summary of the foundations of FMC-QE, basic definitions, the graphical notations, the FMC-QE Calculus and the modeling of open queueing networks as an introductory example. The extensions of FMC-QE in chapter 4 consist of the integration of the summation method in order to support the handling of closed networks and the modeling of multiclass and semaphore scenarios. Furthermore, FMC-QE is compared to other performance modeling and evaluation approaches. In the case study part in chapter 5, proof-of-concept examples, like the modeling of a service based search portal, a service based SAP NetWeaver application and the Axis2 Web service framework will be provided. Finally, conclusions are given by a summary of contributions and an outlook on future work in chapter 6. [1] Werner Zorn. FMC-QE - A New Approach in Quantitative Modeling. In Hamid R. Arabnia, editor, Procee-dings of the International Conference on Modeling, Simulation and Visualization Methods (MSV 2007) within WorldComp '07, pages 280 - 287, Las Vegas, NV, USA, June 2007. CSREA Press. ISBN 1-60132-029-9.},
  language  = {en}
}
@phdthesis{Ahmad2014,
  author    = {Ahmad, Nadeem},
  title     = {People centered HMI's for deaf and functionally illiterate users},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-70391},
  school      = {Universit{\"a}t Potsdam},
  year      = {2014},
  abstract  = {The objective and motivation behind this research is to provide applications with easy-to-use interfaces to communities of deaf and functionally illiterate users, which enables them to work without any human assistance. Although recent years have witnessed technological advancements, the availability of technology does not ensure accessibility to information and communication technologies (ICT). Extensive use of text from menus to document contents means that deaf or functionally illiterate can not access services implemented on most computer software. Consequently, most existing computer applications pose an accessibility barrier to those who are unable to read fluently. Online technologies intended for such groups should be developed in continuous partnership with primary users and include a thorough investigation into their limitations, requirements and usability barriers. In this research, I investigated existing tools in voice, web and other multimedia technologies to identify learning gaps and explored ways to enhance the information literacy for deaf and functionally illiterate users. I worked on the development of user-centered interfaces to increase the capabilities of deaf and low literacy users by enhancing lexical resources and by evaluating several multimedia interfaces for them. The interface of the platform-independent Italian Sign Language (LIS) Dictionary has been developed to enhance the lexical resources for deaf users. The Sign Language Dictionary accepts Italian lemmas as input and provides their representation in the Italian Sign Language as output. The Sign Language dictionary has 3082 signs as set of Avatar animations in which each sign is linked to a corresponding Italian lemma. I integrated the LIS lexical resources with MultiWordNet (MWN) database to form the first LIS MultiWordNet(LMWN). LMWN contains information about lexical relations between words, semantic relations between lexical concepts (synsets), correspondences between Italian and sign language lexical concepts and semantic fields (domains). The approach enhances the deaf users' understanding of written Italian language and shows that a relatively small set of lexicon can cover a significant portion of MWN. Integration of LIS signs with MWN made it useful tool for computational linguistics and natural language processing. The rule-based translation process from written Italian text to LIS has been transformed into service-oriented system. The translation process is composed of various modules including parser, semantic interpreter, generator, and spatial allocation planner. This translation procedure has been implemented in the Java Application Building Center (jABC), which is a framework for extreme model driven design (XMDD). The XMDD approach focuses on bringing software development closer to conceptual design, so that the functionality of a software solution could be understood by someone who is unfamiliar with programming concepts. The transformation addresses the heterogeneity challenge and enhances the re-usability of the system. For enhancing the e-participation of functionally illiterate users, two detailed studies were conducted in the Republic of Rwanda. In the first study, the traditional (textual) interface was compared with the virtual character-based interactive interface. The study helped to identify usability barriers and users evaluated these interfaces according to three fundamental areas of usability, i.e. effectiveness, efficiency and satisfaction. In another study, we developed four different interfaces to analyze the usability and effects of online assistance (consistent help) for functionally illiterate users and compared different help modes including textual, vocal and virtual character on the performance of semi-literate users. In our newly designed interfaces the instructions were automatically translated in Swahili language. All the interfaces were evaluated on the basis of task accomplishment, time consumption, System Usability Scale (SUS) rating and number of times the help was acquired. The results show that the performance of semi-literate users improved significantly when using the online assistance. The dissertation thus introduces a new development approach in which virtual characters are used as additional support for barely literate or naturally challenged users. Such components enhanced the application utility by offering a variety of services like translating contents in local language, providing additional vocal information, and performing automatic translation from text to sign language. Obviously, there is no such thing as one design solution that fits for all in the underlying domain. Context sensitivity, literacy and mental abilities are key factors on which I concentrated and the results emphasize that computer interfaces must be based on a thoughtful definition of target groups, purposes and objectives.},
  language  = {en}
}
@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: <b>Establishing a performance measure based on information theory:</b> 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. <b>Transfer and development of suitable signal processing and machine learning techniques:</b> 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. <b>Implementation of the Berlin brain computer interface and realization of suitable experiments:</b> 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{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{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}
}