@phdthesis{Alnemr2011,
  author    = {Alnemr, Rehab},
  title     = {Reputation object representation model for enabling reputation interoperability},
  address   = {Potsdam},
  pages     = {179 S.},
  year      = {2011},
  language  = {en}
}
@phdthesis{Schuenemann2011,
  author    = {Sch{\"u}nemann, Bj{\"o}rn},
  title     = {The V2X simulation runtime infrastructure: VSimRTI},
  address   = {Potsdam},
  pages     = {163 S.},
  year      = {2011},
  language  = {en}
}
@phdthesis{Richter2011,
  author    = {Richter, Michael},
  title     = {Anwendung nichtlinearer Codes zur Fehlererkennung und -korrektur},
  address   = {Potsdam},
  pages     = {134 S.},
  year      = {2011},
  language  = {de}
}
@phdthesis{Smirnov2011,
  author    = {Smirnov, Sergey},
  title     = {Business process model abstraction},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-60258},
  school      = {Universit{\"a}t Potsdam},
  year      = {2011},
  abstract  = {Business process models are used within a range of organizational initiatives, where every stakeholder has a unique perspective on a process and demands the respective model. As a consequence, multiple process models capturing the very same business process coexist. Keeping such models in sync is a challenge within an ever changing business environment: once a process is changed, all its models have to be updated. Due to a large number of models and their complex relations, model maintenance becomes error-prone and expensive. Against this background, business process model abstraction emerged as an operation reducing the number of stored process models and facilitating model management. Business process model abstraction is an operation preserving essential process properties and leaving out insignificant details in order to retain information relevant for a particular purpose. Process model abstraction has been addressed by several researchers. The focus of their studies has been on particular use cases and model transformations supporting these use cases. This thesis systematically approaches the problem of business process model abstraction shaping the outcome into a framework. We investigate the current industry demand in abstraction summarizing it in a catalog of business process model abstraction use cases. The thesis focuses on one prominent use case where the user demands a model with coarse-grained activities and overall process ordering constraints. We develop model transformations that support this use case starting with the transformations based on process model structure analysis. Further, abstraction methods considering the semantics of process model elements are investigated. First, we suggest how semantically related activities can be discovered in process models-a barely researched challenge. The thesis validates the designed abstraction methods against sets of industrial process models and discusses the method implementation aspects. Second, we develop a novel model transformation, which combined with the related activity discovery allows flexible non-hierarchical abstraction. In this way this thesis advocates novel model transformations that facilitate business process model management and provides the foundations for innovative tool support.},
  language  = {en}
}
@phdthesis{Menzel2011,
  author    = {Menzel, Michael},
  title     = {Model-driven security in service-oriented architectures : leveraging security patterns to transform high-level security requirements to technical policies},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-59058},
  school      = {Universit{\"a}t Potsdam},
  year      = {2011},
  abstract  = {Service-oriented Architectures (SOA) facilitate the provision and orchestration of business services to enable a faster adoption to changing business demands. Web Services provide a technical foundation to implement this paradigm on the basis of XML-messaging. However, the enhanced flexibility of message-based systems comes along with new threats and risks. To face these issues, a variety of security mechanisms and approaches is supported by the Web Service specifications. The usage of these security mechanisms and protocols is configured by stating security requirements in security policies. However, security policy languages for SOA are complex and difficult to create due to the expressiveness of these languages. To facilitate and simplify the creation of security policies, this thesis presents a model-driven approach that enables the generation of complex security policies on the basis of simple security intentions. SOA architects can specify these intentions in system design models and are not required to deal with complex technical security concepts. The approach introduced in this thesis enables the enhancement of any system design modelling languages - for example FMC or BPMN - with security modelling elements. The syntax, semantics, and notion of these elements is defined by our security modelling language SecureSOA. The metamodel of this language provides extension points to enable the integration into system design modelling languages. In particular, this thesis demonstrates the enhancement of FMC block diagrams with SecureSOA. To enable the model-driven generation of security policies, a domain-independent policy model is introduced in this thesis. This model provides an abstraction layer for security policies. Mappings are used to perform the transformation from our model to security policy languages. However, expert knowledge is required to generate instances of this model on the basis of simple security intentions. Appropriate security mechanisms, protocols and options must be chosen and combined to fulfil these security intentions. In this thesis, a formalised system of security patterns is used to represent this knowledge and to enable an automated transformation process. Moreover, a domain-specific language is introduced to state security patterns in an accessible way. On the basis of this language, a system of security configuration patterns is provided to transform security intentions related to data protection and identity management. The formal semantics of the security pattern language enable the verification of the transformation process introduced in this thesis and prove the correctness of the pattern application. Finally, our SOA Security LAB is presented that demonstrates the application of our model-driven approach to facilitate a dynamic creation, configuration, and execution of secure Web Service-based composed applications.},
  language  = {en}
}
@phdthesis{Wang2011,
  author    = {Wang, Long},
  title     = {X-tracking the usage interest on web sites},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-51077},
  school      = {Universit{\"a}t Potsdam},
  year      = {2011},
  abstract  = {The exponential expanding of the numbers of web sites and Internet users makes WWW the most important global information resource. From information publishing and electronic commerce to entertainment and social networking, the Web allows an inexpensive and efficient access to the services provided by individuals and institutions. The basic units for distributing these services are the web sites scattered throughout the world. However, the extreme fragility of web services and content, the high competence between similar services supplied by different sites, and the wide geographic distributions of the web users drive the urgent requirement from the web managers to track and understand the usage interest of their web customers. This thesis, "X-tracking the Usage Interest on Web Sites", aims to fulfill this requirement. "X" stands two meanings: one is that the usage interest differs from various web sites, and the other is that usage interest is depicted from multi aspects: internal and external, structural and conceptual, objective and subjective. "Tracking" shows that our concentration is on locating and measuring the differences and changes among usage patterns. This thesis presents the methodologies on discovering usage interest on three kinds of web sites: the public information portal site, e-learning site that provides kinds of streaming lectures and social site that supplies the public discussions on IT issues. On different sites, we concentrate on different issues related with mining usage interest. The educational information portal sites were the first implementation scenarios on discovering usage patterns and optimizing the organization of web services. In such cases, the usage patterns are modeled as frequent page sets, navigation paths, navigation structures or graphs. However, a necessary requirement is to rebuild the individual behaviors from usage history. We give a systematic study on how to rebuild individual behaviors. Besides, this thesis shows a new strategy on building content clusters based on pair browsing retrieved from usage logs. The difference between such clusters and the original web structure displays the distance between the destinations from usage side and the expectations from design side. Moreover, we study the problem on tracking the changes of usage patterns in their life cycles. The changes are described from internal side integrating conceptual and structure features, and from external side for the physical features; and described from local side measuring the difference between two time spans, and global side showing the change tendency along the life cycle. A platform, Web-Cares, is developed to discover the usage interest, to measure the difference between usage interest and site expectation and to track the changes of usage patterns. E-learning site provides the teaching materials such as slides, recorded lecture videos and exercise sheets. We focus on discovering the learning interest on streaming lectures, such as real medias, mp4 and flash clips. Compared to the information portal site, the usage on streaming lectures encapsulates the variables such as viewing time and actions during learning processes. The learning interest is discovered in the form of answering 6 questions, which covers finding the relations between pieces of lectures and the preference among different forms of lectures. We prefer on detecting the changes of learning interest on the same course from different semesters. The differences on the content and structure between two courses leverage the changes on the learning interest. We give an algorithm on measuring the difference on learning interest integrated with similarity comparison between courses. A search engine, TASK-Moniminer, is created to help the teacher query the learning interest on their streaming lectures on tele-TASK site. Social site acts as an online community attracting web users to discuss the common topics and share their interesting information. Compared to the public information portal site and e-learning web site, the rich interactions among users and web content bring the wider range of content quality, on the other hand, provide more possibilities to express and model usage interest. We propose a framework on finding and recommending high reputation articles in a social site. We observed that the reputation is classified into global and local categories; the quality of the articles having high reputation is related with the content features. Based on these observations, our framework is implemented firstly by finding the articles having global or local reputation, and secondly clustering articles based on their content relations, and then the articles are selected and recommended from each cluster based on their reputation ranks.},
  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{Gebser2011,
  author    = {Gebser, Martin},
  title     = {Proof theory and algorithms for answer set programming},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-55425},
  school      = {Universit{\"a}t Potsdam},
  year      = {2011},
  abstract  = {Answer Set Programming (ASP) is an emerging paradigm for declarative programming, in which a computational problem is specified by a logic program such that particular models, called answer sets, match solutions. ASP faces a growing range of applications, demanding for high-performance tools able to solve complex problems. ASP integrates ideas from a variety of neighboring fields. In particular, automated techniques to search for answer sets are inspired by Boolean Satisfiability (SAT) solving approaches. While the latter have firm proof-theoretic foundations, ASP lacks formal frameworks for characterizing and comparing solving methods. Furthermore, sophisticated search patterns of modern SAT solvers, successfully applied in areas like, e.g., model checking and verification, are not yet established in ASP solving. We address these deficiencies by, for one, providing proof-theoretic frameworks that allow for characterizing, comparing, and analyzing approaches to answer set computation. For another, we devise modern ASP solving algorithms that integrate and extend state-of-the-art techniques for Boolean constraint solving. We thus contribute to the understanding of existing ASP solving approaches and their interconnections as well as to their enhancement by incorporating sophisticated search patterns. The central idea of our approach is to identify atomic as well as composite constituents of a propositional logic program with Boolean variables. This enables us to describe fundamental inference steps, and to selectively combine them in proof-theoretic characterizations of various ASP solving methods. In particular, we show that different concepts of case analyses applied by existing ASP solvers implicate mutual exponential separations regarding their best-case complexities. We also develop a generic proof-theoretic framework amenable to language extensions, and we point out that exponential separations can likewise be obtained due to case analyses on them. We further exploit fundamental inference steps to derive Boolean constraints characterizing answer sets. They enable the conception of ASP solving algorithms including search patterns of modern SAT solvers, while also allowing for direct technology transfers between the areas of ASP and SAT solving. Beyond the search for one answer set of a logic program, we address the enumeration of answer sets and their projections to a subvocabulary, respectively. The algorithms we develop enable repetition-free enumeration in polynomial space without being intrusive, i.e., they do not necessitate any modifications of computations before an answer set is found. Our approach to ASP solving is implemented in clasp, a state-of-the-art Boolean constraint solver that has successfully participated in recent solver competitions. Although we do here not address the implementation techniques of clasp or all of its features, we present the principles of its success in the context of ASP solving.},
  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{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}
}