@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{Hu2006,
  author    = {Hu, Ji},
  title     = {A virtual machine architecture for IT-security laboratories},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-7818},
  school      = {Universit{\"a}t Potsdam},
  year      = {2006},
  abstract  = {This thesis discusses challenges in IT security education, points out a gap between e-learning and practical education, and presents a work to fill the gap. E-learning is a flexible and personalized alternative to traditional education. Nonetheless, existing e-learning systems for IT security education have difficulties in delivering hands-on experience because of the lack of proximity. Laboratory environments and practical exercises are indispensable instruction tools to IT security education, but security education in conventional computer laboratories poses particular problems such as immobility as well as high creation and maintenance costs. Hence, there is a need to effectively transform security laboratories and practical exercises into e-learning forms. In this thesis, we introduce the Tele-Lab IT-Security architecture that allows students not only to learn IT security principles, but also to gain hands-on security experience by exercises in an online laboratory environment. In this architecture, virtual machines are used to provide safe user work environments instead of real computers. Thus, traditional laboratory environments can be cloned onto the Internet by software, which increases accessibility to laboratory resources and greatly reduces investment and maintenance costs. Under the Tele-Lab IT-Security framework, a set of technical solutions is also proposed to provide effective functionalities, reliability, security, and performance. The virtual machines with appropriate resource allocation, software installation, and system configurations are used to build lightweight security laboratories on a hosting computer. Reliability and availability of laboratory platforms are covered by a virtual machine management framework. This management framework provides necessary monitoring and administration services to detect and recover critical failures of virtual machines at run time. Considering the risk that virtual machines can be misused for compromising production networks, we present a security management solution to prevent the misuse of laboratory resources by security isolation at the system and network levels. This work is an attempt to bridge the gap between e-learning/tele-teaching and practical IT security education. It is not to substitute conventional teaching in laboratories but to add practical features to e-learning. This thesis demonstrates the possibility to implement hands-on security laboratories on the Internet reliably, securely, and economically.},
  subject      = {Computersicherheit},
  language  = {en}
}
@phdthesis{Ghasemzadeh2005,
  author    = {Ghasemzadeh, Mohammad},
  title     = {A new algorithm for the quantified satisfiability problem, based on zero-suppressed binary decision diagrams and memoization},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-6378},
  school      = {Universit{\"a}t Potsdam},
  year      = {2005},
  abstract  = {Quantified Boolean formulas (QBFs) play an important role in theoretical computer science. QBF extends propositional logic in such a way that many advanced forms of reasoning can be easily formulated and evaluated. In this dissertation we present our ZQSAT, which is an algorithm for evaluating quantified Boolean formulas. ZQSAT is based on ZBDD: Zero-Suppressed Binary Decision Diagram , which is a variant of BDD, and an adopted version of the DPLL algorithm. It has been implemented in C using the CUDD: Colorado University Decision Diagram package. The capability of ZBDDs in storing sets of subsets efficiently enabled us to store the clauses of a QBF very compactly and let us to embed the notion of memoization to the DPLL algorithm. These points led us to implement the search algorithm in such a way that we could store and reuse the results of all previously solved subformulas with a little overheads. ZQSAT can solve some sets of standard QBF benchmark problems (known to be hard for DPLL based algorithms) faster than the best existing solvers. In addition to prenex-CNF, ZQSAT accepts prenex-NNF formulas. We show and prove how this capability can be exponentially beneficial.},
  subject      = {Bin{\"a}res Entscheidungsdiagramm},
  language  = {en}
}
@article{Arnold2007,
  author    = {Arnold, Holger},
  title     = {A linearized DPLL calculus with learning},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-15421},
  year      = {2007},
  abstract  = {This paper describes the proof calculus LD for clausal propositional logic, which is a linearized form of the well-known DPLL calculus extended by clause learning. It is motivated by the demand to model how current SAT solvers built on clause learning are working, while abstracting from decision heuristics and implementation details. The calculus is proved sound and terminating. Further, it is shown that both the original DPLL calculus and the conflict-directed backtracking calculus with clause learning, as it is implemented in many current SAT solvers, are complete and proof-confluent instances of the LD calculus.},
  language  = {en}
}
@unpublished{Arnold2009,
  author    = {Arnold, Holger},
  title     = {A linearized DPLL calculus with clause learning (2nd, revised version)},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-29080},
  year      = {2009},
  abstract  = {Many formal descriptions of DPLL-based SAT algorithms either do not include all essential proof techniques applied by modern SAT solvers or are bound to particular heuristics or data structures. This makes it difficult to analyze proof-theoretic properties or the search complexity of these algorithms. In this paper we try to improve this situation by developing a nondeterministic proof calculus that models the functioning of SAT algorithms based on the DPLL calculus with clause learning. This calculus is independent of implementation details yet precise enough to enable a formal analysis of realistic DPLL-based SAT algorithms.},
  language  = {en}
}
@phdthesis{Awad2010,
  author    = {Awad, Ahmed Mahmoud Hany Aly},
  title     = {A compliance management framework for business process models},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-49222},
  school      = {Universit{\"a}t Potsdam},
  year      = {2010},
  abstract  = {Companies develop process models to explicitly describe their business operations. In the same time, business operations, business processes, must adhere to various types of compliance requirements. Regulations, e.g., Sarbanes Oxley Act of 2002, internal policies, best practices are just a few sources of compliance requirements. In some cases, non-adherence to compliance requirements makes the organization subject to legal punishment. In other cases, non-adherence to compliance leads to loss of competitive advantage and thus loss of market share. Unlike the classical domain-independent behavioral correctness of business processes, compliance requirements are domain-specific. Moreover, compliance requirements change over time. New requirements might appear due to change in laws and adoption of new policies. Compliance requirements are offered or enforced by different entities that have different objectives behind these requirements. Finally, compliance requirements might affect different aspects of business processes, e.g., control flow and data flow. As a result, it is infeasible to hard-code compliance checks in tools. Rather, a repeatable process of modeling compliance rules and checking them against business processes automatically is needed. This thesis provides a formal approach to support process design-time compliance checking. Using visual patterns, it is possible to model compliance requirements concerning control flow, data flow and conditional flow rules. Each pattern is mapped into a temporal logic formula. The thesis addresses the problem of consistency checking among various compliance requirements, as they might stem from divergent sources. Also, the thesis contributes to automatically check compliance requirements against process models using model checking. We show that extra domain knowledge, other than expressed in compliance rules, is needed to reach correct decisions. In case of violations, we are able to provide a useful feedback to the user. The feedback is in the form of parts of the process model whose execution causes the violation. In some cases, our approach is capable of providing automated remedy of the violation.},
  language  = {en}
}
@phdthesis{Holz2013,
  author    = {Holz, Christian},
  title     = {3D from 2D touch},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-67796},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {While interaction with computers used to be dominated by mice and keyboards, new types of sensors now allow users to interact through touch, speech, or using their whole body in 3D space. These new interaction modalities are often referred to as "natural user interfaces" or "NUIs." While 2D NUIs have experienced major success on billions of mobile touch devices sold, 3D NUI systems have so far been unable to deliver a mobile form factor, mainly due to their use of cameras. The fact that cameras require a certain distance from the capture volume has prevented 3D NUI systems from reaching the flat form factor mobile users expect. In this dissertation, we address this issue by sensing 3D input using flat 2D sensors. The systems we present observe the input from 3D objects as 2D imprints upon physical contact. By sampling these imprints at very high resolutions, we obtain the objects' textures. In some cases, a texture uniquely identifies a biometric feature, such as the user's fingerprint. In other cases, an imprint stems from the user's clothing, such as when walking on multitouch floors. By analyzing from which part of the 3D object the 2D imprint results, we reconstruct the object's pose in 3D space. While our main contribution is a general approach to sensing 3D input on 2D sensors upon physical contact, we also demonstrate three applications of our approach. (1) We present high-accuracy touch devices that allow users to reliably touch targets that are a third of the size of those on current touch devices. We show that different users and 3D finger poses systematically affect touch sensing, which current devices perceive as random input noise. We introduce a model for touch that compensates for this systematic effect by deriving the 3D finger pose and the user's identity from each touch imprint. We then investigate this systematic effect in detail and explore how users conceptually touch targets. Our findings indicate that users aim by aligning visual features of their fingers with the target. We present a visual model for touch input that eliminates virtually all systematic effects on touch accuracy. (2) From each touch, we identify users biometrically by analyzing their fingerprints. Our prototype Fiberio integrates fingerprint scanning and a display into the same flat surface, solving a long-standing problem in human-computer interaction: secure authentication on touchscreens. Sensing 3D input and authenticating users upon touch allows Fiberio to implement a variety of applications that traditionally require the bulky setups of current 3D NUI systems. (3) To demonstrate the versatility of 3D reconstruction on larger touch surfaces, we present a high-resolution pressure-sensitive floor that resolves the texture of objects upon touch. Using the same principles as before, our system GravitySpace analyzes all imprints and identifies users based on their shoe soles, detects furniture, and enables accurate touch input using feet. By classifying all imprints, GravitySpace detects the users' body parts that are in contact with the floor and then reconstructs their 3D body poses using inverse kinematics. GravitySpace thus enables a range of applications for future 3D NUI systems based on a flat sensor, such as smart rooms in future homes. We conclude this dissertation by projecting into the future of mobile devices. Focusing on the mobility aspect of our work, we explore how NUI devices may one day augment users directly in the form of implanted devices.},
  language  = {en}
}