@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} } @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{Luckow2009, author = {Luckow, Andr{\´e}}, title = {A dependable middleware for enhancing the fault tolerance of distributed computations in grid environments}, address = {Potsdam}, pages = {235 S.}, year = {2009}, language = {en} } @phdthesis{Scherfenberg2012, author = {Scherfenberg, Ivonne}, title = {A logic-based Framwork to enable Attribute Assurance for Digital Identities in Service-oriented Architectures and the Web}, address = {Potsdam}, pages = {126 S.}, year = {2012}, language = {en} } @phdthesis{Andjelkovic2021, author = {Andjelkovic, Marko}, title = {A methodology for characterization, modeling and mitigation of single event transient effects in CMOS standard combinational cells}, doi = {10.25932/publishup-53484}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-534843}, school = {Universit{\"a}t Potsdam}, pages = {xxiv, 216}, year = {2021}, abstract = {With the downscaling of CMOS technologies, the radiation-induced Single Event Transient (SET) effects in combinational logic have become a critical reliability issue for modern integrated circuits (ICs) intended for operation under harsh radiation conditions. The SET pulses generated in combinational logic may propagate through the circuit and eventually result in soft errors. It has thus become an imperative to address the SET effects in the early phases of the radiation-hard IC design. In general, the soft error mitigation solutions should accommodate both static and dynamic measures to ensure the optimal utilization of available resources. An efficient soft-error-aware design should address synergistically three main aspects: (i) characterization and modeling of soft errors, (ii) multi-level soft error mitigation, and (iii) online soft error monitoring. Although significant results have been achieved, the effectiveness of SET characterization methods, accuracy of predictive SET models, and efficiency of SET mitigation measures are still critical issues. Therefore, this work addresses the following topics: (i) Characterization and modeling of SET effects in standard combinational cells, (ii) Static mitigation of SET effects in standard combinational cells, and (iii) Online particle detection, as a support for dynamic soft error mitigation. Since the standard digital libraries are widely used in the design of radiation-hard ICs, the characterization of SET effects in standard cells and the availability of accurate SET models for the Soft Error Rate (SER) evaluation are the main prerequisites for efficient radiation-hard design. This work introduces an approach for the SPICE-based standard cell characterization with the reduced number of simulations, improved SET models and optimized SET sensitivity database. It has been shown that the inherent similarities in the SET response of logic cells for different input levels can be utilized to reduce the number of required simulations. Based on characterization results, the fitting models for the SET sensitivity metrics (critical charge, generated SET pulse width and propagated SET pulse width) have been developed. The proposed models are based on the principle of superposition, and they express explicitly the dependence of the SET sensitivity of individual combinational cells on design, operating and irradiation parameters. In contrast to the state-of-the-art characterization methodologies which employ extensive look-up tables (LUTs) for storing the simulation results, this work proposes the use of LUTs for storing the fitting coefficients of the SET sensitivity models derived from the characterization results. In that way the amount of characterization data in the SET sensitivity database is reduced significantly. The initial step in enhancing the robustness of combinational logic is the application of gate-level mitigation techniques. As a result, significant improvement of the overall SER can be achieved with minimum area, delay and power overheads. For the SET mitigation in standard cells, it is essential to employ the techniques that do not require modifying the cell structure. This work introduces the use of decoupling cells for improving the robustness of standard combinational cells. By insertion of two decoupling cells at the output of a target cell, the critical charge of the cell's output node is increased and the attenuation of short SETs is enhanced. In comparison to the most common gate-level techniques (gate upsizing and gate duplication), the proposed approach provides better SET filtering. However, as there is no single gate-level mitigation technique with optimal performance, a combination of multiple techniques is required. This work introduces a comprehensive characterization of gate-level mitigation techniques aimed to quantify their impact on the SET robustness improvement, as well as introduced area, delay and power overhead per gate. By characterizing the gate-level mitigation techniques together with the standard cells, the required effort in subsequent SER analysis of a target design can be reduced. The characterization database of the hardened standard cells can be utilized as a guideline for selection of the most appropriate mitigation solution for a given design. As a support for dynamic soft error mitigation techniques, it is important to enable the online detection of energetic particles causing the soft errors. This allows activating the power-greedy fault-tolerant configurations based on N-modular redundancy only at the high radiation levels. To enable such a functionality, it is necessary to monitor both the particle flux and the variation of particle LET, as these two parameters contribute significantly to the system SER. In this work, a particle detection approach based on custom-sized pulse stretching inverters is proposed. Employing the pulse stretching inverters connected in parallel enables to measure the particle flux in terms of the number of detected SETs, while the particle LET variations can be estimated from the distribution of SET pulse widths. This approach requires a purely digital processing logic, in contrast to the standard detectors which require complex mixed-signal processing. Besides the possibility of LET monitoring, additional advantages of the proposed particle detector are low detection latency and power consumption, and immunity to error accumulation. The results achieved in this thesis can serve as a basis for establishment of an overall soft-error-aware database for a given digital library, and a comprehensive multi-level radiation-hard design flow that can be implemented with the standard IC design tools. The following step will be to evaluate the achieved results with the irradiation experiments.}, language = {en} } @phdthesis{Wolter2010, author = {Wolter, Christian}, title = {A methodology for model-driven process security}, address = {Potsdam}, pages = {xv, 144 S. : graph. Darst.}, year = {2010}, 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} } @phdthesis{Mueller2012, author = {M{\"u}ller, J{\"u}rgen J.}, title = {A real-time in-memory discovery service}, address = {Potsdam}, pages = {XXV, 172 S.}, year = {2012}, language = {en} } @phdthesis{Chen2023, author = {Chen, Junchao}, title = {A self-adaptive resilient method for implementing and managing the high-reliability processing system}, doi = {10.25932/publishup-58313}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-583139}, school = {Universit{\"a}t Potsdam}, pages = {XXIII, 167}, year = {2023}, abstract = {As a result of CMOS scaling, radiation-induced Single-Event Effects (SEEs) in electronic circuits became a critical reliability issue for modern Integrated Circuits (ICs) operating under harsh radiation conditions. SEEs can be triggered in combinational or sequential logic by the impact of high-energy particles, leading to destructive or non-destructive faults, resulting in data corruption or even system failure. Typically, the SEE mitigation methods are deployed statically in processing architectures based on the worst-case radiation conditions, which is most of the time unnecessary and results in a resource overhead. Moreover, the space radiation conditions are dynamically changing, especially during Solar Particle Events (SPEs). The intensity of space radiation can differ over five orders of magnitude within a few hours or days, resulting in several orders of magnitude fault probability variation in ICs during SPEs. This thesis introduces a comprehensive approach for designing a self-adaptive fault resilient multiprocessing system to overcome the static mitigation overhead issue. This work mainly addresses the following topics: (1) Design of on-chip radiation particle monitor for real-time radiation environment detection, (2) Investigation of space environment predictor, as support for solar particle events forecast, (3) Dynamic mode configuration in the resilient multiprocessing system. Therefore, according to detected and predicted in-flight space radiation conditions, the target system can be configured to use no mitigation or low-overhead mitigation during non-critical periods of time. The redundant resources can be used to improve system performance or save power. On the other hand, during increased radiation activity periods, such as SPEs, the mitigation methods can be dynamically configured appropriately depending on the real-time space radiation environment, resulting in higher system reliability. Thus, a dynamic trade-off in the target system between reliability, performance and power consumption in real-time can be achieved. All results of this work are evaluated in a highly reliable quad-core multiprocessing system that allows the self-adaptive setting of optimal radiation mitigation mechanisms during run-time. Proposed methods can serve as a basis for establishing a comprehensive self-adaptive resilient system design process. Successful implementation of the proposed design in the quad-core multiprocessor shows its application perspective also in the other designs.}, 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{Zhou2008, author = {Zhou, Wei}, title = {Access control model and policies for collaborative environments}, address = {Potsdam}, pages = {199 S. : graph. Darst.}, year = {2008}, 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{Hetzer2006, author = {Hetzer, Dirk}, title = {Adaptive Quality of Service based Bandwidth Planning in Internet}, address = {Potsdam}, pages = {190 S. : graph. Darst.}, year = {2006}, language = {en} } @phdthesis{Hecher2021, author = {Hecher, Markus}, title = {Advanced tools and methods for treewidth-based problem solving}, doi = {10.25932/publishup-51251}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-512519}, school = {Universit{\"a}t Potsdam}, pages = {xv, 184}, year = {2021}, abstract = {In the last decades, there was a notable progress in solving the well-known Boolean satisfiability (Sat) problem, which can be witnessed by powerful Sat solvers. One of the reasons why these solvers are so fast are structural properties of instances that are utilized by the solver's interna. This thesis deals with the well-studied structural property treewidth, which measures the closeness of an instance to being a tree. In fact, there are many problems parameterized by treewidth that are solvable in polynomial time in the instance size when parameterized by treewidth. In this work, we study advanced treewidth-based methods and tools for problems in knowledge representation and reasoning (KR). Thereby, we provide means to establish precise runtime results (upper bounds) for canonical problems relevant to KR. Then, we present a new type of problem reduction, which we call decomposition-guided (DG) that allows us to precisely monitor the treewidth when reducing from one problem to another problem. This new reduction type will be the basis for a long-open lower bound result for quantified Boolean formulas and allows us to design a new methodology for establishing runtime lower bounds for problems parameterized by treewidth. Finally, despite these lower bounds, we provide an efficient implementation of algorithms that adhere to treewidth. Our approach finds suitable abstractions of instances, which are subsequently refined in a recursive fashion, and it uses Sat solvers for solving subproblems. It turns out that our resulting solver is quite competitive for two canonical counting problems related to Sat.}, language = {en} } @phdthesis{Mueller2016, author = {M{\"u}ller, Stephan Heinz}, title = {Aggregates Caching for Enterprise Applications}, school = {Universit{\"a}t Potsdam}, pages = {167}, year = {2016}, abstract = {The introduction of columnar in-memory databases, along with hardware evolution, has made the execution of transactional and analytical enterprise application workloads on a single system both feasible and viable. Yet, we argue that executing analytical aggregate queries directly on the transactional data can decrease the overall system performance. Despite the aggregation capabilities of columnar in-memory databases, the direct access to records of a materialized aggregate is always more efficient than aggregating on the fly. The traditional approach to materialized aggregates, however, introduces significant overhead in terms of materialized view selection, maintenance, and exploitation. When this overhead is handled by the application, it increases the application complexity, and can slow down the transactional throughput of inserts, updates, and deletes. In this thesis, we motivate, propose, and evaluate the aggregate cache, a materialized aggregate engine in the main-delta architecture of a columnar in-memory database that provides efficient means to handle costly aggregate queries of enterprise applications. For our design, we leverage the specifics of the main-delta architecture that separates a table into a main and delta partition. The central concept is to only cache the partial aggregate query result as defined on the main partition of a table, because the main partition is relatively stable as records are only inserted into the delta partition. We contribute by proposing incremental aggregate maintenance and query compensation techniques for mixed workloads of enterprise applications. In addition, we introduce aggregate profit metrics that increase the likelihood of persisting the most profitable aggregates in the aggregate cache. Query compensation and maintenance of materialized aggregates based on joins of multiple tables is expensive due to the partitioned tables in the main-delta architecture. Our analysis of enterprise applications has revealed several data schema and workload patterns. This includes the observation that transactional data is persisted in header and item tables, whereas in many cases, the insertion of related header and item records is executed in a single database transaction. We contribute by proposing an approach to transport these application object semantics to the database system and optimize the query processing using the aggregate cache by applying partition pruning and predicate pushdown techniques. For the experimental evaluation, we propose the FICO benchmark that is based on data from a productive ERP system with extracted mixed workloads. Our evaluation reveals that the aggregate cache can accelerate the execution of aggregate queries up to a factor of 60 whereas the speedup highly depends on the number of aggregated records in the main and delta partitions. In mixed workloads, the proposed aggregate maintenance and query compensation techniques perform up to an order of magnitude better than traditional materialized aggregate maintenance approaches. The introduced aggregate profit metrics outperform existing costbased metrics by up to 20\%. Lastly, the join pruning and predicate pushdown techniques can accelerate query execution in the aggregate cache in the presence of multiple partitioned tables by up to an order of magnitude.}, 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{Linckels2008, author = {Linckels, Serge}, title = {An e-librarian service : supporting explorative learning by a description logics based semantic retrieval tool}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-17452}, school = {Universit{\"a}t Potsdam}, year = {2008}, abstract = {Although educational content in electronic form is increasing dramatically, its usage in an educational environment is poor, mainly due to the fact that there is too much of (unreliable) redundant, and not relevant information. Finding appropriate answers is a rather difficult task being reliant on the user filtering of the pertinent information from the noise. Turning knowledge bases like the online tele-TASK archive into useful educational resources requires identifying correct, reliable, and "machine-understandable" information, as well as developing simple but efficient search tools with the ability to reason over this information. Our vision is to create an E-Librarian Service, which is able to retrieve multimedia resources from a knowledge base in a more efficient way than by browsing through an index, or by using a simple keyword search. In our E-Librarian Service, the user can enter his question in a very simple and human way; in natural language (NL). Our premise is that more pertinent results would be retrieved if the search engine understood the sense of the user's query. The returned results are then logical consequences of an inference rather than of keyword matchings. Our E-Librarian Service does not return the answer to the user's question, but it retrieves the most pertinent document(s), in which the user finds the answer to his/her question. Among all the documents that have some common information with the user query, our E-Librarian Service identifies the most pertinent match(es), keeping in mind that the user expects an exhaustive answer while preferring a concise answer with only little or no information overhead. Also, our E-Librarian Service always proposes a solution to the user, even if the system concludes that there is no exhaustive answer. Our E-Librarian Service was implemented prototypically in three different educational tools. A first prototype is CHESt (Computer History Expert System); it has a knowledge base with 300 multimedia clips that cover the main events in computer history. A second prototype is MatES (Mathematics Expert System); it has a knowledge base with 115 clips that cover the topic of fractions in mathematics for secondary school w.r.t. the official school programme. All clips were recorded mainly by pupils. The third and most advanced prototype is the "Lecture Butler's E-Librarain Service"; it has a Web service interface to respect a service oriented architecture (SOA), and was developed in the context of the Web-University project at the Hasso-Plattner-Institute (HPI). Two major experiments in an educational environment - at the Lyc{\´e}e Technique Esch/Alzette in Luxembourg - were made to test the pertinence and reliability of our E-Librarian Service as a complement to traditional courses. The first experiment (in 2005) was made with CHESt in different classes, and covered a single lesson. The second experiment (in 2006) covered a period of 6 weeks of intensive use of MatES in one class. There was no classical mathematics lesson where the teacher gave explanations, but the students had to learn in an autonomous and exploratory way. They had to ask questions to the E-Librarian Service just the way they would if there was a human teacher.}, subject = {Terminologische Logik}, language = {en} } @phdthesis{Heinze2015, author = {Heinze, Theodor}, title = {Analyse von Patientendaten und Entscheidungsunterst{\"u}tzung in der Telemedizin}, school = {Universit{\"a}t Potsdam}, pages = {173}, year = {2015}, language = {de} } @phdthesis{AlSaffar2016, author = {Al-Saffar, Loay Talib Ahmed}, title = {Analysing prerequisites, expectations, apprehensions, and attitudes of University students studying computer science}, school = {Universit{\"a}t Potsdam}, pages = {128}, year = {2016}, language = {en} } @phdthesis{AlSaffar2016, author = {Al-Saffar, Loay Talib Ahmed}, title = {Analysing prerequisites, expectations, apprehensions, and attitudes of university students studying Computer science}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-98437}, school = {Universit{\"a}t Potsdam}, pages = {xii, 131}, year = {2016}, abstract = {The main objective of this dissertation is to analyse prerequisites, expectations, apprehensions, and attitudes of students studying computer science, who are willing to gain a bachelor degree. The research will also investigate in the students' learning style according to the Felder-Silverman model. These investigations fall in the attempt to make an impact on reducing the "dropout"/shrinkage rate among students, and to suggest a better learning environment. The first investigation starts with a survey that has been made at the computer science department at the University of Baghdad to investigate the attitudes of computer science students in an environment dominated by women, showing the differences in attitudes between male and female students in different study years. Students are accepted to university studies via a centrally controlled admission procedure depending mainly on their final score at school. This leads to a high percentage of students studying subjects they do not want. Our analysis shows that 75\% of the female students do not regret studying computer science although it was not their first choice. And according to statistics over previous years, women manage to succeed in their study and often graduate on top of their class. We finish with a comparison of attitudes between the freshman students of two different cultures and two different university enrolment procedures (University of Baghdad, in Iraq, and the University of Potsdam, in Germany) both with opposite gender majority. The second step of investigation took place at the department of computer science at the University of Potsdam in Germany and analyzes the learning styles of students studying the three major fields of study offered by the department (computer science, business informatics, and computer science teaching). Investigating the differences in learning styles between the students of those study fields who usually take some joint courses is important to be aware of which changes are necessary to be adopted in the teaching methods to address those different students. It was a two stage study using two questionnaires; the main one is based on the Index of Learning Styles Questionnaire of B. A. Solomon and R. M. Felder, and the second questionnaire was an investigation on the students' attitudes towards the findings of their personal first questionnaire. Our analysis shows differences in the preferences of learning style between male and female students of the different study fields, as well as differences between students with the different specialties (computer science, business informatics, and computer science teaching). The third investigation looks closely into the difficulties, issues, apprehensions and expectations of freshman students studying computer science. The study took place at the computer science department at the University of Potsdam with a volunteer sample of students. The goal is to determine and discuss the difficulties and issues that they are facing in their study that may lead them to think in dropping-out, changing the study field, or changing the university. The research continued with the same sample of students (with business informatics students being the majority) through more than three semesters. Difficulties and issues during the study were documented, as well as students' attitudes, apprehensions, and expectations. Some of the professors and lecturers opinions and solutions to some students' problems were also documented. Many participants had apprehensions and difficulties, especially towards informatics subjects. Some business informatics participants began to think of changing the university, in particular when they reached their third semester, others thought about changing their field of study. Till the end of this research, most of the participants continued in their studies (the study they have started with or the new study they have changed to) without leaving the higher education system.}, language = {en} } @phdthesis{Floeter2005, author = {Fl{\"o}ter, Andr{\´e}}, title = {Analyzing biological expression data based on decision tree induction}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-6416}, school = {Universit{\"a}t Potsdam}, year = {2005}, abstract = {Modern biological analysis techniques supply scientists with various forms of data. One category of such data are the so called "expression data". These data indicate the quantities of biochemical compounds present in tissue samples. Recently, expression data can be generated at a high speed. This leads in turn to amounts of data no longer analysable by classical statistical techniques. Systems biology is the new field that focuses on the modelling of this information. At present, various methods are used for this purpose. One superordinate class of these meth­ods is machine learning. Methods of this kind had, until recently, predominantly been used for classification and prediction tasks. This neglected a powerful secondary benefit: the ability to induce interpretable models. Obtaining such models from data has become a key issue within Systems biology. Numerous approaches have been proposed and intensively discussed. This thesis focuses on the examination and exploitation of one basic technique: decision trees. The concept of comparing sets of decision trees is developed. This method offers the pos­sibility of identifying significant thresholds in continuous or discrete valued attributes through their corresponding set of decision trees. Finding significant thresholds in attributes is a means of identifying states in living organisms. Knowing about states is an invaluable clue to the un­derstanding of dynamic processes in organisms. Applied to metabolite concentration data, the proposed method was able to identify states which were not found with conventional techniques for threshold extraction. A second approach exploits the structure of sets of decision trees for the discovery of com­binatorial dependencies between attributes. Previous work on this issue has focused either on expensive computational methods or the interpretation of single decision trees ­ a very limited exploitation of the data. This has led to incomplete or unstable results. That is why a new method is developed that uses sets of decision trees to overcome these limitations. Both the introduced methods are available as software tools. They can be applied consecu­tively or separately. That way they make up a package of analytical tools that usefully supplement existing methods. By means of these tools, the newly introduced methods were able to confirm existing knowl­edge and to suggest interesting and new relationships between metabolites.}, subject = {Molekulare Bioinformatik}, language = {en} } @phdthesis{Feinbube2018, author = {Feinbube, Frank}, title = {Ans{\"a}tze zur Integration von Beschleunigern ins Betriebssystem}, school = {Universit{\"a}t Potsdam}, pages = {238}, year = {2018}, 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{Richter2011, author = {Richter, Michael}, title = {Anwendung nichtlinearer Codes zur Fehlererkennung und -korrektur}, address = {Potsdam}, pages = {134 S.}, year = {2011}, language = {de} } @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{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{Schult2009, author = {Schult, Wolfgang}, title = {Architektur komponenten-basierter Systeme mit LOOM : Aspekte, Muster, Werkzeuge}, publisher = {Cuvillier}, address = {G{\"o}ttingen}, isbn = {978-3-86955-031-2}, pages = {217 S.}, year = {2009}, language = {de} } @phdthesis{Reinke2003, author = {Reinke, Thomas}, title = {Architekturbasierte Konstruktion von Multiagentensystemen}, pages = {166 S.}, year = {2003}, language = {de} } @phdthesis{Wist2011, author = {Wist, Dominic}, title = {Attacking complexity in logic synthesis of asynchronous circuits}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-59706}, school = {Universit{\"a}t Potsdam}, year = {2011}, abstract = {Most of the microelectronic circuits fabricated today are synchronous, i.e. they are driven by one or several clock signals. Synchronous circuit design faces several fundamental challenges such as high-speed clock distribution, integration of multiple cores operating at different clock rates, reduction of power consumption and dealing with voltage, temperature, manufacturing and runtime variations. Asynchronous or clockless design plays a key role in alleviating these challenges, however the design and test of asynchronous circuits is much more difficult in comparison to their synchronous counterparts. A driving force for a widespread use of asynchronous technology is the availability of mature EDA (Electronic Design Automation) tools which provide an entire automated design flow starting from an HDL (Hardware Description Language) specification yielding the final circuit layout. Even though there was much progress in developing such EDA tools for asynchronous circuit design during the last two decades, the maturity level as well as the acceptance of them is still not comparable with tools for synchronous circuit design. In particular, logic synthesis (which implies the application of Boolean minimisation techniques) for the entire system's control path can significantly improve the efficiency of the resulting asynchronous implementation, e.g. in terms of chip area and performance. However, logic synthesis, in particular for asynchronous circuits, suffers from complexity problems. Signal Transitions Graphs (STGs) are labelled Petri nets which are a widely used to specify the interface behaviour of speed independent (SI) circuits - a robust subclass of asynchronous circuits. STG decomposition is a promising approach to tackle complexity problems like state space explosion in logic synthesis of SI circuits. The (structural) decomposition of STGs is guided by a partition of the output signals and generates a usually much smaller component STG for each partition member, i.e. a component STG with a much smaller state space than the initial specification. However, decomposition can result in component STGs that in isolation have so-called irreducible CSC conflicts (i.e. these components are not SI synthesisable anymore) even if the specification has none of them. A new approach is presented to avoid such conflicts by introducing internal communication between the components. So far, STG decompositions are guided by the finest output partitions, i.e. one output per component. However, this might not yield optimal circuit implementations. Efficient heuristics are presented to determine coarser partitions leading to improved circuits in terms of chip area. For the new algorithms correctness proofs are given and their implementations are incorporated into the decomposition tool DESIJ. The presented techniques are successfully applied to some benchmarks - including 'real-life' specifications arising in the context of control resynthesis - which delivered promising results.}, language = {en} } @phdthesis{Alsadeh2013, author = {Alsadeh, Ahmad}, title = {Augmented secure neighbor discovery: aligning security, privacy and usability}, address = {Potsdam}, pages = {114 S.}, year = {2013}, language = {en} } @phdthesis{Rasche2008, author = {Rasche, Andreas}, title = {Ausf{\"u}hrung und Entwicklung Adaptiver Komponentenbasierter Anwendungen}, address = {Potsdam}, isbn = {978-3-86727-698-6}, pages = {195 S., graph. Darst.}, year = {2008}, language = {de} } @phdthesis{Rasche2008, author = {Rasche, Andreas}, title = {Ausf{\"u}hrung und Entwicklung adaptiver komponentenbasierter Anwendungen}, publisher = {Cuvillier}, address = {G{\"o}ttingen}, isbn = {978-3-86727-698-6}, pages = {195 S.: graph. Darst.}, year = {2008}, language = {de} } @phdthesis{Weise2021, author = {Weise, Matthias}, title = {Auswahl von Selektions- und Manipulationstechniken f{\"u}r Virtual Reality-Anwendungen}, doi = {10.25932/publishup-53458}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-534586}, school = {Universit{\"a}t Potsdam}, pages = {iii, 218}, year = {2021}, abstract = {Die stetige Weiterentwicklung von VR-Systemen bietet neue M{\"o}glichkeiten der Interaktion mit virtuellen Objekten im dreidimensionalen Raum, stellt Entwickelnde von VRAnwendungen aber auch vor neue Herausforderungen. Selektions- und Manipulationstechniken m{\"u}ssen unter Ber{\"u}cksichtigung des Anwendungsszenarios, der Zielgruppe und der zur Verf{\"u}gung stehenden Ein- und Ausgabeger{\"a}te ausgew{\"a}hlt werden. Diese Arbeit leistet einen Beitrag dazu, die Auswahl von passenden Interaktionstechniken zu unterst{\"u}tzen. Hierf{\"u}r wurde eine repr{\"a}sentative Menge von Selektions- und Manipulationstechniken untersucht und, unter Ber{\"u}cksichtigung existierender Klassifikationssysteme, eine Taxonomie entwickelt, die die Analyse der Techniken hinsichtlich interaktionsrelevanter Eigenschaften erm{\"o}glicht. Auf Basis dieser Taxonomie wurden Techniken ausgew{\"a}hlt, die in einer explorativen Studie verglichen wurden, um R{\"u}ckschl{\"u}sse auf die Dimensionen der Taxonomie zu ziehen und neue Indizien f{\"u}r Vor- und Nachteile der Techniken in spezifischen Anwendungsszenarien zu generieren. Die Ergebnisse der Arbeit m{\"u}nden in eine Webanwendung, die Entwickelnde von VR-Anwendungen gezielt dabei unterst{\"u}tzt, passende Selektions- und Manipulationstechniken f{\"u}r ein Anwendungsszenario auszuw{\"a}hlen, indem Techniken auf Basis der Taxonomie gefiltert und unter Verwendung der Resultate aus der Studie sortiert werden k{\"o}nnen.}, language = {de} } @phdthesis{Yang2013, author = {Yang, Haojin}, title = {Automatic video indexing and retrieval using video ocr technology}, address = {Potsdam}, pages = {182 S.}, year = {2013}, language = {en} } @phdthesis{SchulzHanke2023, author = {Schulz-Hanke, Christian}, title = {BCH Codes mit kombinierter Korrektur und Erkennung}, doi = {10.25932/publishup-61794}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-617943}, school = {Universit{\"a}t Potsdam}, pages = {ii, 191}, year = {2023}, abstract = {BCH Codes mit kombinierter Korrektur und Erkennung In dieser Arbeit wird auf Grundlage des BCH Codes untersucht, wie eine Fehlerkorrektur mit einer Erkennung h{\"o}herer Fehleranzahlen kombiniert werden kann. Mit dem Verfahren der 1-Bit Korrektur mit zus{\"a}tzlicher Erkennung h{\"o}herer Fehler wurde ein Ansatz entwickelt, welcher die Erkennung zus{\"a}tzlicher Fehler durch das parallele L{\"o}sen einfacher Gleichungen der Form s_x = s_1^x durchf{\"u}hrt. Die Anzahl dieser Gleichungen ist linear zu der Anzahl der zu {\"u}berpr{\"u}fenden h{\"o}heren Fehler. In dieser Arbeit wurde zus{\"a}tzlich f{\"u}r bis zu 4-Bit Korrekturen mit zus{\"a}tzlicher Erkennung h{\"o}herer Fehler ein weiterer allgemeiner Ansatz vorgestellt. Dabei werden parallel f{\"u}r alle korrigierbaren Fehleranzahlen spekulative Fehlerkorrekturen durchgef{\"u}hrt. Aus den bestimmten Fehlerstellen werden spekulative Syndromkomponenten erzeugt, durch welche die Fehlerstellen best{\"a}tigt und h{\"o}here erkennbare Fehleranzahlen ausgeschlossen werden k{\"o}nnen. Die vorgestellten Ans{\"a}tze unterscheiden sich von dem in entwickelten Ansatz, bei welchem die Anzahl der Fehlerstellen durch die Berechnung von Determinanten in absteigender Reihenfolge berechnet wird, bis die erste Determinante 0 bildet. Bei dem bekannten Verfahren ist durch die Berechnung der Determinanten eine faktorielle Anzahl an Berechnungen in Relation zu der Anzahl zu {\"u}berpr{\"u}fender Fehler durchzuf{\"u}hren. Im Vergleich zu dem bekannten sequentiellen Verfahrens nach Berlekamp Massey besitzen die Berechnungen im vorgestellten Ansatz simple Gleichungen und k{\"o}nnen parallel durchgef{\"u}hrt werden.Bei dem bekannten Verfahren zur parallelen Korrektur von 4-Bit Fehlern ist eine Gleichung vierten Grades im GF(2^m) zu l{\"o}sen. Dies erfolgt, indem eine Hilfsgleichung dritten Grades und vier Gleichungen zweiten Grades parallel gel{\"o}st werden. In der vorliegenden Arbeit wurde gezeigt, dass sich eine Gleichung zweiten Grades einsparen l{\"a}sst, wodurch sich eine Vereinfachung der Hardware bei einer parallelen Realisierung der 4-Bit Korrektur ergibt. Die erzielten Ergebnisse wurden durch umfangreiche Simulationen in Software und Hardwareimplementierungen {\"u}berpr{\"u}ft.}, language = {de} } @phdthesis{Bog2012, author = {Bog, Anja}, title = {Benchmarking composite transaction and analytical processing systems : the creation of a mixed workload benchmark and its application in evaluating the impact of database schema optimizations in mixed workload scenarios}, address = {Potsdam}, pages = {173 S.}, year = {2012}, language = {en} } @phdthesis{Ziehe2005, author = {Ziehe, Andreas}, title = {Blind source separation based on joint diagonalization of matrices with applications in biomedical signal processing}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-5694}, school = {Universit{\"a}t Potsdam}, year = {2005}, abstract = {This thesis is concerned with the solution of the blind source separation problem (BSS). The BSS problem occurs frequently in various scientific and technical applications. In essence, it consists in separating meaningful underlying components out of a mixture of a multitude of superimposed signals. In the recent research literature there are two related approaches to the BSS problem: The first is known as Independent Component Analysis (ICA), where the goal is to transform the data such that the components become as independent as possible. The second is based on the notion of diagonality of certain characteristic matrices derived from the data. Here the goal is to transform the matrices such that they become as diagonal as possible. In this thesis we study the latter method of approximate joint diagonalization (AJD) to achieve a solution of the BSS problem. After an introduction to the general setting, the thesis provides an overview on particular choices for the set of target matrices that can be used for BSS by joint diagonalization. As the main contribution of the thesis, new algorithms for approximate joint diagonalization of several matrices with non-orthogonal transformations are developed. These newly developed algorithms will be tested on synthetic benchmark datasets and compared to other previous diagonalization algorithms. Applications of the BSS methods to biomedical signal processing are discussed and exemplified with real-life data sets of multi-channel biomagnetic recordings.}, subject = {Signaltrennung}, language = {en} } @phdthesis{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{Wildner1997, author = {Wildner, Uwe}, title = {CASC : compiler assisted self-checking of structural integrity}, pages = {XIV, 134 S. : graph. Darst.}, year = {1997}, language = {en} } @phdthesis{Glubudum2008, author = {Glubudum, Prisana}, title = {Clones of tree languages and non-deterministic hypersubstitutions}, pages = {3,IV, 74 Bl.}, year = {2008}, language = {en} } @phdthesis{Schnjakin2014, author = {Schnjakin, Maxim}, title = {Cloud-RAID}, pages = {137}, year = {2014}, language = {de} } @phdthesis{Kaminski2023, author = {Kaminski, Roland}, title = {Complex reasoning with answer set programming}, school = {Universit{\"a}t Potsdam}, pages = {301}, year = {2023}, abstract = {Answer Set Programming (ASP) allows us to address knowledge-intensive search and optimization problems in a declarative way due to its integrated modeling, grounding, and solving workflow. A problem is modeled using a rule based language and then grounded and solved. Solving results in a set of stable models that correspond to solutions of the modeled problem. In this thesis, we present the design and implementation of the clingo system---perhaps, the most widely used ASP system. It features a rich modeling language originating from the field of knowledge representation and reasoning, efficient grounding algorithms based on database evaluation techniques, and high performance solving algorithms based on Boolean satisfiability (SAT) solving technology. The contributions of this thesis lie in the design of the modeling language, the design and implementation of the grounding algorithms, and the design and implementation of an Application Programmable Interface (API) facilitating the use of ASP in real world applications and the implementation of complex forms of reasoning beyond the traditional ASP workflow.}, language = {en} } @phdthesis{Schneider2019, author = {Schneider, Jan Niklas}, title = {Computational approaches for emotion research}, doi = {10.25932/publishup-45927}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-459275}, school = {Universit{\"a}t Potsdam}, pages = {xv, 145}, year = {2019}, abstract = {Emotionen sind ein zentrales Element menschlichen Erlebens und spielen eine wichtige Rolle bei der Entscheidungsfindung. Diese Dissertation identifiziert drei methodische Probleme der aktuellen Emotionsforschung und zeigt auf, wie diese mittels computergest{\"u}tzter Methoden gel{\"o}st werden k{\"o}nnen. Dieser Ansatz wird in drei Forschungsprojekten demonstriert, die die Entwicklung solcher Methoden sowie deren Anwendung auf konkrete Forschungsfragen beschreiben. Das erste Projekt beschreibt ein Paradigma welches es erm{\"o}glicht, die subjektive und objektive Schwierigkeit der Emotionswahrnehmung zu messen. Dar{\"u}ber hinaus erm{\"o}glicht es die Verwendung einer beliebigen Anzahl von Emotionskategorien im Vergleich zu den {\"u}blichen sechs Kategorien der Basisemotionen. Die Ergebnisse deuten auf eine Zunahme der Schwierigkeiten bei der Wahrnehmung von Emotionen mit zunehmendem Alter der Darsteller hin und liefern Hinweise darauf, dass junge Erwachsene, {\"a}ltere Menschen und M{\"a}nner ihre Schwierigkeit bei der Wahrnehmung von Emotionen untersch{\"a}tzen. Weitere Analysen zeigten eine geringe Relevanz personenbezogener Variablen und deuteten darauf hin, dass die Schwierigkeit der Emotionswahrnehmung vornehmlich durch die Auspr{\"a}gung der Wertigkeit des Ausdrucks bestimmt wird. Das zweite Projekt zeigt am Beispiel von Arousal, einem etablierten, aber vagen Konstrukt der Emotionsforschung, wie Face-Tracking-Daten dazu genutzt werden k{\"o}nnen solche Konstrukte zu sch{\"a}rfen. Es beschreibt, wie aus Face-Tracking-Daten Maße f{\"u}r die Entfernung, Geschwindigkeit und Beschleunigung von Gesichtsausdr{\"u}cken berechnet werden k{\"o}nnen. Das Projekt untersuchte wie diesen Maße mit der Arousal-Wahrnehmung in Menschen mit und ohne Autismus zusammenh{\"a}ngen. Der Abstand zum Neutralgesicht war pr{\"a}diktiv f{\"u}r die Arousal-Bewertungen in beiden Gruppen. Die Ergebnisse deuten auf eine qualitativ {\"a}hnliche Wahrnehmung von Arousal f{\"u}r Menschen mit und ohne Autismus hin. Im dritten Projekt stellen wir die Partial-Least-Squares-Analyse als allgemeine Methode vor, um eine optimale Repr{\"a}sentation zur Verkn{\"u}pfung zweier hochdimensionale Datens{\"a}tze zu finden. Das Projekt demonstriert die Anwendbarkeit dieser Methode in der Emotionsforschung anhand der Frage nach Unterschieden in der Emotionswahrnehmung zwischen M{\"a}nnern und Frauen. Wir konnten zeigen, dass die emotionale Wahrnehmung von Frauen systematisch mehr Varianz der Gesichtsausdr{\"u}cke erfasst und dass signifikante Unterschiede in der Art und Weise bestehen, wie Frauen und M{\"a}nner einige Gesichtsausdr{\"u}cke wahrnehmen. Diese konnten wir als dynamische Gesichtsausdr{\"u}cke visualisieren. Um die Anwendung der entwickelten Methode f{\"u}r die Forschungsgemeinschaft zu erleichtern, wurde ein Software-Paket f{\"u}r die Statistikumgebung R geschrieben. Zudem wurde eine Website entwickelt (thisemotiondoesnotexist.com), die es Besuchern erlaubt, ein Partial-Least-Squares-Modell von Emotionsbewertungen und Face-Tracking-Daten interaktiv zu erkunden, um die entwickelte Methode zu verbreiten und ihren Nutzen f{\"u}r die Emotionsforschung zu illustrieren.}, language = {en} } @phdthesis{Gros2013, author = {Gros, Oliver}, title = {Computergest{\"u}tzte Wissensextraktion aus befundtexten der Pathologie}, address = {Potsdam}, pages = {170 S.}, year = {2013}, language = {de} } @phdthesis{Grum2021, author = {Grum, Marcus}, title = {Construction of a concept of neuronal modeling}, year = {2021}, abstract = {The business problem of having inefficient processes, imprecise process analyses, and simulations as well as non-transparent artificial neuronal network models can be overcome by an easy-to-use modeling concept. With the aim of developing a flexible and efficient approach to modeling, simulating, and optimizing processes, this paper proposes a flexible Concept of Neuronal Modeling (CoNM). The modeling concept, which is described by the modeling language designed and its mathematical formulation and is connected to a technical substantiation, is based on a collection of novel sub-artifacts. As these have been implemented as a computational model, the set of CoNM tools carries out novel kinds of Neuronal Process Modeling (NPM), Neuronal Process Simulations (NPS), and Neuronal Process Optimizations (NPO). The efficacy of the designed artifacts was demonstrated rigorously by means of six experiments and a simulator of real industrial production processes.}, language = {en} } @phdthesis{Huong2001, author = {Huong, Dinh Thi Thanh}, title = {Correctness proofs and probabilistic tests for constructive specifications and functional programs}, pages = {154 S.}, year = {2001}, language = {en} } @phdthesis{Tarnick1995, author = {Tarnick, Steffen}, title = {Data compression techniques for concurrent error detection and built-in self test}, pages = {159 S. : Ill.}, year = {1995}, language = {en} } @phdthesis{Bleiholder2010, author = {Bleiholder, Jens}, title = {Data fusion and conflict resolution in integrated information systems}, address = {Potsdam}, pages = {171 S.}, year = {2010}, language = {en} } @phdthesis{Rabenalt2011, author = {Rabenalt, Thomas}, title = {Datenkompaktierung f{\"u}r Diagnose und Test}, address = {Potsdam}, pages = {116 S.}, year = {2011}, language = {de} } @phdthesis{Phusanga2013, author = {Phusanga, Dara}, title = {Derived algebraic systems}, address = {Potsdam}, pages = {81 S.}, year = {2013}, language = {en} } @phdthesis{Decker2009, author = {Decker, Gero}, title = {Design and analysis of process choreographies}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-40761}, school = {Universit{\"a}t Potsdam}, year = {2009}, abstract = {With the rise of electronic integration between organizations, the need for a precise specification of interaction behavior increases. Information systems, replacing interaction previously carried out by humans via phone, faxes and emails, require a precise specification for handling all possible situations. Such interaction behavior is described in process choreographies. Choreographies enumerate the roles involved, the allowed interactions, the message contents and the behavioral dependencies between interactions. Choreographies serve as interaction contract and are the starting point for adapting existing business processes and systems or for implementing new software components. As a thorough analysis and comparison of choreography modeling languages is missing in the literature, this thesis introduces a requirements framework for choreography languages and uses it for comparing current choreography languages. Language proposals for overcoming the limitations are given for choreography modeling on the conceptual and on the technical level. Using an interconnection modeling style, behavioral dependencies are defined on a per-role basis and different roles are interconnected using message flow. This thesis reveals a number of modeling "anti-patterns" for interconnection modeling, motivating further investigations on choreography languages following the interaction modeling style. Here, interactions are seen as atomic building blocks and the behavioral dependencies between them are defined globally. Two novel language proposals are put forward for this modeling style which have already influenced industrial standardization initiatives. While avoiding many of the pitfalls of interconnection modeling, new anomalies can arise in interaction models. A choreography might not be realizable, i.e. there does not exist a set of interacting roles that collectively realize the specified behavior. This thesis investigates different dimensions of realizability.}, language = {en} } @phdthesis{Semmo2016, author = {Semmo, Amir}, title = {Design and implementation of non-photorealistic rendering techniques for 3D geospatial data}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-99525}, school = {Universit{\"a}t Potsdam}, pages = {XVI, 155}, year = {2016}, abstract = {Geospatial data has become a natural part of a growing number of information systems and services in the economy, society, and people's personal lives. In particular, virtual 3D city and landscape models constitute valuable information sources within a wide variety of applications such as urban planning, navigation, tourist information, and disaster management. Today, these models are often visualized in detail to provide realistic imagery. However, a photorealistic rendering does not automatically lead to high image quality, with respect to an effective information transfer, which requires important or prioritized information to be interactively highlighted in a context-dependent manner. Approaches in non-photorealistic renderings particularly consider a user's task and camera perspective when attempting optimal expression, recognition, and communication of important or prioritized information. However, the design and implementation of non-photorealistic rendering techniques for 3D geospatial data pose a number of challenges, especially when inherently complex geometry, appearance, and thematic data must be processed interactively. Hence, a promising technical foundation is established by the programmable and parallel computing architecture of graphics processing units. This thesis proposes non-photorealistic rendering techniques that enable both the computation and selection of the abstraction level of 3D geospatial model contents according to user interaction and dynamically changing thematic information. To achieve this goal, the techniques integrate with hardware-accelerated rendering pipelines using shader technologies of graphics processing units for real-time image synthesis. The techniques employ principles of artistic rendering, cartographic generalization, and 3D semiotics—unlike photorealistic rendering—to synthesize illustrative renditions of geospatial feature type entities such as water surfaces, buildings, and infrastructure networks. In addition, this thesis contributes a generic system that enables to integrate different graphic styles—photorealistic and non-photorealistic—and provide their seamless transition according to user tasks, camera view, and image resolution. Evaluations of the proposed techniques have demonstrated their significance to the field of geospatial information visualization including topics such as spatial perception, cognition, and mapping. In addition, the applications in illustrative and focus+context visualization have reflected their potential impact on optimizing the information transfer regarding factors such as cognitive load, integration of non-realistic information, visualization of uncertainty, and visualization on small displays.}, language = {en} } @phdthesis{Boehne2019, author = {B{\"o}hne, Sebastian}, title = {Different degrees of formality}, doi = {10.25932/publishup-42379}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-423795}, school = {Universit{\"a}t Potsdam}, pages = {VI, 167}, year = {2019}, abstract = {In this thesis we introduce the concept of the degree of formality. It is directed against a dualistic point of view, which only distinguishes between formal and informal proofs. This dualistic attitude does not respect the differences between the argumentations classified as informal and it is unproductive because the individual potential of the respective argumentation styles cannot be appreciated and remains untapped. This thesis has two parts. In the first of them we analyse the concept of the degree of formality (including a discussion about the respective benefits for each degree) while in the second we demonstrate its usefulness in three case studies. In the first case study we will repair Haskell B. Curry's view of mathematics, which incidentally is of great importance in the first part of this thesis, in light of the different degrees of formality. In the second case study we delineate how awareness of the different degrees of formality can be used to help students to learn how to prove. Third, we will show how the advantages of proofs of different degrees of formality can be combined by the development of so called tactics having a medium degree of formality. Together the three case studies show that the degrees of formality provide a convincing solution to the problem of untapped potential.}, language = {en} } @phdthesis{Dick2016, author = {Dick, Uwe}, title = {Discriminative Classification Models for Internet Security}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-102593}, school = {Universit{\"a}t Potsdam}, pages = {x, 57}, year = {2016}, abstract = {Services that operate over the Internet are under constant threat of being exposed to fraudulent use. Maintaining good user experience for legitimate users often requires the classification of entities as malicious or legitimate in order to initiate countermeasures. As an example, inbound email spam filters decide for spam or non-spam. They can base their decision on both the content of each email as well as on features that summarize prior emails received from the sending server. In general, discriminative classification methods learn to distinguish positive from negative entities. Each decision for a label may be based on features of the entity and related entities. When labels of related entities have strong interdependencies---as can be assumed e.g. for emails being delivered by the same user---classification decisions should not be made independently and dependencies should be modeled in the decision function. This thesis addresses the formulation of discriminative classification problems that are tailored for the specific demands of the following three Internet security applications. Theoretical and algorithmic solutions are devised to protect an email service against flooding of user inboxes, to mitigate abusive usage of outbound email servers, and to protect web servers against distributed denial of service attacks. In the application of filtering an inbound email stream for unsolicited emails, utilizing features that go beyond each individual email's content can be valuable. Information about each sending mail server can be aggregated over time and may help in identifying unwanted emails. However, while this information will be available to the deployed email filter, some parts of the training data that are compiled by third party providers may not contain this information. The missing features have to be estimated at training time in order to learn a classification model. In this thesis an algorithm is derived that learns a decision function that integrates over a distribution of values for each missing entry. The distribution of missing values is a free parameter that is optimized to learn an optimal decision function. The outbound stream of emails of an email service provider can be separated by the customer IDs that ask for delivery. All emails that are sent by the same ID in the same period of time are related, both in content and in label. Hijacked customer accounts may send batches of unsolicited emails to other email providers, which in turn might blacklist the sender's email servers after detection of incoming spam emails. The risk of being blocked from further delivery depends on the rate of outgoing unwanted emails and the duration of high spam sending rates. An optimization problem is developed that minimizes the expected cost for the email provider by learning a decision function that assigns a limit on the sending rate to customers based on the each customer's email stream. Identifying attacking IPs during HTTP-level DDoS attacks allows to block those IPs from further accessing the web servers. DDoS attacks are usually carried out by infected clients that are members of the same botnet and show similar traffic patterns. HTTP-level attacks aim at exhausting one or more resources of the web server infrastructure, such as CPU time. If the joint set of attackers cannot increase resource usage close to the maximum capacity, no effect will be experienced by legitimate users of hosted web sites. However, if the additional load raises the computational burden towards the critical range, user experience will degrade until service may be unavailable altogether. As the loss of missing one attacker depends on block decisions for other attackers---if most other attackers are detected, not blocking one client will likely not be harmful---a structured output model has to be learned. In this thesis an algorithm is developed that learns a structured prediction decoder that searches the space of label assignments, guided by a policy. Each model is evaluated on real-world data and is compared to reference methods. The results show that modeling each classification problem according to the specific demands of the task improves performance over solutions that do not consider the constraints inherent to an application.}, language = {en} } @phdthesis{Makowski2021, author = {Makowski, Silvia}, title = {Discriminative Models for Biometric Identification using Micro- and Macro-Movements of the Eyes}, school = {Universit{\"a}t Potsdam}, pages = {xi, 91}, year = {2021}, abstract = {Human visual perception is an active process. Eye movements either alternate between fixations and saccades or follow a smooth pursuit movement in case of moving targets. Besides these macroscopic gaze patterns, the eyes perform involuntary micro-movements during fixations which are commonly categorized into micro-saccades, drift and tremor. Eye movements are frequently studied in cognitive psychology, because they reflect a complex interplay of perception, attention and oculomotor control. A common insight of psychological research is that macro-movements are highly individual. Inspired by this finding, there has been a considerable amount of prior research on oculomotoric biometric identification. However, the accuracy of known approaches is too low and the time needed for identification is too long for any practical application. This thesis explores discriminative models for the task of biometric identification. Discriminative models optimize a quality measure of the predictions and are usually superior to generative approaches in discriminative tasks. However, using discriminative models requires to select a suitable form of data representation for sequential eye gaze data; i.e., by engineering features or constructing a sequence kernel and the performance of the classification model strongly depends on the data representation. We study two fundamentally different ways of representing eye gaze within a discriminative framework. In the first part of this thesis, we explore the integration of data and psychological background knowledge in the form of generative models to construct representations. To this end, we first develop generative statistical models of gaze behavior during reading and scene viewing that account for viewer-specific distributional properties of gaze patterns. In a second step, we develop a discriminative identification model by deriving Fisher kernel functions from these and several baseline models. We find that an SVM with Fisher kernel is able to reliably identify users based on their eye gaze during reading and scene viewing. However, since the generative models are constrained to use low-frequency macro-movements, they discard a significant amount of information contained in the raw eye tracking signal at a high cost: identification requires about one minute of input recording, which makes it inapplicable for real world biometric systems. In the second part of this thesis, we study a purely data-driven modeling approach. Here, we aim at automatically discovering the individual pattern hidden in the raw eye tracking signal. To this end, we develop a deep convolutional neural network DeepEyedentification that processes yaw and pitch gaze velocities and learns a representation end-to-end. Compared to prior work, this model increases the identification accuracy by one order of magnitude and the time to identification decreases to only seconds. The DeepEyedentificationLive model further improves upon the identification performance by processing binocular input and it also detects presentation-attacks. We find that by learning a representation, the performance of oculomotoric identification and presentation-attack detection can be driven close to practical relevance for biometric applications. Eye tracking devices with high sampling frequency and precision are expensive and the applicability of eye movement as a biometric feature heavily depends on cost of recording devices. In the last part of this thesis, we therefore study the requirements on data quality by evaluating the performance of the DeepEyedentificationLive network under reduced spatial and temporal resolution. We find that the method still attains a high identification accuracy at a temporal resolution of only 250 Hz and a precision of 0.03 degrees. Reducing both does not have an additive deteriorating effect.}, language = {en} } @phdthesis{Dramlitsch2002, author = {Dramlitsch, Thomas}, title = {Distributed computations in a dynamic, heterogeneous Grid environment}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-0000759}, school = {Universit{\"a}t Potsdam}, year = {2002}, abstract = {Die immer dichtere und schnellere Vernetzung von Rechnern und Rechenzentren {\"u}ber Hochgeschwindigkeitsnetzwerke erm{\"o}glicht eine neue Art des wissenschaftlich verteilten Rechnens, bei der geographisch weit auseinanderliegende Rechenkapazit{\"a}ten zu einer Gesamtheit zusammengefasst werden k{\"o}nnen. Dieser so entstehende virtuelle Superrechner, der selbst aus mehreren Grossrechnern besteht, kann dazu genutzt werden Probleme zu berechnen, f{\"u}r die die einzelnen Grossrechner zu klein sind. Die Probleme, die numerisch mit heutigen Rechenkapazit{\"a}ten nicht l{\"o}sbar sind, erstrecken sich durch s{\"a}mtliche Gebiete der heutigen Wissenschaft, angefangen von Astrophysik, Molek{\"u}lphysik, Bioinformatik, Meteorologie, bis hin zur Zahlentheorie und Fluiddynamik um nur einige Gebiete zu nennen. Je nach Art der Problemstellung und des L{\"o}sungsverfahrens gestalten sich solche "Meta-Berechnungen" mehr oder weniger schwierig. Allgemein kann man sagen, dass solche Berechnungen um so schwerer und auch um so uneffizienter werden, je mehr Kommunikation zwischen den einzelnen Prozessen (oder Prozessoren) herrscht. Dies ist dadurch begr{\"u}ndet, dass die Bandbreiten bzw. Latenzzeiten zwischen zwei Prozessoren auf demselben Grossrechner oder Cluster um zwei bis vier Gr{\"o}ssenordnungen h{\"o}her bzw. niedriger liegen als zwischen Prozessoren, welche hunderte von Kilometern entfernt liegen. Dennoch bricht nunmehr eine Zeit an, in der es m{\"o}glich ist Berechnungen auf solch virtuellen Supercomputern auch mit kommunikationsintensiven Programmen durchzuf{\"u}hren. Eine grosse Klasse von kommunikations- und berechnungsintensiven Programmen ist diejenige, die die L{\"o}sung von Differentialgleichungen mithilfe von finiten Differenzen zum Inhalt hat. Gerade diese Klasse von Programmen und deren Betrieb in einem virtuellen Superrechner wird in dieser vorliegenden Dissertation behandelt. Methoden zur effizienteren Durchf{\"u}hrung von solch verteilten Berechnungen werden entwickelt, analysiert und implementiert. Der Schwerpunkt liegt darin vorhandene, klassische Parallelisierungsalgorithmen zu analysieren und so zu erweitern, dass sie vorhandene Informationen (z.B. verf{\"u}gbar durch das Globus Toolkit) {\"u}ber Maschinen und Netzwerke zur effizienteren Parallelisierung nutzen. Soweit wir wissen werden solche Zusatzinformationen kaum in relevanten Programmen genutzt, da der Grossteil aller Parallelisierungsalgorithmen implizit f{\"u}r die Ausf{\"u}hrung auf Grossrechnern oder Clustern entwickelt wurde.}, language = {en} } @phdthesis{Zarezadeh2012, author = {Zarezadeh, Aliakbar}, title = {Distributed smart cameras : architecture and communication protocols}, address = {Potsdam}, pages = {135 S.}, year = {2012}, language = {en} } @phdthesis{Off2011, author = {Off, Thomas}, title = {Durchg{\"a}ngige Verfolgbarkeit im Vorfeld der Softwareentwicklung von E-Government-Anwendungen : ein ontologiebasierter und modellgetriebener Ansatz am Beispiel von B{\"u}rgerdiensten}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-57478}, school = {Universit{\"a}t Potsdam}, year = {2011}, abstract = {Die {\"o}ffentliche Verwaltung setzt seit mehreren Jahren E-Government-Anwendungssysteme ein, um ihre Verwaltungsprozesse intensiver mit moderner Informationstechnik zu unterst{\"u}tzen. Da die {\"o}ffentliche Verwaltung in ihrem Handeln in besonderem Maße an Recht und Gesetz gebunden ist verst{\"a}rkt und verbreitet sich der Zusammenhang zwischen den Gesetzen und Rechtsvorschriften einerseits und der zur Aufgabenunterst{\"u}tzung eingesetzten Informationstechnik andererseits. Aus Sicht der Softwaretechnik handelt es sich bei diesem Zusammenhang um eine spezielle Form der Verfolgbarkeit von Anforderungen (engl. Traceability), die so genannte Verfolgbarkeit im Vorfeld der Anforderungsspezifikation (Pre-Requirements Specification Traceability, kurz Pre-RS Traceability), da sie Aspekte betrifft, die relevant sind, bevor die Anforderungen in eine Spezifikation eingeflossen sind (Urspr{\"u}nge von Anforderungen). Der Ansatz dieser Arbeit leistet einen Beitrag zur Verfolgbarkeit im Vorfeld der Anforderungsspezifikation von E-Government-Anwendungssystemen. Er kombiniert dazu aktuelle Entwicklungen und Standards (insbesondere des World Wide Web Consortium und der Object Management Group) aus den Bereichen Verfolgbarkeit von Anforderungen, Semantic Web, Ontologiesprachen und modellgetriebener Softwareentwicklung. Der L{\"o}sungsansatz umfasst eine spezielle Ontologie des Verwaltungshandeln, die mit den Techniken, Methoden und Werkzeugen des Semantic Web eingesetzt wird, um in Texten von Rechtsvorschriften relevante Urspr{\"u}nge von Anforderungen durch Annotationen mit einer definierten Semantik zu versehen. Darauf aufbauend wird das Ontology Definition Metamodel (ODM) verwendet, um die Annotationen als spezielle Individuen einer Ontologie auf Elemente der Unified Modeling Language (UML) abzubilden. Dadurch entsteht ein neuer Modelltyp Pre-Requirements Model (PRM), der das Vorfeld der Anforderungsspezifikation formalisiert. Modelle diesen Typs k{\"o}nnen auch verwendet werden, um Aspekte zu formalisieren die sich nicht oder nicht vollst{\"a}ndig aus dem Text der Rechtsvorschrift ergeben. Weiterhin bietet das Modell die M{\"o}glichkeit zum Anschluss an die modellgetriebene Softwareentwicklung. In der Arbeit wird deshalb eine Erweiterung der Model Driven Architecture (MDA) vorgeschlagen. Zus{\"a}tzlich zu den etablierten Modelltypen Computation Independent Model (CIM), Platform Independent Model (PIM) und Platform Specific Model (PSM) k{\"o}nnte der Einsatz des PRM Vorteile f{\"u}r die Verfolgbarkeit bringen. Wird die MDA mit dem PRM auf das Vorfeld der Anforderungsspezifikation ausgeweitet, kann eine Transformation des PRM in ein CIM als initiale Anforderungsspezifikation erfolgen, indem der MOF Query View Transformation Standard (QVT) eingesetzt wird. Als Teil des QVT-Standards ist die Aufzeichnung von Verfolgbarkeitsinformationen bei Modelltransformationen verbindlich. Um die semantische L{\"u}cke zwischen PRM und CIM zu {\"u}berbr{\"u}cken, erfolgt analog zum Einsatz des Plattformmodells (PM) in der PIM nach PSM Transformation der Einsatz spezieller Hilfsmodelle. Es kommen daf{\"u}r die im Projekt "E-LoGo" an der Universit{\"a}t Potsdam entwickelten Referenzmodelle zum Einsatz. Durch die Aufzeichnung der Abbildung annotierter Textelemente auf Elemente im PRM und der Transformation der Elemente des PRM in Elemente des CIM kann durchg{\"a}ngige Verfolgbarkeit im Vorfeld der Anforderungsspezifikation erreicht werden. Der Ansatz basiert auf einer so genannten Verfolgbarkeitsdokumentation in Form verlinkter Hypertextdokumente, die mittels XSL-Stylesheet erzeugt wurden und eine Verbindung zur graphischen Darstellung des Diagramms (z. B. Anwendungsfall-, Klassendiagramm der UML) haben. Der Ansatz unterst{\"u}tzt die horizontale Verfolgbarkeit zwischen Elementen unterschiedlicher Modelle vorw{\"a}rts- und r{\"u}ckw{\"a}rtsgerichtet umfassend. Er bietet außerdem vertikale Verfolgbarkeit, die Elemente des gleichen Modells und verschiedener Modellversionen in Beziehung setzt. {\"U}ber den offensichtlichen Nutzen einer durchg{\"a}ngigen Verfolgbarkeit im Vorfeld der Anforderungsspezifikation (z. B. Analyse der Auswirkungen einer Gesetzes{\"a}nderung, Ber{\"u}cksichtigung des vollst{\"a}ndigen Kontextes einer Anforderung bei ihrer Priorisierung) hinausgehend, bietet diese Arbeit eine erste Ansatzm{\"o}glichkeit f{\"u}r eine Feedback-Schleife im Prozess der Gesetzgebung. Stehen beispielsweise mehrere gleichwertige Gestaltungsoptionen eines Gesetzes zur Auswahl, k{\"o}nnen die Auswirkungen jeder Option analysiert und der Aufwand ihrer Umsetzung in E-Government-Anwendungen als Auswahlkriterium ber{\"u}cksichtigt werden. Die am 16. M{\"a}rz 2011 in Kraft getretene {\"A}nderung des NKRG schreibt eine solche Analyse des so genannten „Erf{\"u}llungsaufwands" f{\"u}r Teilbereiche des Verwaltungshandelns bereits heute verbindlich vor. F{\"u}r diese Analyse kann die vorliegende Arbeit einen Ansatz bieten, um zu fundierten Aussagen {\"u}ber den {\"A}nderungsaufwand eingesetzter E-Government-Anwendungssysteme zu kommen.}, language = {de} } @phdthesis{Schmidt1995, author = {Schmidt, Henning}, title = {Dynamisch ver{\"a}nderbare Betriebssystemstrukturen}, pages = {XII, 141 S.}, year = {1995}, language = {de} } @phdthesis{Troeger2008, author = {Tr{\"o}ger, Peter}, title = {Dynamische Ressourcenverwaltung f{\"u}r dienstbasierte Software-Systeme}, publisher = {Cuvillier}, address = {G{\"o}ttingen}, isbn = {978-3-86727-622-1}, pages = {v, 174 S.: Ill., garph. Darst.}, year = {2008}, language = {de} } @phdthesis{Troeger2008, author = {Tr{\"o}ger, Peter}, title = {Dynamische Ressourcenverwaltung f{\"u}r dienstbasierte Software-Systeme}, address = {Potsdam}, pages = {174 S., graph. Darst.}, year = {2008}, language = {de} } @phdthesis{Jung2015, author = {Jung, J{\"o}rg}, title = {Efficient credit based server load balancing}, school = {Universit{\"a}t Potsdam}, pages = {353}, year = {2015}, language = {en} } @phdthesis{Marienfeld2007, author = {Marienfeld, Daniel}, title = {Effiziente Fehlerkennung f{\"u}r arithmetische Einheiten}, address = {Potsdam}, pages = {VIII, 122 S. : graph. Darst.}, year = {2007}, language = {de} } @phdthesis{Quasthoff2011, author = {Quasthoff, Matthias}, title = {Effizientes Entwickeln von Semantic-Web-Software mit Object Triple Mapping}, address = {Potsdam}, pages = {138 S.}, year = {2011}, language = {de} } @phdthesis{Rostock2002, author = {Rostock, Gisbert}, title = {Ein polynomialer Algorithmus zur Erkennung von Isomorphie von Graphen}, pages = {63 S.}, year = {2002}, language = {de} } @phdthesis{Kiertscher2017, author = {Kiertscher, Simon}, title = {Energieeffizientes Clustermanagement im Server-Load-Balacing-Bereich, am Fallbeispiel eines Apache-Webserver-Clusters}, school = {Universit{\"a}t Potsdam}, pages = {185}, year = {2017}, language = {de} } @phdthesis{Tiwari2019, author = {Tiwari, Abhishek}, title = {Enhancing Users' Privacy: Static Resolution of the Dynamic Properties of Android}, school = {Universit{\"a}t Potsdam}, pages = {xiii, 111}, year = {2019}, abstract = {The usage of mobile devices is rapidly growing with Android being the most prevalent mobile operating system. Thanks to the vast variety of mobile applications, users are preferring smartphones over desktops for day to day tasks like Internet surfing. Consequently, smartphones store a plenitude of sensitive data. This data together with the high values of smartphones make them an attractive target for device/data theft (thieves/malicious applications). Unfortunately, state-of-the-art anti-theft solutions do not work if they do not have an active network connection, e.g., if the SIM card was removed from the device. In the majority of these cases, device owners permanently lose their smartphone together with their personal data, which is even worse. Apart from that malevolent applications perform malicious activities to steal sensitive information from smartphones. Recent research considered static program analysis to detect dangerous data leaks. These analyses work well for data leaks due to inter-component communication, but suffer from shortcomings for inter-app communication with respect to precision, soundness, and scalability. This thesis focuses on enhancing users' privacy on Android against physical device loss/theft and (un)intentional data leaks. It presents three novel frameworks: (1) ThiefTrap, an anti-theft framework for Android, (2) IIFA, a modular inter-app intent information flow analysis of Android applications, and (3) PIAnalyzer, a precise approach for PendingIntent vulnerability analysis. ThiefTrap is based on a novel concept of an anti-theft honeypot account that protects the owner's data while preventing a thief from resetting the device. We implemented the proposed scheme and evaluated it through an empirical user study with 35 participants. In this study, the owner's data could be protected, recovered, and anti-theft functionality could be performed unnoticed from the thief in all cases. IIFA proposes a novel approach for Android's inter-component/inter-app communication (ICC/IAC) analysis. Our main contribution is the first fully automatic, sound, and precise ICC/IAC information flow analysis that is scalable for realistic apps due to modularity, avoiding combinatorial explosion: Our approach determines communicating apps using short summaries rather than inlining intent calls between components and apps, which requires simultaneously analyzing all apps installed on a device. We evaluate IIFA in terms of precision, recall, and demonstrate its scalability to a large corpus of real-world apps. IIFA reports 62 problematic ICC-/IAC-related information flows via two or more apps/components. PIAnalyzer proposes a novel approach to analyze PendingIntent related vulnerabilities. PendingIntents are a powerful and universal feature of Android for inter-component communication. We empirically evaluate PIAnalyzer on a set of 1000 randomly selected applications and find 1358 insecure usages of PendingIntents, including 70 severe vulnerabilities.}, language = {en} } @phdthesis{AbuJarour2011, author = {AbuJarour, Mohammed}, title = {Enriched service descriptions: sources, approaches and usages}, address = {Potsdam}, pages = {140 S.}, year = {2011}, 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{Krueger2014, author = {Kr{\"u}ger, Jens}, title = {Enterprise-specific in-memory data managment : HYRISEc - an in-memory column store engine for OLXP}, publisher = {Hasso-Plattner-Insitut}, address = {Potsdam}, pages = {201 S.}, year = {2014}, language = {en} } @phdthesis{Petrasch1999, author = {Petrasch, Roland}, title = {Entwicklung von Modelltypen f{\"u}r das Qualit{\"a}tsmanagement in der Software-Entwicklung am Beispiel von ausgew{\"a}hlten Qualit{\"a}tssicherungsmaßnahmen}, pages = {Bl. i - viii; 173 Bl. : graph. Darst.}, year = {1999}, language = {de} } @phdthesis{Moschanin1999, author = {Moschanin, Wladimir}, title = {Entwurf selbstdualer digitaler Schaltungen zur Fehlererkennung}, address = {Potsdam}, pages = {III, 94 S. : graph. Darst.}, year = {1999}, language = {de} } @phdthesis{Kirsch2005, author = {Kirsch, Florian}, title = {Entwurf und Implementierung eines computergraphischen Systems zur Integration komplexer, echtzeitf{\"a}higer 3D-Renderingverfahren}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-6079}, school = {Universit{\"a}t Potsdam}, year = {2005}, abstract = {Thema dieser Arbeit sind echtzeitf{\"a}hige 3D-Renderingverfahren, die 3D-Geometrie mit {\"u}ber der Standarddarstellung hinausgehenden Qualit{\"a}ts- und Gestaltungsmerkmalen rendern k{\"o}nnen. Beispiele sind Verfahren zur Darstellung von Schatten, Reflexionen oder Transparenz. Mit heutigen computergraphischen Software-Basissystemen ist ihre Integration in 3D-Anwendungssysteme sehr aufw{\"a}ndig: Dies liegt einerseits an der technischen, algorithmischen Komplexit{\"a}t der Einzelverfahren, andererseits an Ressourcenkonflikten und Seiteneffekten bei der Kombination mehrerer Verfahren. Szenengraphsysteme, intendiert als computergraphische Softwareschicht zur Abstraktion von der Graphikhardware, stellen derzeit keine Mechanismen zur Nutzung dieser Renderingverfahren zur Verf{\"u}gung. Ziel dieser Arbeit ist es, eine Software-Architektur f{\"u}r ein Szenengraphsystem zu konzipieren und umzusetzen, die echtzeitf{\"a}hige 3D-Renderingverfahren als Komponenten modelliert und es damit erlaubt, diese Verfahren innerhalb des Szenengraphsystems f{\"u}r die Anwendungsentwicklung effektiv zu nutzen. Ein Entwickler, der ein solches Szenengraphsystem nutzt, steuert diese Komponenten durch Elemente in der Szenenbeschreibung an, die die sichtbare Wirkung eines Renderingverfahrens auf die Geometrie in der Szene angeben, aber keine Hinweise auf die algorithmische Implementierung des Verfahrens enthalten. Damit werden Renderingverfahren in 3D-Anwendungssystemen nutzbar, ohne dass ein Entwickler detaillierte Kenntnisse {\"u}ber sie ben{\"o}tigt, so dass der Aufwand f{\"u}r ihre Entwicklung drastisch reduziert wird. Ein besonderer Augenmerk der Arbeit liegt darauf, auf diese Weise auch verschiedene Renderingverfahren in einer Szene kombiniert einsetzen zu k{\"o}nnen. Hierzu ist eine Unterteilung der Renderingverfahren in mehrere Kategorien erforderlich, die mit Hilfe unterschiedlicher Ans{\"a}tze ausgewertet werden. Dies erlaubt die Abstimmung verschiedener Komponenten f{\"u}r Renderingverfahren und ihrer verwendeten Ressourcen. Die Zusammenarbeit mehrerer Renderingverfahren hat dort ihre Grenzen, wo die Kombination von Renderingverfahren graphisch nicht sinnvoll ist oder fundamentale technische Beschr{\"a}nkungen der Verfahren eine gleichzeitige Verwendung unm{\"o}glich machen. Die in dieser Arbeit vorgestellte Software-Architektur kann diese Grenzen nicht verschieben, aber sie erm{\"o}glicht den gleichzeitigen Einsatz vieler Verfahren, bei denen eine Kombination aufgrund der hohen Komplexit{\"a}t der Implementierung bislang nicht erreicht wurde. Das Verm{\"o}gen zur Zusammenarbeit ist dabei allerdings von der Art eines Einzelverfahrens abh{\"a}ngig: Verfahren zur Darstellung transparenter Geometrie beispielsweise erfordern bei der Kombination mit anderen Verfahren in der Regel vollst{\"a}ndig neuentwickelte Renderingverfahren; entsprechende Komponenten f{\"u}r das Szenengraphsystem k{\"o}nnen daher nur eingeschr{\"a}nkt mit Komponenten f{\"u}r andere Renderingverfahren verwendet werden. Das in dieser Arbeit entwickelte System integriert und kombiniert Verfahren zur Darstellung von Bumpmapping, verschiedene Schatten- und Reflexionsverfahren sowie bildbasiertes CSG-Rendering. Damit stehen wesentliche Renderingverfahren in einem Szenengraphsystem erstmalig komponentenbasiert und auf einem hohen Abstraktionsniveau zur Verf{\"u}gung. Das System ist trotz des zus{\"a}tzlichen Verwaltungsaufwandes in der Lage, die Renderingverfahren einzeln und in Kombination grunds{\"a}tzlich in Echtzeit auszuf{\"u}hren.}, subject = {Dreidimensionale Computergraphik}, language = {de} } @phdthesis{Otscheretnij2003, author = {Otscheretnij, Vitalij}, title = {Entwurf von fehlertoleranten kompinatorischen Schaltungen}, pages = {80 S.}, year = {2003}, language = {de} } @phdthesis{Morosov1996, author = {Morosov, Andrej}, title = {Entwurf von selbstpr{\"u}fenden digitalen Schaltungen mit monoton unabh{\"a}ngigen Ausg{\"a}ngen}, pages = {85 S.}, year = {1996}, language = {de} } @phdthesis{Muehlbauer2011, author = {M{\"u}hlbauer, Felix}, title = {Entwurf, Methoden und Werkzeuge f{\"u}r komplexe Bildverarbeitungssysteme auf Rekonfigurierbaren System-on-Chip-Architekturen}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-59923}, school = {Universit{\"a}t Potsdam}, year = {2011}, abstract = {Bildverarbeitungsanwendungen stellen besondere Anspr{\"u}che an das ausf{\"u}hrende Rechensystem. Einerseits ist eine hohe Rechenleistung erforderlich. Andererseits ist eine hohe Flexibilit{\"a}t von Vorteil, da die Entwicklung tendentiell ein experimenteller und interaktiver Prozess ist. F{\"u}r neue Anwendungen tendieren Entwickler dazu, eine Rechenarchitektur zu w{\"a}hlen, die sie gut kennen, anstatt eine Architektur einzusetzen, die am besten zur Anwendung passt. Bildverarbeitungsalgorithmen sind inh{\"a}rent parallel, doch herk{\"o}mmliche bildverarbeitende eingebettete Systeme basieren meist auf sequentiell arbeitenden Prozessoren. Im Gegensatz zu dieser "Unstimmigkeit" k{\"o}nnen hocheffiziente Systeme aus einer gezielten Synergie aus Software- und Hardwarekomponenten aufgebaut werden. Die Konstruktion solcher System ist jedoch komplex und viele L{\"o}sungen, wie zum Beispiel grobgranulare Architekturen oder anwendungsspezifische Programmiersprachen, sind oft zu akademisch f{\"u}r einen Einsatz in der Wirtschaft. Die vorliegende Arbeit soll ein Beitrag dazu leisten, die Komplexit{\"a}t von Hardware-Software-Systemen zu reduzieren und damit die Entwicklung hochperformanter on-Chip-Systeme im Bereich Bildverarbeitung zu vereinfachen und wirtschaftlicher zu machen. Dabei wurde Wert darauf gelegt, den Aufwand f{\"u}r Einarbeitung, Entwicklung als auch Erweiterungen gering zu halten. Es wurde ein Entwurfsfluss konzipiert und umgesetzt, welcher es dem Softwareentwickler erm{\"o}glicht, Berechnungen durch Hardwarekomponenten zu beschleunigen und das zu Grunde liegende eingebettete System komplett zu prototypisieren. Hierbei werden komplexe Bildverarbeitungsanwendungen betrachtet, welche ein Betriebssystem erfordern, wie zum Beispiel verteilte Kamerasensornetzwerke. Die eingesetzte Software basiert auf Linux und der Bildverarbeitungsbibliothek OpenCV. Die Verteilung der Berechnungen auf Software- und Hardwarekomponenten und die daraus resultierende Ablaufplanung und Generierung der Rechenarchitektur erfolgt automatisch. Mittels einer auf der Antwortmengenprogrammierung basierten Entwurfsraumexploration ergeben sich Vorteile bei der Modellierung und Erweiterung. Die Systemsoftware wird mit OpenEmbedded/Bitbake synthetisiert und die erzeugten on-Chip-Architekturen auf FPGAs realisiert.}, language = {de} } @phdthesis{Lincke2014, author = {Lincke, Jens}, title = {Evolving Tools in a Collaborative Self-supporting Development Environment}, school = {Universit{\"a}t Potsdam}, pages = {164}, year = {2014}, language = {en} } @phdthesis{Freund2006, author = {Freund, Tessen}, title = {Experimentelles Software Engineering durch Modellierung wissensintensiver Entwicklungsprozesse}, address = {Potsdam}, pages = {XII, 316 S. : graph. Darst.}, year = {2006}, language = {de} } @phdthesis{Appeltauer2012, author = {Appeltauer, Malte}, title = {Extending Context-oriented Programming to New Application Domains: Run-time Adaptation Support for Java}, address = {Potsdam}, pages = {157 S.}, year = {2012}, 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{Repp2009, author = {Repp, Stephan}, title = {Extraktion von semantischen Informationen aus audivisuellen Vorlesungsaufzeichnungen : Sprachskripte der Vorlesungsvideos als Informationsressource}, address = {Potsdam}, pages = {183 S.}, year = {2009}, language = {de} } @phdthesis{Kuznetsov2007, author = {Kuznetsov, Grigory}, title = {Fehlererkennung in systemmetrischen Block-Chiffren}, address = {Potsdam}, pages = {118 S. : graph. Darst.}, year = {2007}, language = {de} } @phdthesis{Nordmann2020, author = {Nordmann, Paul-Patrick}, title = {Fehlerkorrektur von Speicherfehlern mit Low-Density-Parity-Check-Codes}, doi = {10.25932/publishup-48048}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-480480}, school = {Universit{\"a}t Potsdam}, pages = {IV, 99, XII}, year = {2020}, abstract = {Die Fehlerkorrektur in der Codierungstheorie besch{\"a}ftigt sich mit der Erkennung und Behebung von Fehlern bei der {\"U}bertragung und auch Sicherung von Nachrichten. Hierbei wird die Nachricht durch zus{\"a}tzliche Informationen in ein Codewort kodiert. Diese Kodierungsverfahren besitzen verschiedene Anspr{\"u}che, wie zum Beispiel die maximale Anzahl der zu korrigierenden Fehler und die Geschwindigkeit der Korrektur. Ein g{\"a}ngiges Codierungsverfahren ist der BCH-Code, welches industriell f{\"u}r bis zu vier Fehler korrigiere Codes Verwendung findet. Ein Nachteil dieser Codes ist die technische Durchlaufzeit f{\"u}r die Berechnung der Fehlerstellen mit zunehmender Codel{\"a}nge. Die Dissertation stellt ein neues Codierungsverfahren vor, bei dem durch spezielle Anordnung kleinere Codel{\"a}ngen eines BCH-Codes ein langer Code erzeugt wird. Diese Anordnung geschieht {\"u}ber einen weiteren speziellen Code, einem LDPC-Code, welcher f{\"u}r eine schneller Fehlererkennung konzipiert ist. Hierf{\"u}r wird ein neues Konstruktionsverfahren vorgestellt, welches einen Code f{\"u}r einen beliebige L{\"a}nge mit vorgebbaren beliebigen Anzahl der zu korrigierenden Fehler vorgibt. Das vorgestellte Konstruktionsverfahren erzeugt zus{\"a}tzlich zum schnellen Verfahren der Fehlererkennung auch eine leicht und schnelle Ableitung eines Verfahrens zu Kodierung der Nachricht zum Codewort. Dies ist in der Literatur f{\"u}r die LDPC-Codes bis zum jetzigen Zeitpunkt einmalig. Durch die Konstruktion eines LDPC-Codes wird ein Verfahren vorgestellt wie dies mit einem BCH-Code kombiniert wird, wodurch eine Anordnung des BCH-Codes in Bl{\"o}cken erzeugt wird. Neben der allgemeinen Beschreibung dieses Codes, wird ein konkreter Code f{\"u}r eine 2-Bitfehlerkorrektur beschrieben. Diese besteht aus zwei Teilen, welche in verschiedene Varianten beschrieben und verglichen werden. F{\"u}r bestimmte L{\"a}ngen des BCH-Codes wird ein Problem bei der Korrektur aufgezeigt, welche einer algebraischen Regel folgt. Der BCH-Code wird sehr allgemein beschrieben, doch existiert durch bestimmte Voraussetzungen ein BCH-Code im engerem Sinne, welcher den Standard vorgibt. Dieser BCH-Code im engerem Sinne wird in dieser Dissertation modifiziert, so dass das algebraische Problem bei der 2-Bitfehler Korrektur bei der Kombination mit dem LDPC-Code nicht mehr existiert. Es wird gezeigt, dass nach der Modifikation der neue Code weiterhin ein BCH-Code im allgemeinen Sinne ist, welcher 2-Bitfehler korrigieren und 3-Bitfehler erkennen kann. Bei der technischen Umsetzung der Fehlerkorrektur wird des Weiteren gezeigt, dass die Durchlaufzeiten des modifizierten Codes im Vergleich zum BCH-Code schneller ist und weiteres Potential f{\"u}r Verbesserungen besitzt. Im letzten Kapitel wird gezeigt, dass sich dieser modifizierte Code mit beliebiger L{\"a}nge eignet f{\"u}r die Kombination mit dem LDPC-Code, wodurch dieses Verfahren nicht nur umf{\"a}nglicher in der L{\"a}nge zu nutzen ist, sondern auch durch die schnellere Dekodierung auch weitere Vorteile gegen{\"u}ber einem BCH-Code im engerem Sinne besitzt.}, 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{Przybylla2018, author = {Przybylla, Mareen}, title = {From Embedded Systems to Physical Computing: Challenges of the "Digital World" in Secondary Computer Science Education}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-418339}, school = {Universit{\"a}t Potsdam}, pages = {xvii, 277}, year = {2018}, abstract = {Physical computing covers the design and realization of interactive objects and installations and allows learners to develop concrete, tangible products of the real world, which arise from their imagination. This can be used in computer science education to provide learners with interesting and motivating access to the different topic areas of the subject in constructionist and creative learning environments. However, if at all, physical computing has so far mostly been taught in afternoon clubs or other extracurricular settings. Thus, for the majority of students so far there are no opportunities to design and create their own interactive objects in regular school lessons. Despite its increasing popularity also for schools, the topic has not yet been clearly and sufficiently characterized in the context of computer science education. The aim of this doctoral thesis therefore is to clarify physical computing from the perspective of computer science education and to adequately prepare the topic both content-wise and methodologically for secondary school teaching. For this purpose, teaching examples, activities, materials and guidelines for classroom use are developed, implemented and evaluated in schools. In the theoretical part of the thesis, first the topic is examined from a technical point of view. A structured literature analysis shows that basic concepts used in physical computing can be derived from embedded systems, which are the core of a large field of different application areas and disciplines. Typical methods of physical computing in professional settings are analyzed and, from an educational perspective, elements suitable for computer science teaching in secondary schools are extracted, e. g. tinkering and prototyping. The investigation and classification of suitable tools for school teaching show that microcontrollers and mini computers, often with extensions that greatly facilitate the handling of additional components, are particularly attractive tools for secondary education. Considering the perspectives of science, teachers, students and society, in addition to general design principles, exemplary teaching approaches for school education and suitable learning materials are developed and the design, production and evaluation of a physical computing construction kit suitable for teaching is described. In the practical part of this thesis, with "My Interactive Garden", an exemplary approach to integrate physical computing in computer science teaching is tested and evaluated in different courses and refined based on the findings in a design-based research approach. In a series of workshops on physical computing, which is based on a concept for constructionist professional development that is developed specifically for this purpose, teachers are empowered and encouraged to develop and conduct physical computing lessons suitable for their particular classroom settings. Based on their in-class experiences, a process model of physical computing teaching is derived. Interviews with those teachers illustrate that benefits of physical computing, including the tangibility of crafted objects and creativity in the classroom, outweigh possible drawbacks like longer preparation times, technical difficulties or difficult assessment. Hurdles in the classroom are identified and possible solutions discussed. Empirical investigations in the different settings reveal that "My Interactive Garden" and physical computing in general have a positive impact, among others, on learner motivation, fun and interest in class and perceived competencies. Finally, the results from all evaluations are combined to evaluate the design principles for physical computing teaching and to provide a perspective on the development of decision-making aids for physical computing activities in school education.}, language = {en} } @phdthesis{Zoerner2021, author = {Zoerner, Dietmar}, title = {F{\"o}rderung von Aufmerksamkeit und Motivationserhalt durch digitale spielbasierte Lernsysteme mit spezifischer Eignung bei Autismus}, doi = {10.25932/publishup-52372}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-523725}, school = {Universit{\"a}t Potsdam}, pages = {xvi, 324}, year = {2021}, abstract = {Institutionelle Bildung ist f{\"u}r autistische Lernende mit vielgestaltigen und spezifischen Hindernissen verbunden. Dies gilt insbesondere im Zusammenhang mit Inklusion, deren Relevanz nicht zuletzt durch das {\"U}bereinkommen der Vereinten Nationen {\"u}ber die Rechte von Menschen mit Behinderung gegeben ist. Diese Arbeit diskutiert zahlreiche lernrelevante Besonderheiten im Kontext von Autismus und zeigt Diskrepanzen zu den nicht immer ausreichend angemessenen institutionellen Lehrkonzepten. Eine zentrale These ist hierbei, dass die ungew{\"o}hnlich intensive Aufmerksamkeit von Autist*innen f{\"u}r ihre Spezialinteressen daf{\"u}r genutzt werden kann, das Lernen mit fremdgestellten Inhalten zu erleichtern. Darauf aufbauend werden L{\"o}sungsans{\"a}tze diskutiert, welche in einem neuartigen Konzept f{\"u}r ein digitales mehrger{\"a}tebasiertes Lernspiel resultieren. Eine wesentliche Herausforderung bei der Konzeption spielbasierten Lernens besteht in der ad{\"a}quaten Einbindung von Lerninhalten in einen fesselnden narrativen Kontext. Am Beispiel von {\"U}bungen zur emotionalen Deutung von Mimik, welche f{\"u}r das Lernen von sozioemotionalen Kompetenzen besonders im Rahmen von Therapiekonzepten bei Autismus Verwendung finden, wird eine angemessene Narration vorgestellt, welche die st{\"o}rungsarme Einbindung dieser sehr speziellen Lerninhalte erm{\"o}glicht. Die Effekte der einzelnen Konzeptionselemente werden anhand eines prototypisch entwickelten Lernspiels untersucht. Darauf aufbauend zeigt eine quantitative Studie die gute Akzeptanz und Nutzerfreundlichkeit des Spiels und belegte vor allem die Verst{\"a}ndlichkeit der Narration und der Spielelemente. Ein weiterer Schwerpunkt liegt in der minimalinvasiven Untersuchung m{\"o}glicher St{\"o}rungen des Spielerlebnisses durch den Wechsel zwischen verschiedenen Endger{\"a}ten, f{\"u}r die ein innovatives Messverfahren entwickelt wurde. Im Ergebnis beleuchtet diese Arbeit die Bedeutung und die Grenzen von spielbasierten Ans{\"a}tzen f{\"u}r autistische Lernende. Ein großer Teil der vorgestellten Konzepte l{\"a}sst sich auf andersartige Lernszenarien {\"u}bertragen. Das daf{\"u}r entwickelte technische Framework zur Realisierung narrativer Lernpfade ist ebenfalls darauf vorbereitet, f{\"u}r weitere Lernszenarien, gerade auch im institutionellen Kontext, Verwendung zu finden.}, language = {de} } @phdthesis{Rzeha2007, author = {Rzeha, Jan}, title = {Generation and Storage of Diagnosis Data On-Chip}, address = {Potsdam}, pages = {VII, 94 S. : graph. Darst.}, year = {2007}, language = {en} } @phdthesis{Middelanis2023, author = {Middelanis, Robin}, title = {Global response to local extremes—a storyline approach on economic loss propagation from weather extremes}, doi = {10.25932/publishup-61112}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-611127}, school = {Universit{\"a}t Potsdam}, pages = {vii, 237}, year = {2023}, abstract = {Due to anthropogenic greenhouse gas emissions, Earth's average surface temperature is steadily increasing. As a consequence, many weather extremes are likely to become more frequent and intense. This poses a threat to natural and human systems, with local impacts capable of destroying exposed assets and infrastructure, and disrupting economic and societal activity. Yet, these effects are not locally confined to the directly affected regions, as they can trigger indirect economic repercussions through loss propagation along supply chains. As a result, local extremes yield a potentially global economic response. To build economic resilience and design effective adaptation measures that mitigate adverse socio-economic impacts of ongoing climate change, it is crucial to gain a comprehensive understanding of indirect impacts and the underlying economic mechanisms. Presenting six articles in this thesis, I contribute towards this understanding. To this end, I expand on local impacts under current and future climate, the resulting global economic response, as well as the methods and tools to analyze this response. Starting with a traditional assessment of weather extremes under climate change, the first article investigates extreme snowfall in the Northern Hemisphere until the end of the century. Analyzing an ensemble of global climate model projections reveals an increase of the most extreme snowfall, while mean snowfall decreases. Assessing repercussions beyond local impacts, I employ numerical simulations to compute indirect economic effects from weather extremes with the numerical agent-based shock propagation model Acclimate. This model is used in conjunction with the recently emerged storyline framework, which involves analyzing the impacts of a particular reference extreme event and comparing them to impacts in plausible counterfactual scenarios under various climate or socio-economic conditions. Using this approach, I introduce three primary storylines that shed light on the complex mechanisms underlying economic loss propagation. In the second and third articles of this thesis, I analyze storylines for the historical Hurricanes Sandy (2012) and Harvey (2017) in the USA. For this, I first estimate local economic output losses and then simulate the resulting global economic response with Acclimate. The storyline for Hurricane Sandy thereby focuses on global consumption price anomalies and the resulting changes in consumption. I find that the local economic disruption leads to a global wave-like economic price ripple, with upstream effects propagating in the supplier direction and downstream effects in the buyer direction. Initially, an upstream demand reduction causes consumption price decreases, followed by a downstream supply shortage and increasing prices, before the anomalies decay in a normalization phase. A dominant upstream or downstream effect leads to net consumption gains or losses of a region, respectively. Moreover, I demonstrate that a longer direct economic shock intensifies the downstream effect for many regions, leading to an overall consumption loss. The third article of my thesis builds upon the developed loss estimation method by incorporating projections to future global warming levels. I use these projections to explore how the global production response to Hurricane Harvey would change under further increased global warming. The results show that, while the USA is able to nationally offset direct losses in the reference configuration, other countries have to compensate for increasing shares of counterfactual future losses. This compensation is mainly achieved by large exporting countries, but gradually shifts towards smaller regions. These findings not only highlight the economy's ability to flexibly mitigate disaster losses to a certain extent, but also reveal the vulnerability and economic disadvantage of regions that are exposed to extreme weather events. The storyline in the fourth article of my thesis investigates the interaction between global economic stress and the propagation of losses from weather extremes. I examine indirect impacts of weather extremes — tropical cyclones, heat stress, and river floods — worldwide under two different economic conditions: an unstressed economy and a globally stressed economy, as seen during the Covid-19 pandemic. I demonstrate that the adverse effects of weather extremes on global consumption are strongly amplified when the economy is under stress. Specifically, consumption losses in the USA and China double and triple, respectively, due to the global economy's decreased capacity for disaster loss compensation. An aggravated scarcity intensifies the price response, causing consumption losses to increase. Advancing on the methods and tools used here, the final two articles in my thesis extend the agent-based model Acclimate and formalize the storyline approach. With the model extension described in the fifth article, regional consumers make rational choices on the goods bought such that their utility is maximized under a constrained budget. In an out-of-equilibrium economy, these rational consumers are shown to temporarily increase consumption of certain goods in spite of rising prices. The sixth article of my thesis proposes a formalization of the storyline framework, drawing on multiple studies including storylines presented in this thesis. The proposed guideline defines eight central elements that can be used to construct a storyline. Overall, this thesis contributes towards a better understanding of economic repercussions of weather extremes. It achieves this by providing assessments of local direct impacts, highlighting mechanisms and impacts of loss propagation, and advancing on methods and tools used.}, language = {en} } @phdthesis{Mueller2008, author = {M{\"u}ller, Claudia}, title = {Graphentheoretische Analyse der Evolution von Wiki-basierten Netzwerken f{\"u}r selbstorganisiertes Wissensmanagement}, address = {Potsdam}, pages = {x, 287 S. : graph. Darst.}, year = {2008}, language = {de} } @phdthesis{Kaufmann2015, author = {Kaufmann, Benjamin}, title = {High performance answer set solving}, pages = {182}, year = {2015}, language = {en} } @phdthesis{Schindler2016, author = {Schindler, Sven}, title = {Honeypot Architectures for IPv6 Networks}, school = {Universit{\"a}t Potsdam}, pages = {164}, year = {2016}, language = {en} } @phdthesis{Schumacher2017, author = {Schumacher, Kinga}, title = {Hybride semantische Suche - eine Kombination aus Fakten- und Dokumentretrieval}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-405973}, school = {Universit{\"a}t Potsdam}, pages = {vii, 187}, year = {2017}, abstract = {Das Thema der vorliegenden Arbeit ist die semantische Suche im Kontext heutiger Informationsmanagementsysteme. Zu diesen Systemen z{\"a}hlen Intranets, Web 3.0-Anwendungen sowie viele Webportale, die Informationen in heterogenen Formaten und Strukturen beinhalten. Auf diesen befinden sich einerseits Daten in strukturierter Form und andererseits Dokumente, die inhaltlich mit diesen Daten in Beziehung stehen. Diese Dokumente sind jedoch in der Regel nur teilweise strukturiert oder vollst{\"a}ndig unstrukturiert. So beschreiben beispielsweise Reiseportale durch strukturierte Daten den Zeitraum, das Reiseziel, den Preis einer Reise und geben in unstrukturierter Form weitere Informationen, wie Beschreibungen zum Hotel, Zielort, Ausflugsziele an. Der Fokus heutiger semantischer Suchmaschinen liegt auf dem Finden von Wissen entweder in strukturierter Form, auch Faktensuche genannt, oder in semi- bzw. unstrukturierter Form, was {\"u}blicherweise als semantische Dokumentensuche bezeichnet wird. Einige wenige Suchmaschinen versuchen die L{\"u}cke zwischen diesen beiden Ans{\"a}tzen zu schließen. Diese durchsuchen zwar gleichzeitig strukturierte sowie unstrukturierte Daten, werten diese jedoch entweder weitgehend voneinander unabh{\"a}ngig aus oder schr{\"a}nken die Suchm{\"o}glichkeiten stark ein, indem sie beispielsweise nur bestimmte Fragemuster unterst{\"u}tzen. Hierdurch werden die im System verf{\"u}gbaren Informationen nicht ausgesch{\"o}pft und gleichzeitig unterbunden, dass Zusammenh{\"a}nge zwischen einzelnen Inhalten der jeweiligen Informationssysteme und sich erg{\"a}nzende Informationen den Benutzer erreichen.
 Um diese L{\"u}cke zu schließen, wurde in der vorliegenden Arbeit ein neuer hybrider semantischer Suchansatz entwickelt und untersucht, der strukturierte und semi- bzw. unstrukturierte Inhalte w{\"a}hrend des gesamten Suchprozesses kombiniert. Durch diesen Ansatz werden nicht nur sowohl Fakten als auch Dokumente gefunden, es werden auch Zusammenh{\"a}nge, die zwischen den unterschiedlich strukturierten Daten bestehen, in jeder Phase der Suche genutzt und fließen in die Suchergebnisse mit ein. Liegt die Antwort zu einer Suchanfrage nicht vollst{\"a}ndig strukturiert, in Form von Fakten, oder unstrukturiert, in Form von Dokumenten vor, so liefert dieser Ansatz eine Kombination der beiden. Die Ber{\"u}cksichtigung von unterschiedlich Inhalten w{\"a}hrend des gesamten Suchprozesses stellt jedoch besondere Herausforderungen an die Suchmaschine. Diese muss in der Lage sein, Fakten und Dokumente in Abh{\"a}ngigkeit voneinander zu durchsuchen, sie zu kombinieren sowie die unterschiedlich strukturierten Ergebnisse in eine geeignete Rangordnung zu bringen. Weiterhin darf die Komplexit{\"a}t der Daten nicht an die Endnutzer weitergereicht werden. Die Darstellung der Inhalte muss vielmehr sowohl bei der Anfragestellung als auch bei der Darbietung der Ergebnisse verst{\"a}ndlich und leicht interpretierbar sein. Die zentrale Fragestellung der Arbeit ist, ob ein hybrider Ansatz auf einer vorgegebenen Datenbasis die Suchanfragen besser beantworten kann als die semantische Dokumentensuche und die Faktensuche f{\"u}r sich genommen, bzw. als eine Suche die diese Ans{\"a}tze im Rahmen des Suchprozesses nicht kombiniert. Die durchgef{\"u}hrten Evaluierungen aus System- und aus Benutzersicht zeigen, dass die im Rahmen der Arbeit entwickelte hybride semantische Suchl{\"o}sung durch die Kombination von strukturierten und unstrukturierten Inhalten im Suchprozess bessere Antworten liefert als die oben genannten Verfahren und somit Vorteile gegen{\"u}ber bisherigen Ans{\"a}tzen bietet. Eine Befragung von Benutzern macht deutlich, dass die hybride semantische Suche als verst{\"a}ndlich empfunden und f{\"u}r heterogen strukturierte Datenmengen bevorzugt wird.}, language = {de} } @phdthesis{Grund2012, author = {Grund, Martin}, title = {Hyrise : a main memory hybrid database storage engine}, address = {Potsdam}, pages = {175 S.}, year = {2012}, language = {en} } @phdthesis{Boeken2022, author = {B{\"o}ken, Bj{\"o}rn}, title = {Improving prediction accuracy using dynamic information}, doi = {10.25932/publishup-58512}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-585125}, school = {Universit{\"a}t Potsdam}, pages = {xii, 160}, year = {2022}, abstract = {Accurately solving classification problems nowadays is likely to be the most relevant machine learning task. Binary classification separating two classes only is algorithmically simpler but has fewer potential applications as many real-world problems are multi-class. On the reverse, separating only a subset of classes simplifies the classification task. Even though existing multi-class machine learning algorithms are very flexible regarding the number of classes, they assume that the target set Y is fixed and cannot be restricted once the training is finished. On the other hand, existing state-of-the-art production environments are becoming increasingly interconnected with the advance of Industry 4.0 and related technologies such that additional information can simplify the respective classification problems. In light of this, the main aim of this thesis is to introduce dynamic classification that generalizes multi-class classification such that the target class set can be restricted arbitrarily to a non-empty class subset M of Y at any time between two consecutive predictions. This task is solved by a combination of two algorithmic approaches. First, classifier calibration, which transforms predictions into posterior probability estimates that are intended to be well calibrated. The analysis provided focuses on monotonic calibration and in particular corrects wrong statements that appeared in the literature. It also reveals that bin-based evaluation metrics, which became popular in recent years, are unjustified and should not be used at all. Next, the validity of Platt scaling, which is the most relevant parametric calibration approach, is analyzed in depth. In particular, its optimality for classifier predictions distributed according to four different families of probability distributions as well its equivalence with Beta calibration up to a sigmoidal preprocessing are proven. For non-monotonic calibration, extended variants on kernel density estimation and the ensemble method EKDE are introduced. Finally, the calibration techniques are evaluated using a simulation study with complete information as well as on a selection of 46 real-world data sets. Building on this, classifier calibration is applied as part of decomposition-based classification that aims to reduce multi-class problems to simpler (usually binary) prediction tasks. For the involved fusing step performed at prediction time, a new approach based on evidence theory is presented that uses classifier calibration to model mass functions. This allows the analysis of decomposition-based classification against a strictly formal background and to prove closed-form equations for the overall combinations. Furthermore, the same formalism leads to a consistent integration of dynamic class information, yielding a theoretically justified and computationally tractable dynamic classification model. The insights gained from this modeling are combined with pairwise coupling, which is one of the most relevant reduction-based classification approaches, such that all individual predictions are combined with a weight. This not only generalizes existing works on pairwise coupling but also enables the integration of dynamic class information. Lastly, a thorough empirical study is performed that compares all newly introduced approaches to existing state-of-the-art techniques. For this, evaluation metrics for dynamic classification are introduced that depend on corresponding sampling strategies. Thereafter, these are applied during a three-part evaluation. First, support vector machines and random forests are applied on 26 data sets from the UCI Machine Learning Repository. Second, two state-of-the-art deep neural networks are evaluated on five benchmark data sets from a relatively recent reference work. Here, computationally feasible strategies to apply the presented algorithms in combination with large-scale models are particularly relevant because a naive application is computationally intractable. Finally, reference data from a real-world process allowing the inclusion of dynamic class information are collected and evaluated. The results show that in combination with support vector machines and random forests, pairwise coupling approaches yield the best results, while in combination with deep neural networks, differences between the different approaches are mostly small to negligible. Most importantly, all results empirically confirm that dynamic classification succeeds in improving the respective prediction accuracies. Therefore, it is crucial to pass dynamic class information in respective applications, which requires an appropriate digital infrastructure.}, language = {en} } @phdthesis{Panchenko2012, author = {Panchenko, Oleksandr}, title = {In-Memory database support for source code querying and analytics}, address = {Potsdam}, pages = {113 S.}, year = {2012}, 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{Gharib2008, author = {Gharib, Mona}, title = {Incremental answer set programming}, address = {Potsdam}, pages = {184 S. : graph. Darst.}, year = {2008}, 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{Thomas2002, author = {Thomas, Marco}, title = {Informatische Modellbildung : modellieren von Modellen als ein zentrales Element der Informatik f{\"u}r den allgemeinbildenden Schulunterricht}, pages = {98 S.}, year = {2002}, language = {de} } @phdthesis{Schuschel2006, author = {Schuschel, Hilmar}, title = {Integrierte Prozessplanung und -ausf{\"u}hrung}, address = {Potsdam}, pages = {135 S.}, year = {2006}, language = {de} }