@phdthesis{Buchholz2006,
  author    = {Buchholz, Henrik},
  title     = {Real-time visualization of 3D city models},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-13337},
  school      = {Universit{\"a}t Potsdam},
  year      = {2006},
  abstract  = {An increasing number of applications requires user interfaces that facilitate the handling of large geodata sets. Using virtual 3D city models, complex geospatial information can be communicated visually in an intuitive way. Therefore, real-time visualization of virtual 3D city models represents a key functionality for interactive exploration, presentation, analysis, and manipulation of geospatial data. This thesis concentrates on the development and implementation of concepts and techniques for real-time city model visualization. It discusses rendering algorithms as well as complementary modeling concepts and interaction techniques. Particularly, the work introduces a new real-time rendering technique to handle city models of high complexity concerning texture size and number of textures. Such models are difficult to handle by current technology, primarily due to two problems: - Limited texture memory: The amount of simultaneously usable texture data is limited by the memory of the graphics hardware. - Limited number of textures: Using several thousand different textures simultaneously causes significant performance problems due to texture switch operations during rendering. The multiresolution texture atlases approach, introduced in this thesis, overcomes both problems. During rendering, it permanently maintains a small set of textures that are sufficient for the current view and the screen resolution available. The efficiency of multiresolution texture atlases is evaluated in performance tests. To summarize, the results demonstrate that the following goals have been achieved: - Real-time rendering becomes possible for 3D scenes whose amount of texture data exceeds the main memory capacity. - Overhead due to texture switches is kept permanently low, so that the number of different textures has no significant effect on the rendering frame rate. Furthermore, this thesis introduces two new approaches for real-time city model visualization that use textures as core visualization elements: - An approach for visualization of thematic information. - An approach for illustrative visualization of 3D city models. Both techniques demonstrate that multiresolution texture atlases provide a basic functionality for the development of new applications and systems in the domain of city model visualization.},
  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{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{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{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{Christgau2017,
  author    = {Christgau, Steffen},
  title     = {One-sided communication on a non-cache-coherent many-core architecture},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-403100},
  school      = {Universit{\"a}t Potsdam},
  pages     = {219},
  year      = {2017},
  abstract  = {Aktuelle Mehrkernprozessoren stellen parallele Systeme dar, die den darauf ausgef{\"u}hrten Programmen gemeinsamen Speicher zur Verf{\"u}gung stellen. Sowohl die ansteigende Kernanzahlen in sogenannten Vielkernprozessoren (many-core processors) als auch die weiterhin steigende Leistungsf{\"a}higkeit der einzelnen Kerne erfordert hohe Bandbreiten, die das Speichersystem des Prozessors liefern muss. Hardware-basierte Cache-Koh{\"a}renz st{\"o}ßt in aktuellen Vielkernprozessoren an Grenzen des praktisch Machbaren. Dementsprechend m{\"u}ssen alternative Architekturen und entsprechend geeignete Programmiermodelle untersucht werden. In dieser Arbeit wird der Single-Chip Cloud Computer (SCC), ein nicht-cachekoh{\"a}renter Vielkernprozessor betrachtet, der aus 48, {\"u}ber ein Gitternetzwerk verbundenen Kernen besteht. Obwohl der Prozessor f{\"u}r nachrichten-basierte Kommunikation entwickelt worden ist, zeigen die Ergebnisse dieser Arbeit, dass einseitige Kommunikation auf Basis gemeinsamen Speichers effizient auf diesem Architekturtyp realisiert werden kann. Einseitige Kommunikation erm{\"o}glicht Datenaustausch zwischen Prozessen, bei der der Empf{\"a}nger keine Details {\"u}ber die stattfindende Kommunikation besitzen muss. Im Sinne des MPI-Standards ist so ein Zugriff auf Speicher entfernter Prozesse m{\"o}glich. Zur Umsetzung dieses Konzepts auf nicht-koh{\"a}renten Architekturen werden in dieser Arbeit sowohl eine effiziente Prozesssynchronisation als auch ein Kommunikationsschema auf Basis von software-basierter Cache-Koh{\"a}renz erarbeitet und untersucht. Die Prozesssynchronisation setzt das Konzept der general active target synchronization aus dem MPI-Standard um. Ein existierendes Klassifikationsschema f{\"u}r dessen Implementierungen wird erweitert und zur Identifikation einer geeigneten Klasse f{\"u}r die nicht-koh{\"a}rente Plattform des SCC verwendet. Auf Grundlage der Klassifikation werden existierende Implementierungen analysiert, daraus geeignete Konzepte extrahiert und ein leichtgewichtiges Synchronisationsprotokoll f{\"u}r den SCC entwickelt, das sowohl gemeinsamen Speicher als auch ungecachete Speicherzugriffe verwendet. Das vorgestellte Schema ist nicht anf{\"a}llig f{\"u}r Verz{\"o}gerungen zwischen Prozessen und erlaubt direkte Kommunikation sobald beide Kommunikationspartner daf{\"u}r bereit sind. Die experimentellen Ergebnisse zeigen ein sehr gutes Skaliserungsverhalten und eine f{\"u}nffach geringere Latenz f{\"u}r die Prozesssynchronisation im Vergleich zu einer auf Nachrichten basierenden MPI-Implementierung des SCC. F{\"u}r die Kommunikation wird mit SCOSCo ein auf gemeinsamen Speicher und software-basierter Cache-Koh{\"a}renz basierenden Konzept vorgestellt. Entsprechende Anforderungen an die Koh{\"a}renz, die dem MPI-Standard entsprechen, werden aufgestellt und eine schlanke Implementierung auf Basis der Hard- und Software-Funktionalit{\"a}ten des SCCs entwickelt. Trotz einer aufgedecktem Fehlfunktion im Speichersubsystem des SCC kann in den experimentellen Auswertungen von Mikrobenchmarks eine f{\"u}nffach verbesserte Bandbreite und eine nahezu vierfach verringerte Latenz beobachtet werden. In Anwendungsexperimenten, wie einer dreidimensionalen schnellen Fourier-Transformation, kann der Anteil der Kommunikation an der Laufzeit um den Faktor f{\"u}nf reduziert werden. In Erg{\"a}nzung dazu werden in dieser Arbeit Konzepte aufgestellt, die in zuk{\"u}nftigen Architekturen, die Cache-Koh{\"a}renz nicht auf einer globalen Ebene des Prozessors liefern k{\"o}nnen, f{\"u}r die Umsetzung von Software-basierter Koh{\"a}renz f{\"u}r einseitige Kommunikation hilfreich sind.},
  language  = {en}
}
@phdthesis{Dawoud2013,
  author    = {Dawoud, Wesam},
  title     = {Scalability and performance management of internet applications in the cloud},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-68187},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {Cloud computing is a model for enabling on-demand access to a shared pool of computing resources. With virtually limitless on-demand resources, a cloud environment enables the hosted Internet application to quickly cope when there is an increase in the workload. However, the overhead of provisioning resources exposes the Internet application to periods of under-provisioning and performance degradation. Moreover, the performance interference, due to the consolidation in the cloud environment, complicates the performance management of the Internet applications. In this dissertation, we propose two approaches to mitigate the impact of the resources provisioning overhead. The first approach employs control theory to scale resources vertically and cope fast with workload. This approach assumes that the provider has knowledge and control over the platform running in the virtual machines (VMs), which limits it to Platform as a Service (PaaS) and Software as a Service (SaaS) providers. The second approach is a customer-side one that deals with the horizontal scalability in an Infrastructure as a Service (IaaS) model. It addresses the trade-off problem between cost and performance with a multi-goal optimization solution. This approach finds the scale thresholds that achieve the highest performance with the lowest increase in the cost. Moreover, the second approach employs a proposed time series forecasting algorithm to scale the application proactively and avoid under-utilization periods. Furthermore, to mitigate the interference impact on the Internet application performance, we developed a system which finds and eliminates the VMs suffering from performance interference. The developed system is a light-weight solution which does not imply provider involvement. To evaluate our approaches and the designed algorithms at large-scale level, we developed a simulator called (ScaleSim). In the simulator, we implemented scalability components acting as the scalability components of Amazon EC2. The current scalability implementation in Amazon EC2 is used as a reference point for evaluating the improvement in the scalable application performance. ScaleSim is fed with realistic models of the RUBiS benchmark extracted from the real environment. The workload is generated from the access logs of the 1998 world cup website. The results show that optimizing the scalability thresholds and adopting proactive scalability can mitigate 88\% of the resources provisioning overhead impact with only a 9\% increase in the cost.},
  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{Dehne2021,
  author    = {Dehne, Julian},
  title     = {M{\"o}glichkeiten und Limitationen der medialen Unterst{\"u}tzung forschenden Lernens},
  doi       = {10.25932/publishup-49789},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-497894},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xvii, 404},
  year      = {2021},
  abstract  = {Forschendes Lernen und die digitale Transformation sind zwei der wichtigsten Einfl{\"u}sse auf die Entwicklung der Hochschuldidaktik im deutschprachigen Raum. W{\"a}hrend das forschende Lernen als normative Theorie das sollen beschreibt, geben die digitalen Werkzeuge, alte wie neue, das k{\"o}nnen in vielen Bereichen vor. In der vorliegenden Arbeit wird ein Prozessmodell aufgestellt, was den Versuch unternimmt, das forschende Lernen hinsichtlich interaktiver, gruppenbasierter Prozesse zu systematisieren. Basierend auf dem entwickelten Modell wurde ein Softwareprototyp implementiert, der den gesamten Forschungsprozess begleiten kann. Dabei werden Gruppenformation, Feedback- und Reflexionsprozesse und das Peer Assessment mit Bildungstechnologien unterst{\"u}tzt. Die Entwicklungen wurden in einem qualitativen Experiment eingesetzt, um Systemwissen {\"u}ber die M{\"o}glichkeiten und Grenzen der digitalen Unterst{\"u}tzung von forschendem Lernen zu gewinnen.},
  language  = {de}
}
@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}
}