@phdthesis{Gumienny2013,
  author    = {Gumienny, Raja Carola},
  title     = {Understanding the adoption of digital whiteboard systems for collaborative design work},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-72417},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {User-centered design processes are the first choice when new interactive systems or services are developed to address real customer needs and provide a good user experience. Common tools for collecting user research data, conducting brainstormings, or sketching ideas are whiteboards and sticky notes. They are ubiquitously available, and no technical or domain knowledge is necessary to use them. However, traditional pen and paper tools fall short when saving the content and sharing it with others unable to be in the same location. They are also missing further digital advantages such as searching or sorting content. Although research on digital whiteboard and sticky note applications has been conducted for over 20 years, these tools are not widely adopted in company contexts. While many research prototypes exist, they have not been used for an extended period of time in a real-world context. The goal of this thesis is to investigate what the enablers and obstacles for the adoption of digital whiteboard systems are. As an instrument for different studies, we developed the Tele-Board software system for collaborative creative work. Based on interviews, observations, and findings from former research, we tried to transfer the analog way of working to the digital world. Being a software system, Tele-Board can be used with a variety of hardware and does not depend on special devices. This feature became one of the main factors for adoption on a larger scale. In this thesis, I will present three studies on the use of Tele-Board with different user groups and foci. I will use a combination of research methods (laboratory case studies and data from field research) with the overall goal of finding out when a digital whiteboard system is used and in which cases not. Not surprisingly, the system is used and accepted if a user sees a main benefit that neither analog tools nor other applications can offer. However, I found that these perceived benefits are very different for each user and usage context. If a tool provides possibilities to use in different ways and with different equipment, the chances of its adoption by a larger group increase. Tele-Board has now been in use for over 1.5 years in a global IT company in at least five countries with a constantly growing user base. Its use, advantages, and disadvantages will be described based on 42 interviews and usage statistics from server logs. Through these insights and findings from laboratory case studies, I will present a detailed analysis of digital whiteboard use in different contexts with design implications for future systems.},
  language  = {en}
}
@phdthesis{Menzel2011,
  author    = {Menzel, Michael},
  title     = {Model-driven security in service-oriented architectures : leveraging security patterns to transform high-level security requirements to technical policies},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-59058},
  school      = {Universit{\"a}t Potsdam},
  year      = {2011},
  abstract  = {Service-oriented Architectures (SOA) facilitate the provision and orchestration of business services to enable a faster adoption to changing business demands. Web Services provide a technical foundation to implement this paradigm on the basis of XML-messaging. However, the enhanced flexibility of message-based systems comes along with new threats and risks. To face these issues, a variety of security mechanisms and approaches is supported by the Web Service specifications. The usage of these security mechanisms and protocols is configured by stating security requirements in security policies. However, security policy languages for SOA are complex and difficult to create due to the expressiveness of these languages. To facilitate and simplify the creation of security policies, this thesis presents a model-driven approach that enables the generation of complex security policies on the basis of simple security intentions. SOA architects can specify these intentions in system design models and are not required to deal with complex technical security concepts. The approach introduced in this thesis enables the enhancement of any system design modelling languages - for example FMC or BPMN - with security modelling elements. The syntax, semantics, and notion of these elements is defined by our security modelling language SecureSOA. The metamodel of this language provides extension points to enable the integration into system design modelling languages. In particular, this thesis demonstrates the enhancement of FMC block diagrams with SecureSOA. To enable the model-driven generation of security policies, a domain-independent policy model is introduced in this thesis. This model provides an abstraction layer for security policies. Mappings are used to perform the transformation from our model to security policy languages. However, expert knowledge is required to generate instances of this model on the basis of simple security intentions. Appropriate security mechanisms, protocols and options must be chosen and combined to fulfil these security intentions. In this thesis, a formalised system of security patterns is used to represent this knowledge and to enable an automated transformation process. Moreover, a domain-specific language is introduced to state security patterns in an accessible way. On the basis of this language, a system of security configuration patterns is provided to transform security intentions related to data protection and identity management. The formal semantics of the security pattern language enable the verification of the transformation process introduced in this thesis and prove the correctness of the pattern application. Finally, our SOA Security LAB is presented that demonstrates the application of our model-driven approach to facilitate a dynamic creation, configuration, and execution of secure Web Service-based composed applications.},
  language  = {en}
}
@phdthesis{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{Wang2016,
  author    = {Wang, Cheng},
  title     = {Deep Learning of Multimodal Representations},
  school      = {Universit{\"a}t Potsdam},
  pages     = {142},
  year      = {2016},
  language  = {en}
}
@phdthesis{Baier2015,
  author    = {Baier, Thomas},
  title     = {Matching events and activities},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-84548},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xxii, 213},
  year      = {2015},
  abstract  = {Nowadays, business processes are increasingly supported by IT services that produce massive amounts of event data during process execution. Aiming at a better process understanding and improvement, this event data can be used to analyze processes using process mining techniques. Process models can be automatically discovered and the execution can be checked for conformance to specified behavior. Moreover, existing process models can be enhanced and annotated with valuable information, for example for performance analysis. While the maturity of process mining algorithms is increasing and more tools are entering the market, process mining projects still face the problem of different levels of abstraction when comparing events with modeled business activities. Mapping the recorded events to activities of a given process model is essential for conformance checking, annotation and understanding of process discovery results. Current approaches try to abstract from events in an automated way that does not capture the required domain knowledge to fit business activities. Such techniques can be a good way to quickly reduce complexity in process discovery. Yet, they fail to enable techniques like conformance checking or model annotation, and potentially create misleading process discovery results by not using the known business terminology. In this thesis, we develop approaches that abstract an event log to the same level that is needed by the business. Typically, this abstraction level is defined by a given process model. Thus, the goal of this thesis is to match events from an event log to activities in a given process model. To accomplish this goal, behavioral and linguistic aspects of process models and event logs as well as domain knowledge captured in existing process documentation are taken into account to build semiautomatic matching approaches. The approaches establish a pre--processing for every available process mining technique that produces or annotates a process model, thereby reducing the manual effort for process analysts. While each of the presented approaches can be used in isolation, we also introduce a general framework for the integration of different matching approaches. The approaches have been evaluated in case studies with industry and using a large industry process model collection and simulated event logs. The evaluation demonstrates the effectiveness and efficiency of the approaches and their robustness towards nonconforming execution logs.},
  language  = {en}
}
@phdthesis{Abedjan2014,
  author    = {Abedjan, Ziawasch},
  title     = {Improving RDF data with data mining},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-71334},
  school      = {Universit{\"a}t Potsdam},
  year      = {2014},
  abstract  = {Linked Open Data (LOD) comprises very many and often large public data sets and knowledge bases. Those datasets are mostly presented in the RDF triple structure of subject, predicate, and object, where each triple represents a statement or fact. Unfortunately, the heterogeneity of available open data requires significant integration steps before it can be used in applications. Meta information, such as ontological definitions and exact range definitions of predicates, are desirable and ideally provided by an ontology. However in the context of LOD, ontologies are often incomplete or simply not available. Thus, it is useful to automatically generate meta information, such as ontological dependencies, range definitions, and topical classifications. Association rule mining, which was originally applied for sales analysis on transactional databases, is a promising and novel technique to explore such data. We designed an adaptation of this technique for min-ing Rdf data and introduce the concept of "mining configurations", which allows us to mine RDF data sets in various ways. Different configurations enable us to identify schema and value dependencies that in combination result in interesting use cases. To this end, we present rule-based approaches for auto-completion, data enrichment, ontology improvement, and query relaxation. Auto-completion remedies the problem of inconsistent ontology usage, providing an editing user with a sorted list of commonly used predicates. A combination of different configurations step extends this approach to create completely new facts for a knowledge base. We present two approaches for fact generation, a user-based approach where a user selects the entity to be amended with new facts and a data-driven approach where an algorithm discovers entities that have to be amended with missing facts. As knowledge bases constantly grow and evolve, another approach to improve the usage of RDF data is to improve existing ontologies. Here, we present an association rule based approach to reconcile ontology and data. Interlacing different mining configurations, we infer an algorithm to discover synonymously used predicates. Those predicates can be used to expand query results and to support users during query formulation. We provide a wide range of experiments on real world datasets for each use case. The experiments and evaluations show the added value of association rule mining for the integration and usability of RDF data and confirm the appropriateness of our mining configuration methodology.},
  language  = {en}
}
@phdthesis{Kunze2013,
  author    = {Kunze, Matthias},
  title     = {Searching business process models by example},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-68844},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {Business processes are fundamental to the operations of a company. Each product manufactured and every service provided is the result of a series of actions that constitute a business process. Business process management is an organizational principle that makes the processes of a company explicit and offers capabilities to implement procedures, control their execution, analyze their performance, and improve them. Therefore, business processes are documented as process models that capture these actions and their execution ordering, and make them accessible to stakeholders. As these models are an essential knowledge asset, they need to be managed effectively. In particular, the discovery and reuse of existing knowledge becomes challenging in the light of companies maintaining hundreds and thousands of process models. In practice, searching process models has been solved only superficially by means of free-text search of process names and their descriptions. Scientific contributions are limited in their scope, as they either present measures for process similarity or elaborate on query languages to search for particular aspects. However, they fall short in addressing efficient search, the presentation of search results, and the support to reuse discovered models. This thesis presents a novel search method, where a query is expressed by an exemplary business process model that describes the behavior of a possible answer. This method builds upon a formal framework that captures and compares the behavior of process models by the execution ordering of actions. The framework contributes a conceptual notion of behavioral distance that quantifies commonalities and differences of a pair of process models, and enables process model search. Based on behavioral distances, a set of measures is proposed that evaluate the quality of a particular search result to guide the user in assessing the returned matches. A projection of behavioral aspects to a process model enables highlighting relevant fragments that led to a match and facilitates its reuse. The thesis further elaborates on two search techniques that provide concrete behavioral distance functions as an instantiation of the formal framework. Querying enables search with a notion of behavioral inclusion with regard to the query. In contrast, similarity search obtains process models that are similar to a query, even if the query is not precisely matched. For both techniques, indexes are presented that enable efficient search. Methods to evaluate the quality and performance of process model search are introduced and applied to the techniques of this thesis. They show good results with regard to human assessment and scalability in a practical setting.},
  language  = {en}
}
@phdthesis{Glander2012,
  author    = {Glander, Tassilo},
  title     = {Multi-scale representations of virtual 3D city models},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64117},
  school      = {Universit{\"a}t Potsdam},
  year      = {2012},
  abstract  = {Virtual 3D city and landscape models are the main subject investigated in this thesis. They digitally represent urban space and have many applications in different domains, e.g., simulation, cadastral management, and city planning. Visualization is an elementary component of these applications. Photo-realistic visualization with an increasingly high degree of detail leads to fundamental problems for comprehensible visualization. A large number of highly detailed and textured objects within a virtual 3D city model may create visual noise and overload the users with information. Objects are subject to perspective foreshortening and may be occluded or not displayed in a meaningful way, as they are too small. In this thesis we present abstraction techniques that automatically process virtual 3D city and landscape models to derive abstracted representations. These have a reduced degree of detail, while essential characteristics are preserved. After introducing definitions for model, scale, and multi-scale representations, we discuss the fundamentals of map generalization as well as techniques for 3D generalization. The first presented technique is a cell-based generalization of virtual 3D city models. It creates abstract representations that have a highly reduced level of detail while maintaining essential structures, e.g., the infrastructure network, landmark buildings, and free spaces. The technique automatically partitions the input virtual 3D city model into cells based on the infrastructure network. The single building models contained in each cell are aggregated to abstracted cell blocks. Using weighted infrastructure elements, cell blocks can be computed on different hierarchical levels, storing the hierarchy relation between the cell blocks. Furthermore, we identify initial landmark buildings within a cell by comparing the properties of individual buildings with the aggregated properties of the cell. For each block, the identified landmark building models are subtracted using Boolean operations and integrated in a photo-realistic way. Finally, for the interactive 3D visualization we discuss the creation of the virtual 3D geometry and their appearance styling through colors, labeling, and transparency. We demonstrate the technique with example data sets. Additionally, we discuss applications of generalization lenses and transitions between abstract representations. The second technique is a real-time-rendering technique for geometric enhancement of landmark objects within a virtual 3D city model. Depending on the virtual camera distance, landmark objects are scaled to ensure their visibility within a specific distance interval while deforming their environment. First, in a preprocessing step a landmark hierarchy is computed, this is then used to derive distance intervals for the interactive rendering. At runtime, using the virtual camera distance, a scaling factor is computed and applied to each landmark. The scaling factor is interpolated smoothly at the interval boundaries using cubic B{\´e}zier splines. Non-landmark geometry that is near landmark objects is deformed with respect to a limited number of landmarks. We demonstrate the technique by applying it to a highly detailed virtual 3D city model and a generalized 3D city model. In addition we discuss an adaptation of the technique for non-linear projections and mobile devices. The third technique is a real-time rendering technique to create abstract 3D isocontour visualization of virtual 3D terrain models. The virtual 3D terrain model is visualized as a layered or stepped relief. The technique works without preprocessing and, as it is implemented using programmable graphics hardware, can be integrated with minimal changes into common terrain rendering techniques. Consequently, the computation is done in the rendering pipeline for each vertex, primitive, i.e., triangle, and fragment. For each vertex, the height is quantized to the nearest isovalue. For each triangle, the vertex configuration with respect to their isovalues is determined first. Using the configuration, the triangle is then subdivided. The subdivision forms a partial step geometry aligned with the triangle. For each fragment, the surface appearance is determined, e.g., depending on the surface texture, shading, and height-color-mapping. Flexible usage of the technique is demonstrated with applications from focus+context visualization, out-of-core terrain rendering, and information visualization. This thesis presents components for the creation of abstract representations of virtual 3D city and landscape models. Re-using visual language from cartography, the techniques enable users to build on their experience with maps when interpreting these representations. Simultaneously, characteristics of 3D geovirtual environments are taken into account by addressing and discussing, e.g., continuous scale, interaction, and perspective.},
  language  = {en}
}
@phdthesis{Seibel2012,
  author    = {Seibel, Andreas},
  title     = {Traceability and model management with executable and dynamic hierarchical megamodels},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64222},
  school      = {Universit{\"a}t Potsdam},
  year      = {2012},
  abstract  = {Nowadays, model-driven engineering (MDE) promises to ease software development by decreasing the inherent complexity of classical software development. In order to deliver on this promise, MDE increases the level of abstraction and automation, through a consideration of domain-specific models (DSMs) and model operations (e.g. model transformations or code generations). DSMs conform to domain-specific modeling languages (DSMLs), which increase the level of abstraction, and model operations are first-class entities of software development because they increase the level of automation. Nevertheless, MDE has to deal with at least two new dimensions of complexity, which are basically caused by the increased linguistic and technological heterogeneity. The first dimension of complexity is setting up an MDE environment, an activity comprised of the implementation or selection of DSMLs and model operations. Setting up an MDE environment is both time-consuming and error-prone because of the implementation or adaptation of model operations. The second dimension of complexity is concerned with applying MDE for actual software development. Applying MDE is challenging because a collection of DSMs, which conform to potentially heterogeneous DSMLs, are required to completely specify a complex software system. A single DSML can only be used to describe a specific aspect of a software system at a certain level of abstraction and from a certain perspective. Additionally, DSMs are usually not independent but instead have inherent interdependencies, reflecting (partial) similar aspects of a software system at different levels of abstraction or from different perspectives. A subset of these dependencies are applications of various model operations, which are necessary to keep the degree of automation high. This becomes even worse when addressing the first dimension of complexity. Due to continuous changes, all kinds of dependencies, including the applications of model operations, must also be managed continuously. This comprises maintaining the existence of these dependencies and the appropriate (re-)application of model operations. The contribution of this thesis is an approach that combines traceability and model management to address the aforementioned challenges of configuring and applying MDE for software development. The approach is considered as a traceability approach because it supports capturing and automatically maintaining dependencies between DSMs. The approach is considered as a model management approach because it supports managing the automated (re-)application of heterogeneous model operations. In addition, the approach is considered as a comprehensive model management. Since the decomposition of model operations is encouraged to alleviate the first dimension of complexity, the subsequent composition of model operations is required to counteract their fragmentation. A significant portion of this thesis concerns itself with providing a method for the specification of decoupled yet still highly cohesive complex compositions of heterogeneous model operations. The approach supports two different kinds of compositions - data-flow compositions and context compositions. Data-flow composition is used to define a network of heterogeneous model operations coupled by sharing input and output DSMs alone. Context composition is related to a concept used in declarative model transformation approaches to compose individual model transformation rules (units) at any level of detail. In this thesis, context composition provides the ability to use a collection of dependencies as context for the composition of other dependencies, including model operations. In addition, the actual implementation of model operations, which are going to be composed, do not need to implement any composition concerns. The approach is realized by means of a formalism called an executable and dynamic hierarchical megamodel, based on the original idea of megamodels. This formalism supports specifying compositions of dependencies (traceability and model operations). On top of this formalism, traceability is realized by means of a localization concept, and model management by means of an execution concept.},
  language  = {en}
}
@phdthesis{Polyvyanyy2012,
  author    = {Polyvyanyy, Artem},
  title     = {Structuring process models},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-59024},
  school      = {Universit{\"a}t Potsdam},
  year      = {2012},
  abstract  = {One can fairly adopt the ideas of Donald E. Knuth to conclude that process modeling is both a science and an art. Process modeling does have an aesthetic sense. Similar to composing an opera or writing a novel, process modeling is carried out by humans who undergo creative practices when engineering a process model. Therefore, the very same process can be modeled in a myriad number of ways. Once modeled, processes can be analyzed by employing scientific methods. Usually, process models are formalized as directed graphs, with nodes representing tasks and decisions, and directed arcs describing temporal constraints between the nodes. Common process definition languages, such as Business Process Model and Notation (BPMN) and Event-driven Process Chain (EPC) allow process analysts to define models with arbitrary complex topologies. The absence of structural constraints supports creativity and productivity, as there is no need to force ideas into a limited amount of available structural patterns. Nevertheless, it is often preferable that models follow certain structural rules. A well-known structural property of process models is (well-)structuredness. A process model is (well-)structured if and only if every node with multiple outgoing arcs (a split) has a corresponding node with multiple incoming arcs (a join), and vice versa, such that the set of nodes between the split and the join induces a single-entry-single-exit (SESE) region; otherwise the process model is unstructured. The motivations for well-structured process models are manifold: (i) Well-structured process models are easier to layout for visual representation as their formalizations are planar graphs. (ii) Well-structured process models are easier to comprehend by humans. (iii) Well-structured process models tend to have fewer errors than unstructured ones and it is less probable to introduce new errors when modifying a well-structured process model. (iv) Well-structured process models are better suited for analysis with many existing formal techniques applicable only for well-structured process models. (v) Well-structured process models are better suited for efficient execution and optimization, e.g., when discovering independent regions of a process model that can be executed concurrently. Consequently, there are process modeling languages that encourage well-structured modeling, e.g., Business Process Execution Language (BPEL) and ADEPT. However, the well-structured process modeling implies some limitations: (i) There exist processes that cannot be formalized as well-structured process models. (ii) There exist processes that when formalized as well-structured process models require a considerable duplication of modeling constructs. Rather than expecting well-structured modeling from start, we advocate for the absence of structural constraints when modeling. Afterwards, automated methods can suggest, upon request and whenever possible, alternative formalizations that are "better" structured, preferably well-structured. In this thesis, we study the problem of automatically transforming process models into equivalent well-structured models. The developed transformations are performed under a strong notion of behavioral equivalence which preserves concurrency. The findings are implemented in a tool, which is publicly available.},
  language  = {en}
}
@phdthesis{Takouna2014,
  author    = {Takouna, Ibrahim},
  title     = {Energy-efficient and performance-aware virtual machine management for cloud data centers},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-72399},
  school      = {Universit{\"a}t Potsdam},
  year      = {2014},
  abstract  = {Virtualisierte Cloud Datenzentren stellen nach Bedarf Ressourcen zur Verf{\"u}gu-ng, erm{\"o}glichen agile Ressourcenbereitstellung und beherbergen heterogene Applikationen mit verschiedenen Anforderungen an Ressourcen. Solche Datenzentren verbrauchen enorme Mengen an Energie, was die Erh{\"o}hung der Betriebskosten, der W{\"a}rme innerhalb der Zentren und des Kohlendioxidausstoßes verursacht. Der Anstieg des Energieverbrauches kann durch ein ineffektives Ressourcenmanagement, das die ineffiziente Ressourcenausnutzung verursacht, entstehen. Die vorliegende Dissertation stellt detaillierte Modelle und neue Verfahren f{\"u}r virtualisiertes Ressourcenmanagement in Cloud Datenzentren vor. Die vorgestellten Verfahren ziehen das Service-Level-Agreement (SLA) und die Heterogenit{\"a}t der Auslastung bez{\"u}glich des Bedarfs an Speicherzugriffen und Kommunikationsmustern von Web- und HPC- (High Performance Computing) Applikationen in Betracht. Um die pr{\"a}sentierten Techniken zu evaluieren, verwenden wir Simulationen und echte Protokollierung der Auslastungen von Web- und HPC- Applikationen. Außerdem vergleichen wir unser Techniken und Verfahren mit anderen aktuellen Verfahren durch die Anwendung von verschiedenen Performance Metriken. Die Hauptbeitr{\"a}ge dieser Dissertation sind Folgendes: Ein Proaktives auf robuster Optimierung basierendes Ressourcenbereitstellungsverfahren. Dieses Verfahren erh{\"o}ht die F{\"a}higkeit der Hostes zur Verf{\"u}g-ungsstellung von mehr VMs. Gleichzeitig aber wird der unn{\"o}tige Energieverbrauch minimiert. Zus{\"a}tzlich mindert diese Technik unerw{\"u}nschte {\"A}nde-rungen im Energiezustand des Servers. Die vorgestellte Technik nutzt einen auf Intervall basierenden Vorhersagealgorithmus zur Implementierung einer robusten Optimierung. Dabei werden unsichere Anforderungen in Betracht gezogen. Ein adaptives und auf Intervall basierendes Verfahren zur Vorhersage des Arbeitsaufkommens mit hohen, in k{\"u}rzer Zeit auftretenden Schwankungen. Die Intervall basierende Vorhersage ist implementiert in der Standard Abweichung Variante und in der Median absoluter Abweichung Variante. Die Intervall-{\"A}nderungen basieren auf einem adaptiven Vertrauensfenster um die Schwankungen des Arbeitsaufkommens zu bew{\"a}ltigen. Eine robuste VM Zusammenlegung f{\"u}r ein effizientes Energie und Performance Management. Dies erm{\"o}glicht die gegenseitige Abh{\"a}ngigkeit zwischen der Energie und der Performance zu minimieren. Unser Verfahren reduziert die Anzahl der VM-Migrationen im Vergleich mit den neu vor kurzem vorgestellten Verfahren. Dies tr{\"a}gt auch zur Reduzierung des durch das Netzwerk verursachten Energieverbrauches. Außerdem reduziert dieses Verfahren SLA-Verletzungen und die Anzahl von {\"A}nderungen an Energiezus-t{\"a}nden. Ein generisches Modell f{\"u}r das Netzwerk eines Datenzentrums um die verz{\"o}-gerte Kommunikation und ihre Auswirkung auf die VM Performance und auf die Netzwerkenergie zu simulieren. Außerdem wird ein generisches Modell f{\"u}r ein Memory-Bus des Servers vorgestellt. Dieses Modell beinhaltet auch Modelle f{\"u}r die Latenzzeit und den Energieverbrauch f{\"u}r verschiedene Memory Frequenzen. Dies erlaubt eine Simulation der Memory Verz{\"o}gerung und ihre Auswirkung auf die VM-Performance und auf den Memory Energieverbrauch. Kommunikation bewusste und Energie effiziente Zusammenlegung f{\"u}r parallele Applikationen um die dynamische Entdeckung von Kommunikationsmustern und das Umplanen von VMs zu erm{\"o}glichen. Das Umplanen von VMs benutzt eine auf den entdeckten Kommunikationsmustern basierende Migration. Eine neue Technik zur Entdeckung von dynamischen Mustern ist implementiert. Sie basiert auf der Signal Verarbeitung des Netzwerks von VMs, anstatt die Informationen des virtuellen Umstellung der Hosts oder der Initiierung der VMs zu nutzen. Das Ergebnis zeigt, dass unsere Methode die durchschnittliche Anwendung des Netzwerks reduziert und aufgrund der Reduzierung der aktiven Umstellungen Energie gespart. Außerdem bietet sie eine bessere VM Performance im Vergleich zu der CPU-basierten Platzierung. Memory bewusste VM Zusammenlegung f{\"u}r unabh{\"a}ngige VMs. Sie nutzt die Vielfalt des VMs Memory Zuganges um die Anwendung vom Memory-Bus der Hosts zu balancieren. Die vorgestellte Technik, Memory-Bus Load Balancing (MLB), verteilt die VMs reaktiv neu im Bezug auf ihre Anwendung vom Memory-Bus. Sie nutzt die VM Migration um die Performance des gesamtem Systems zu verbessern. Außerdem sind die dynamische Spannung, die Frequenz Skalierung des Memory und die MLB Methode kombiniert um ein besseres Energiesparen zu leisten.},
  language  = {en}
}
@phdthesis{Steinmetz2013,
  author    = {Steinmetz, Nadine},
  title     = {Context-aware semantic analysis of video metadata},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-70551},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {Im Vergleich zu einer stichwortbasierten Suche erm{\"o}glicht die semantische Suche ein pr{\"a}ziseres und anspruchsvolleres Durchsuchen von (Web)-Dokumenten, weil durch die explizite Semantik Mehrdeutigkeiten von nat{\"u}rlicher Sprache vermieden und semantische Beziehungen in das Suchergebnis einbezogen werden k{\"o}nnen. Eine semantische, Entit{\"a}ten-basierte Suche geht von einer Anfrage mit festgelegter Bedeutung aus und liefert nur Dokumente, die mit dieser Entit{\"a}t annotiert sind als Suchergebnis. Die wichtigste Voraussetzung f{\"u}r eine Entit{\"a}ten-zentrierte Suche stellt die Annotation der Dokumente im Archiv mit Entit{\"a}ten und Kategorien dar. Textuelle Informationen werden analysiert und mit den entsprechenden Entit{\"a}ten und Kategorien versehen, um den Inhalt semantisch erschließen zu k{\"o}nnen. Eine manuelle Annotation erfordert Dom{\"a}nenwissen und ist sehr zeitaufwendig. Die semantische Annotation von Videodokumenten erfordert besondere Aufmerksamkeit, da inhaltsbasierte Metadaten von Videos aus verschiedenen Quellen stammen, verschiedene Eigenschaften und Zuverl{\"a}ssigkeiten besitzen und daher nicht wie Fließtext behandelt werden k{\"o}nnen. Die vorliegende Arbeit stellt einen semantischen Analyseprozess f{\"u}r Video-Metadaten vor. Die Eigenschaften der verschiedenen Metadatentypen werden analysiert und ein Konfidenzwert ermittelt. Dieser Wert spiegelt die Korrektheit und die wahrscheinliche Mehrdeutigkeit eines Metadatums wieder. Beginnend mit dem Metadatum mit dem h{\"o}chsten Konfidenzwert wird der Analyseprozess innerhalb eines Kontexts in absteigender Reihenfolge des Konfidenzwerts durchgef{\"u}hrt. Die bereits analysierten Metadaten dienen als Referenzpunkt f{\"u}r die weiteren Analysen. So kann eine m{\"o}glichst korrekte Analyse der heterogen strukturierten Daten eines Kontexts sichergestellt werden. Am Ende der Analyse eines Metadatums wird die f{\"u}r den Kontext relevanteste Entit{\"a}t aus einer Liste von Kandidaten identifiziert - das Metadatum wird disambiguiert. Hierf{\"u}r wurden verschiedene Disambiguierungsalgorithmen entwickelt, die Beschreibungstexte und semantische Beziehungen der Entit{\"a}tenkandidaten zum gegebenen Kontext in Betracht ziehen. Der Kontext f{\"u}r die Disambiguierung wird f{\"u}r jedes Metadatum anhand der Eigenschaften und Konfidenzwerte zusammengestellt. Der vorgestellte Analyseprozess ist an zwei Hypothesen angelehnt: Um die Analyseergebnisse verbessern zu k{\"o}nnen, sollten die Metadaten eines Kontexts in absteigender Reihenfolge ihres Konfidenzwertes verarbeitet werden und die Kontextgrenzen von Videometadaten sollten durch Segmentgrenzen definiert werden, um m{\"o}glichst Kontexte mit koh{\"a}rentem Inhalt zu erhalten. Durch ausf{\"u}hrliche Evaluationen konnten die gestellten Hypothesen best{\"a}tigt werden. Der Analyseprozess wurden gegen mehrere State-of-the-Art Methoden verglichen und erzielt verbesserte Ergebnisse in Bezug auf Recall und Precision, besonders f{\"u}r Metadaten, die aus weniger zuverl{\"a}ssigen Quellen stammen. Der Analyseprozess ist Teil eines Videoanalyse-Frameworks und wurde bereits erfolgreich in verschiedenen Projekten eingesetzt.},
  language  = {en}
}
@phdthesis{Wang2011,
  author    = {Wang, Long},
  title     = {X-tracking the usage interest on web sites},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-51077},
  school      = {Universit{\"a}t Potsdam},
  year      = {2011},
  abstract  = {The exponential expanding of the numbers of web sites and Internet users makes WWW the most important global information resource. From information publishing and electronic commerce to entertainment and social networking, the Web allows an inexpensive and efficient access to the services provided by individuals and institutions. The basic units for distributing these services are the web sites scattered throughout the world. However, the extreme fragility of web services and content, the high competence between similar services supplied by different sites, and the wide geographic distributions of the web users drive the urgent requirement from the web managers to track and understand the usage interest of their web customers. This thesis, "X-tracking the Usage Interest on Web Sites", aims to fulfill this requirement. "X" stands two meanings: one is that the usage interest differs from various web sites, and the other is that usage interest is depicted from multi aspects: internal and external, structural and conceptual, objective and subjective. "Tracking" shows that our concentration is on locating and measuring the differences and changes among usage patterns. This thesis presents the methodologies on discovering usage interest on three kinds of web sites: the public information portal site, e-learning site that provides kinds of streaming lectures and social site that supplies the public discussions on IT issues. On different sites, we concentrate on different issues related with mining usage interest. The educational information portal sites were the first implementation scenarios on discovering usage patterns and optimizing the organization of web services. In such cases, the usage patterns are modeled as frequent page sets, navigation paths, navigation structures or graphs. However, a necessary requirement is to rebuild the individual behaviors from usage history. We give a systematic study on how to rebuild individual behaviors. Besides, this thesis shows a new strategy on building content clusters based on pair browsing retrieved from usage logs. The difference between such clusters and the original web structure displays the distance between the destinations from usage side and the expectations from design side. Moreover, we study the problem on tracking the changes of usage patterns in their life cycles. The changes are described from internal side integrating conceptual and structure features, and from external side for the physical features; and described from local side measuring the difference between two time spans, and global side showing the change tendency along the life cycle. A platform, Web-Cares, is developed to discover the usage interest, to measure the difference between usage interest and site expectation and to track the changes of usage patterns. E-learning site provides the teaching materials such as slides, recorded lecture videos and exercise sheets. We focus on discovering the learning interest on streaming lectures, such as real medias, mp4 and flash clips. Compared to the information portal site, the usage on streaming lectures encapsulates the variables such as viewing time and actions during learning processes. The learning interest is discovered in the form of answering 6 questions, which covers finding the relations between pieces of lectures and the preference among different forms of lectures. We prefer on detecting the changes of learning interest on the same course from different semesters. The differences on the content and structure between two courses leverage the changes on the learning interest. We give an algorithm on measuring the difference on learning interest integrated with similarity comparison between courses. A search engine, TASK-Moniminer, is created to help the teacher query the learning interest on their streaming lectures on tele-TASK site. Social site acts as an online community attracting web users to discuss the common topics and share their interesting information. Compared to the public information portal site and e-learning web site, the rich interactions among users and web content bring the wider range of content quality, on the other hand, provide more possibilities to express and model usage interest. We propose a framework on finding and recommending high reputation articles in a social site. We observed that the reputation is classified into global and local categories; the quality of the articles having high reputation is related with the content features. Based on these observations, our framework is implemented firstly by finding the articles having global or local reputation, and secondly clustering articles based on their content relations, and then the articles are selected and recommended from each cluster based on their reputation ranks.},
  language  = {en}
}