@book{AlbrechtNaumann2012,
  author    = {Albrecht, Alexander and Naumann, Felix},
  title     = {Understanding cryptic schemata in large extract-transform-load systems},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-201-8},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-61257},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {19},
  year      = {2012},
  abstract  = {Extract-Transform-Load (ETL) tools are used for the creation, maintenance, and evolution of data warehouses, data marts, and operational data stores. ETL workflows populate those systems with data from various data sources by specifying and executing a DAG of transformations. Over time, hundreds of individual workflows evolve as new sources and new requirements are integrated into the system. The maintenance and evolution of large-scale ETL systems requires much time and manual effort. A key problem is to understand the meaning of unfamiliar attribute labels in source and target databases and ETL transformations. Hard-to-understand attribute labels lead to frustration and time spent to develop and understand ETL workflows. We present a schema decryption technique to support ETL developers in understanding cryptic schemata of sources, targets, and ETL transformations. For a given ETL system, our recommender-like approach leverages the large number of mapped attribute labels in existing ETL workflows to produce good and meaningful decryptions. In this way we are able to decrypt attribute labels consisting of a number of unfamiliar few-letter abbreviations, such as UNP_PEN_INT, which we can decrypt to UNPAID_PENALTY_INTEREST. We evaluate our schema decryption approach on three real-world repositories of ETL workflows and show that our approach is able to suggest high-quality decryptions for cryptic attribute labels in a given schema.},
  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}
}
@book{AppeltauerHirschfeld2012,
  author    = {Appeltauer, Malte and Hirschfeld, Robert},
  title     = {The JCop language specification : Version 1.0, April 2012},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-193-6},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-60208},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {iv, 48},
  year      = {2012},
  abstract  = {Program behavior that relies on contextual information, such as physical location or network accessibility, is common in today's applications, yet its representation is not sufficiently supported by programming languages. With context-oriented programming (COP), such context-dependent behavioral variations can be explicitly modularized and dynamically activated. In general, COP could be used to manage any context-specific behavior. However, its contemporary realizations limit the control of dynamic adaptation. This, in turn, limits the interaction of COP's adaptation mechanisms with widely used architectures, such as event-based, mobile, and distributed programming. The JCop programming language extends Java with language constructs for context-oriented programming and additionally provides a domain-specific aspect language for declarative control over runtime adaptations. As a result, these redesigned implementations are more concise and better modularized than their counterparts using plain COP. JCop's main features have been described in our previous publications. However, a complete language specification has not been presented so far. This report presents the entire JCop language including the syntax and semantics of its new language constructs.},
  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{Mahr2012,
  author    = {Mahr, Philipp},
  title     = {Resource efficient communication in network-based reconfigurable on-chip systems},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-59914},
  school      = {Universit{\"a}t Potsdam},
  year      = {2012},
  abstract  = {The constantly growing capacity of reconfigurable devices allows simultaneous execution of complex applications on those devices. The mere diversity of applications deems it impossible to design an interconnection network matching the requirements of every possible application perfectly, leading to suboptimal performance in many cases. However, the architecture of the interconnection network is not the only aspect affecting performance of communication. The resource manager places applications on the device and therefore influences latency between communicating partners and overall network load. Communication protocols affect performance by introducing data and processing overhead putting higher load on the network and increasing resource demand. Approaching communication holistically not only considers the architecture of the interconnect, but communication-aware resource management, communication protocols and resource usage just as well. Incorporation of different parts of a reconfigurable system during design- and runtime and optimizing them with respect to communication demand results in more resource efficient communication. Extensive evaluation shows enhanced performance and flexibility, if communication on reconfigurable devices is regarded in a holistic fashion.},
  language  = {en}
}
@book{KrauseGiese2012,
  author    = {Krause, Christian and Giese, Holger},
  title     = {Quantitative modeling and analysis of service-oriented real-time systems using interval probabilistic timed automata},
  publisher = {Universit{\"a}tsverlah Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-171-4},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-57845},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {45},
  year      = {2012},
  abstract  = {One of the key challenges in service-oriented systems engineering is the prediction and assurance of non-functional properties, such as the reliability and the availability of composite interorganizational services. Such systems are often characterized by a variety of inherent uncertainties, which must be addressed in the modeling and the analysis approach. The different relevant types of uncertainties can be categorized into (1) epistemic uncertainties due to incomplete knowledge and (2) randomization as explicitly used in protocols or as a result of physical processes. In this report, we study a probabilistic timed model which allows us to quantitatively reason about nonfunctional properties for a restricted class of service-oriented real-time systems using formal methods. To properly motivate the choice for the used approach, we devise a requirements catalogue for the modeling and the analysis of probabilistic real-time systems with uncertainties and provide evidence that the uncertainties of type (1) and (2) in the targeted systems have a major impact on the used models and require distinguished analysis approaches. The formal model we use in this report are Interval Probabilistic Timed Automata (IPTA). Based on the outlined requirements, we give evidence that this model provides both enough expressiveness for a realistic and modular specifiation of the targeted class of systems, and suitable formal methods for analyzing properties, such as safety and reliability properties in a quantitative manner. As technical means for the quantitative analysis, we build on probabilistic model checking, specifically on probabilistic time-bounded reachability analysis and computation of expected reachability rewards and costs. To carry out the quantitative analysis using probabilistic model checking, we developed an extension of the Prism tool for modeling and analyzing IPTA. Our extension of Prism introduces a means for modeling probabilistic uncertainty in the form of probability intervals, as required for IPTA. For analyzing IPTA, our Prism extension moreover adds support for probabilistic reachability checking and computation of expected rewards and costs. We discuss the performance of our extended version of Prism and compare the interval-based IPTA approach to models with fixed probabilities.},
  language  = {en}
}
@book{OPUS4-5731,
  title     = {Proceedings of the 4th Many-core Applications Research Community (MARC) Symposium},
  editor    = {Tr{\"o}ger, Peter and Polze, Andreas},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-169-1},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-57898},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {82},
  year      = {2012},
  abstract  = {In continuation of a successful series of events, the 4th Many-core Applications Research Community (MARC) symposium took place at the HPI in Potsdam on December 8th and 9th 2011. Over 60 researchers from different fields presented their work on many-core hardware architectures, their programming models, and the resulting research questions for the upcoming generation of heterogeneous parallel systems.},
  language  = {en}
}
@phdthesis{Brueckner2012,
  author    = {Br{\"u}ckner, Michael},
  title     = {Prediction games : machine learning in the presence of an adversary},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-203-2},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-60375},
  school      = {Universit{\"a}t Potsdam},
  pages     = {x, 121},
  year      = {2012},
  abstract  = {In many applications one is faced with the problem of inferring some functional relation between input and output variables from given data. Consider, for instance, the task of email spam filtering where one seeks to find a model which automatically assigns new, previously unseen emails to class spam or non-spam. Building such a predictive model based on observed training inputs (e.g., emails) with corresponding outputs (e.g., spam labels) is a major goal of machine learning. Many learning methods assume that these training data are governed by the same distribution as the test data which the predictive model will be exposed to at application time. That assumption is violated when the test data are generated in response to the presence of a predictive model. This becomes apparent, for instance, in the above example of email spam filtering. Here, email service providers employ spam filters and spam senders engineer campaign templates such as to achieve a high rate of successful deliveries despite any filters. Most of the existing work casts such situations as learning robust models which are unsusceptible against small changes of the data generation process. The models are constructed under the worst-case assumption that these changes are performed such to produce the highest possible adverse effect on the performance of the predictive model. However, this approach is not capable to realistically model the true dependency between the model-building process and the process of generating future data. We therefore establish the concept of prediction games: We model the interaction between a learner, who builds the predictive model, and a data generator, who controls the process of data generation, as an one-shot game. The game-theoretic framework enables us to explicitly model the players' interests, their possible actions, their level of knowledge about each other, and the order at which they decide for an action. We model the players' interests as minimizing their own cost function which both depend on both players' actions. The learner's action is to choose the model parameters and the data generator's action is to perturbate the training data which reflects the modification of the data generation process with respect to the past data. We extensively study three instances of prediction games which differ regarding the order in which the players decide for their action. We first assume that both player choose their actions simultaneously, that is, without the knowledge of their opponent's decision. We identify conditions under which this Nash prediction game has a meaningful solution, that is, a unique Nash equilibrium, and derive algorithms that find the equilibrial prediction model. As a second case, we consider a data generator who is potentially fully informed about the move of the learner. This setting establishes a Stackelberg competition. We derive a relaxed optimization criterion to determine the solution of this game and show that this Stackelberg prediction game generalizes existing prediction models. Finally, we study the setting where the learner observes the data generator's action, that is, the (unlabeled) test data, before building the predictive model. As the test data and the training data may be governed by differing probability distributions, this scenario reduces to learning under covariate shift. We derive a new integrated as well as a two-stage method to account for this data set shift. In case studies on email spam filtering we empirically explore properties of all derived models as well as several existing baseline methods. We show that spam filters resulting from the Nash prediction game as well as the Stackelberg prediction game in the majority of cases outperform other existing baseline methods.},
  language  = {en}
}
@misc{GebserKaufmannSchaub2012,
  author    = {Gebser, Martin and Kaufmann, Benjamin and Schaub, Torsten H.},
  title     = {Multi-threaded ASP solving with clasp},
  series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  journal   = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  number    = {586},
  issn      = {1866-8372},
  doi       = {10.25932/publishup-41397},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-413977},
  pages     = {21},
  year      = {2012},
  abstract  = {We present the new multi-threaded version of the state-of-the-art answer set solver clasp. We detail its component and communication architecture and illustrate how they support the principal functionalities of clasp. Also, we provide some insights into the data representation used for different constraint types handled by clasp. All this is accompanied by an extensive experimental analysis of the major features related to multi-threading in clasp.},
  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}
}