@article{PengLiuWangetal.2018,
  author    = {Peng, Junjie and Liu, Danxu and Wang, Yingtao and Zeng, Ying and Cheng, Feng and Zhang, Wenqiang},
  title     = {Weight-based strategy for an I/O-intensive application at a cloud data center},
  series = {Concurrency and computation : practice \& experience},
  volume    = {30},
  journal   = {Concurrency and computation : practice \& experience},
  number    = {19},
  publisher = {Wiley},
  address   = {Hoboken},
  issn      = {1532-0626},
  doi       = {10.1002/cpe.4648},
  pages     = {14},
  year      = {2018},
  abstract  = {Applications with different characteristics in the cloud may have different resources preferences. However, traditional resource allocation and scheduling strategies rarely take into account the characteristics of applications. Considering that an I/O-intensive application is a typical type of application and that frequent I/O accesses, especially small files randomly accessing the disk, may lead to an inefficient use of resources and reduce the quality of service (QoS) of applications, a weight allocation strategy is proposed based on the available resources that a physical server can provide as well as the characteristics of the applications. Using the weight obtained, a resource allocation and scheduling strategy is presented based on the specific application characteristics in the data center. Extensive experiments show that the strategy is correct and can guarantee a high concurrency of I/O per second (IOPS) in a cloud data center with high QoS. Additionally, the strategy can efficiently improve the utilization of the disk and resources of the data center without affecting the service quality of applications.},
  language  = {en}
}
@article{KossmannHalfpapJankriftetal.2020,
  author    = {Kossmann, Jan and Halfpap, Stefan and Jankrift, Marcel and Schlosser, Rainer},
  title     = {Magic mirror in my hand, which is the best in the land?},
  series = {Proceedings of the VLDB Endowment},
  volume    = {13},
  journal   = {Proceedings of the VLDB Endowment},
  number    = {11},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {2150-8097},
  doi       = {10.14778/3407790.3407832},
  pages     = {2382 -- 2395},
  year      = {2020},
  abstract  = {Indexes are essential for the efficient processing of database workloads. Proposed solutions for the relevant and challenging index selection problem range from metadata-based simple heuristics, over sophisticated multi-step algorithms, to approaches that yield optimal results. The main challenges are (i) to accurately determine the effect of an index on the workload cost while considering the interaction of indexes and (ii) a large number of possible combinations resulting from workloads containing many queries and massive schemata with possibly thousands of attributes. <br /> In this work, we describe and analyze eight index selection algorithms that are based on different concepts and compare them along different dimensions, such as solution quality, runtime, multi-column support, solution granularity, and complexity. In particular, we analyze the solutions of the algorithms for the challenging analytical Join Order, TPC-H, and TPC-DS benchmarks. Afterward, we assess strengths and weaknesses, infer insights for index selection in general and each approach individually, before we give recommendations on when to use which approach.},
  language  = {en}
}
@article{MattisBeckmannReinetal.2022,
  author    = {Mattis, Toni and Beckmann, Tom and Rein, Patrick and Hirschfeld, Robert},
  title     = {First-class concepts},
  series = {Journal of object technology : JOT / ETH Z{\"u}rich, Department of Computer Science},
  volume    = {21},
  journal   = {Journal of object technology : JOT / ETH Z{\"u}rich, Department of Computer Science},
  number    = {2},
  publisher = {ETH Z{\"u}rich, Department of Computer Science},
  address   = {Z{\"u}rich},
  issn      = {1660-1769},
  doi       = {10.5381/jot.2022.21.2.a6},
  pages     = {1 -- 15},
  year      = {2022},
  abstract  = {Ideally, programs are partitioned into independently maintainable and understandable modules. As a system grows, its architecture gradually loses the capability to accommodate new concepts in a modular way. While refactoring is expensive and not always possible, and the programming language might lack dedicated primary language constructs to express certain cross-cutting concerns, programmers are still able to explain and delineate convoluted concepts through secondary means: code comments, use of whitespace and arrangement of code, documentation, or communicating tacit knowledge. <br /> Secondary constructs are easy to change and provide high flexibility in communicating cross-cutting concerns and other concepts among programmers. However, such secondary constructs usually have no reified representation that can be explored and manipulated as first-class entities through the programming environment. <br /> In this exploratory work, we discuss novel ways to express a wide range of concepts, including cross-cutting concerns, patterns, and lifecycle artifacts independently of the dominant decomposition imposed by an existing architecture. We propose the representation of concepts as first-class objects inside the programming environment that retain the capability to change as easily as code comments. We explore new tools that allow programmers to view, navigate, and change programs based on conceptual perspectives. In a small case study, we demonstrate how such views can be created and how the programming experience changes from draining programmers' attention by stretching it across multiple modules toward focusing it on cohesively presented concepts. Our designs are geared toward facilitating multiple secondary perspectives on a system to co-exist in symbiosis with the original architecture, hence making it easier to explore, understand, and explain complex contexts and narratives that are hard or impossible to express using primary modularity constructs.},
  language  = {en}
}
@article{KoumarelasJiangNaumann2020,
  author    = {Koumarelas, Ioannis and Jiang, Lan and Naumann, Felix},
  title     = {Data preparation for duplicate detection},
  series = {Journal of data and information quality : (JDIQ)},
  volume    = {12},
  journal   = {Journal of data and information quality : (JDIQ)},
  number    = {3},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {1936-1955},
  doi       = {10.1145/3377878},
  pages     = {24},
  year      = {2020},
  abstract  = {Data errors represent a major issue in most application workflows. Before any important task can take place, a certain data quality has to be guaranteed by eliminating a number of different errors that may appear in data. Typically, most of these errors are fixed with data preparation methods, such as whitespace removal. However, the particular error of duplicate records, where multiple records refer to the same entity, is usually eliminated independently with specialized techniques. Our work is the first to bring these two areas together by applying data preparation operations under a systematic approach prior to performing duplicate detection. <br /> Our process workflow can be summarized as follows: It begins with the user providing as input a sample of the gold standard, the actual dataset, and optionally some constraints to domain-specific data preparations, such as address normalization. The preparation selection operates in two consecutive phases. First, to vastly reduce the search space of ineffective data preparations, decisions are made based on the improvement or worsening of pair similarities. Second, using the remaining data preparations an iterative leave-one-out classification process removes preparations one by one and determines the redundant preparations based on the achieved area under the precision-recall curve (AUC-PR). Using this workflow, we manage to improve the results of duplicate detection up to 19\% in AUC-PR.},
  language  = {en}
}
@article{KossmannSchlosser2020,
  author    = {Kossmann, Jan and Schlosser, Rainer},
  title     = {Self-driving database systems},
  series = {Distributed and parallel databases},
  volume    = {38},
  journal   = {Distributed and parallel databases},
  number    = {4},
  publisher = {Springer},
  address   = {Dordrecht},
  issn      = {0926-8782},
  doi       = {10.1007/s10619-020-07288-w},
  pages     = {795 -- 817},
  year      = {2020},
  abstract  = {Challenges for self-driving database systems, which tune their physical design and configuration autonomously, are manifold: Such systems have to anticipate future workloads, find robust configurations efficiently, and incorporate knowledge gained by previous actions into later decisions. We present a component-based framework for self-driving database systems that enables database integration and development of self-managing functionality with low overhead by relying on separation of concerns. By keeping the components of the framework reusable and exchangeable, experiments are simplified, which promotes further research in that area. Moreover, to optimize multiple mutually dependent features, e.g., index selection and compression configurations, we propose a linear programming (LP) based algorithm to derive an efficient tuning order automatically. Afterwards, we demonstrate the applicability and scalability of our approach with reproducible examples.},
  language  = {en}
}
@article{SchneiderWenigPapenbrock2021,
  author    = {Schneider, Johannes and Wenig, Phillip and Papenbrock, Thorsten},
  title     = {Distributed detection of sequential anomalies in univariate time series},
  series = {The VLDB journal : the international journal on very large data bases},
  volume    = {30},
  journal   = {The VLDB journal : the international journal on very large data bases},
  number    = {4},
  publisher = {Springer},
  address   = {Berlin},
  issn      = {1066-8888},
  doi       = {10.1007/s00778-021-00657-6},
  pages     = {579 -- 602},
  year      = {2021},
  abstract  = {The automated detection of sequential anomalies in time series is an essential task for many applications, such as the monitoring of technical systems, fraud detection in high-frequency trading, or the early detection of disease symptoms. All these applications require the detection to find all sequential anomalies possibly fast on potentially very large time series. In other words, the detection needs to be effective, efficient and scalable w.r.t. the input size. Series2Graph is an effective solution based on graph embeddings that are robust against re-occurring anomalies and can discover sequential anomalies of arbitrary length and works without training data. Yet, Series2Graph is no t scalable due to its single-threaded approach; it cannot, in particular, process arbitrarily large sequences due to the memory constraints of a single machine. In this paper, we propose our distributed anomaly detection system, short DADS, which is an efficient and scalable adaptation of Series2Graph. Based on the actor programming model, DADS distributes the input time sequence, intermediate state and the computation to all processors of a cluster in a way that minimizes communication costs and synchronization barriers. Our evaluation shows that DADS is orders of magnitude faster than S2G, scales almost linearly with the number of processors in the cluster and can process much larger input sequences due to its scale-out property.},
  language  = {en}
}
@phdthesis{Kluth2011,
  author    = {Kluth, Stephan},
  title     = {Quantitative modeling and analysis with FMC-QE},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-52987},
  school      = {Universit{\"a}t Potsdam},
  year      = {2011},
  abstract  = {The modeling and evaluation calculus FMC-QE, the Fundamental Modeling Concepts for Quanti-tative Evaluation [1], extends the Fundamental Modeling Concepts (FMC) for performance modeling and prediction. In this new methodology, the hierarchical service requests are in the main focus, because they are the origin of every service provisioning process. Similar to physics, these service requests are a tuple of value and unit, which enables hierarchical service request transformations at the hierarchical borders and therefore the hierarchical modeling. Through reducing the model complexity of the models by decomposing the system in different hierarchical views, the distinction between operational and control states and the calculation of the performance values on the assumption of the steady state, FMC-QE has a scalable applica-bility on complex systems. According to FMC, the system is modeled in a 3-dimensional hierarchical representation space, where system performance parameters are described in three arbitrarily fine-grained hierarchi-cal bipartite diagrams. The hierarchical service request structures are modeled in Entity Relationship Diagrams. The static server structures, divided into logical and real servers, are de-scribed as Block Diagrams. The dynamic behavior and the control structures are specified as Petri Nets, more precisely Colored Time Augmented Petri Nets. From the structures and pa-rameters of the performance model, a hierarchical set of equations is derived. The calculation of the performance values is done on the assumption of stationary processes and is based on fundamental laws of the performance analysis: Little's Law and the Forced Traffic Flow Law. Little's Law is used within the different hierarchical levels (horizontal) and the Forced Traffic Flow Law is the key to the dependencies among the hierarchical levels (vertical). This calculation is suitable for complex models and allows a fast (re-)calculation of different performance scenarios in order to support development and configuration decisions. Within the Research Group Zorn at the Hasso Plattner Institute, the work is embedded in a broader research in the development of FMC-QE. While this work is concentrated on the theoretical background, description and definition of the methodology as well as the extension and validation of the applicability, other topics are in the development of an FMC-QE modeling and evaluation tool and the usage of FMC-QE in the design of an adaptive transport layer in order to fulfill Quality of Service and Service Level Agreements in volatile service based environments. This thesis contains a state-of-the-art, the description of FMC-QE as well as extensions of FMC-QE in representative general models and case studies. In the state-of-the-art part of the thesis in chapter 2, an overview on existing Queueing Theory and Time Augmented Petri Net models and other quantitative modeling and evaluation languages and methodologies is given. Also other hierarchical quantitative modeling frameworks will be considered. The description of FMC-QE in chapter 3 consists of a summary of the foundations of FMC-QE, basic definitions, the graphical notations, the FMC-QE Calculus and the modeling of open queueing networks as an introductory example. The extensions of FMC-QE in chapter 4 consist of the integration of the summation method in order to support the handling of closed networks and the modeling of multiclass and semaphore scenarios. Furthermore, FMC-QE is compared to other performance modeling and evaluation approaches. In the case study part in chapter 5, proof-of-concept examples, like the modeling of a service based search portal, a service based SAP NetWeaver application and the Axis2 Web service framework will be provided. Finally, conclusions are given by a summary of contributions and an outlook on future work in chapter 6. [1] Werner Zorn. FMC-QE - A New Approach in Quantitative Modeling. In Hamid R. Arabnia, editor, Procee-dings of the International Conference on Modeling, Simulation and Visualization Methods (MSV 2007) within WorldComp '07, pages 280 - 287, Las Vegas, NV, USA, June 2007. CSREA Press. ISBN 1-60132-029-9.},
  language  = {en}
}
@book{DraisbachNaumannSzottetal.2012,
  author    = {Draisbach, Uwe and Naumann, Felix and Szott, Sascha and Wonneberg, Oliver},
  title     = {Adaptive windows for duplicate detection},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-143-1},
  issn      = {1613-5652},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-53007},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {41},
  year      = {2012},
  abstract  = {Duplicate detection is the task of identifying all groups of records within a data set that represent the same real-world entity, respectively. This task is difficult, because (i) representations might differ slightly, so some similarity measure must be defined to compare pairs of records and (ii) data sets might have a high volume making a pair-wise comparison of all records infeasible. To tackle the second problem, many algorithms have been suggested that partition the data set and compare all record pairs only within each partition. One well-known such approach is the Sorted Neighborhood Method (SNM), which sorts the data according to some key and then advances a window over the data comparing only records that appear within the same window. We propose several variations of SNM that have in common a varying window size and advancement. The general intuition of such adaptive windows is that there might be regions of high similarity suggesting a larger window size and regions of lower similarity suggesting a smaller window size. We propose and thoroughly evaluate several adaption strategies, some of which are provably better than the original SNM in terms of efficiency (same results with fewer comparisons).},
  language  = {en}
}
@phdthesis{Perscheid2013,
  author    = {Perscheid, Michael},
  title     = {Test-driven fault navigation for debugging reproducible failures},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-68155},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {The correction of software failures tends to be very cost-intensive because their debugging is an often time-consuming development activity. During this activity, developers largely attempt to understand what causes failures: Starting with a test case that reproduces the observable failure they have to follow failure causes on the infection chain back to the root cause (defect). This idealized procedure requires deep knowledge of the system and its behavior because failures and defects can be far apart from each other. Unfortunately, common debugging tools are inadequate for systematically investigating such infection chains in detail. Thus, developers have to rely primarily on their intuition and the localization of failure causes is not time-efficient. To prevent debugging by disorganized trial and error, experienced developers apply the scientific method and its systematic hypothesis-testing. However, even when using the scientific method, the search for failure causes can still be a laborious task. First, lacking expertise about the system makes it hard to understand incorrect behavior and to create reasonable hypotheses. Second, contemporary debugging approaches provide no or only partial support for the scientific method. In this dissertation, we present test-driven fault navigation as a debugging guide for localizing reproducible failures with the scientific method. Based on the analysis of passing and failing test cases, we reveal anomalies and integrate them into a breadth-first search that leads developers to defects. This systematic search consists of four specific navigation techniques that together support the creation, evaluation, and refinement of failure cause hypotheses for the scientific method. First, structure navigation localizes suspicious system parts and restricts the initial search space. Second, team navigation recommends experienced developers for helping with failures. Third, behavior navigation allows developers to follow emphasized infection chains back to root causes. Fourth, state navigation identifies corrupted state and reveals parts of the infection chain automatically. We implement test-driven fault navigation in our Path Tools framework for the Squeak/Smalltalk development environment and limit its computation cost with the help of our incremental dynamic analysis. This lightweight dynamic analysis ensures an immediate debugging experience with our tools by splitting the run-time overhead over multiple test runs depending on developers' needs. Hence, our test-driven fault navigation in combination with our incremental dynamic analysis answers important questions in a short time: where to start debugging, who understands failure causes best, what happened before failures, and which state properties are infected.},
  language  = {en}
}
@phdthesis{Berg2013,
  author    = {Berg, Gregor},
  title     = {Virtual prototypes for the model-based elicitation and validation of collaborative scenarios},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-69729},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {Requirements engineers have to elicit, document, and validate how stakeholders act and interact to achieve their common goals in collaborative scenarios. Only after gathering all information concerning who interacts with whom to do what and why, can a software system be designed and realized which supports the stakeholders to do their work. To capture and structure requirements of different (groups of) stakeholders, scenario-based approaches have been widely used and investigated. Still, the elicitation and validation of requirements covering collaborative scenarios remains complicated, since the required information is highly intertwined, fragmented, and distributed over several stakeholders. Hence, it can only be elicited and validated collaboratively. In times of globally distributed companies, scheduling and conducting workshops with groups of stakeholders is usually not feasible due to budget and time constraints. Talking to individual stakeholders, on the other hand, is feasible but leads to fragmented and incomplete stakeholder scenarios. Going back and forth between different individual stakeholders to resolve this fragmentation and explore uncovered alternatives is an error-prone, time-consuming, and expensive task for the requirements engineers. While formal modeling methods can be employed to automatically check and ensure consistency of stakeholder scenarios, such methods introduce additional overhead since their formal notations have to be explained in each interaction between stakeholders and requirements engineers. Tangible prototypes as they are used in other disciplines such as design, on the other hand, allow designers to feasibly validate and iterate concepts and requirements with stakeholders. This thesis proposes a model-based approach for prototyping formal behavioral specifications of stakeholders who are involved in collaborative scenarios. By simulating and animating such specifications in a remote domain-specific visualization, stakeholders can experience and validate the scenarios captured so far, i.e., how other stakeholders act and react. This interactive scenario simulation is referred to as a model-based virtual prototype. Moreover, through observing how stakeholders interact with a virtual prototype of their collaborative scenarios, formal behavioral specifications can be automatically derived which complete the otherwise fragmented scenarios. This, in turn, enables requirements engineers to elicit and validate collaborative scenarios in individual stakeholder sessions - decoupled, since stakeholders can participate remotely and are not forced to be available for a joint session at the same time. This thesis discusses and evaluates the feasibility, understandability, and modifiability of model-based virtual prototypes. Similarly to how physical prototypes are perceived, the presented approach brings behavioral models closer to being tangible for stakeholders and, moreover, combines the advantages of joint stakeholder sessions and decoupled sessions.},
  language  = {en}
}
@phdthesis{RoggeSolti2014,
  author    = {Rogge-Solti, Andreas},
  title     = {Probabilistic Estimation of Unobserved Process Events},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-70426},
  school      = {Universit{\"a}t Potsdam},
  year      = {2014},
  abstract  = {Organizations try to gain competitive advantages, and to increase customer satisfaction. To ensure the quality and efficiency of their business processes, they perform business process management. An important part of process management that happens on the daily operational level is process controlling. A prerequisite of controlling is process monitoring, i.e., keeping track of the performed activities in running process instances. Only by process monitoring can business analysts detect delays and react to deviations from the expected or guaranteed performance of a process instance. To enable monitoring, process events need to be collected from the process environment. When a business process is orchestrated by a process execution engine, monitoring is available for all orchestrated process activities. Many business processes, however, do not lend themselves to automatic orchestration, e.g., because of required freedom of action. This situation is often encountered in hospitals, where most business processes are manually enacted. Hence, in practice it is often inefficient or infeasible to document and monitor every process activity. Additionally, manual process execution and documentation is prone to errors, e.g., documentation of activities can be forgotten. Thus, organizations face the challenge of process events that occur, but are not observed by the monitoring environment. These unobserved process events can serve as basis for operational process decisions, even without exact knowledge of when they happened or when they will happen. An exemplary decision is whether to invest more resources to manage timely completion of a case, anticipating that the process end event will occur too late. This thesis offers means to reason about unobserved process events in a probabilistic way. We address decisive questions of process managers (e.g., "when will the case be finished?", or "when did we perform the activity that we forgot to document?") in this thesis. As main contribution, we introduce an advanced probabilistic model to business process management that is based on a stochastic variant of Petri nets. We present a holistic approach to use the model effectively along the business process lifecycle. Therefore, we provide techniques to discover such models from historical observations, to predict the termination time of processes, and to ensure quality by missing data management. We propose mechanisms to optimize configuration for monitoring and prediction, i.e., to offer guidance in selecting important activities to monitor. An implementation is provided as a proof of concept. For evaluation, we compare the accuracy of the approach with that of state-of-the-art approaches using real process data of a hospital. Additionally, we show its more general applicability in other domains by applying the approach on process data from logistics and finance.},
  language  = {en}
}
@phdthesis{Waetzoldt2016,
  author    = {W{\"a}tzoldt, Sebastian},
  title     = {Modeling collaborations in adaptive systems of systems},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-97494},
  school      = {Universit{\"a}t Potsdam},
  pages     = {XII, 380},
  year      = {2016},
  abstract  = {Recently, due to an increasing demand on functionality and flexibility, beforehand isolated systems have become interconnected to gain powerful adaptive Systems of Systems (SoS) solutions with an overall robust, flexible and emergent behavior. The adaptive SoS comprises a variety of different system types ranging from small embedded to adaptive cyber-physical systems. On the one hand, each system is independent, follows a local strategy and optimizes its behavior to reach its goals. On the other hand, systems must cooperate with each other to enrich the overall functionality to jointly perform on the SoS level reaching global goals, which cannot be satisfied by one system alone. Due to difficulties of local and global behavior optimizations conflicts may arise between systems that have to be solved by the adaptive SoS. This thesis proposes a modeling language that facilitates the description of an adaptive SoS by considering the adaptation capabilities in form of feedback loops as first class entities. Moreover, this thesis adopts the Models@runtime approach to integrate the available knowledge in the systems as runtime models into the modeled adaptation logic. Furthermore, the modeling language focuses on the description of system interactions within the adaptive SoS to reason about individual system functionality and how it emerges via collaborations to an overall joint SoS behavior. Therefore, the modeling language approach enables the specification of local adaptive system behavior, the integration of knowledge in form of runtime models and the joint interactions via collaboration to place the available adaptive behavior in an overall layered, adaptive SoS architecture. Beside the modeling language, this thesis proposes analysis rules to investigate the modeled adaptive SoS, which enables the detection of architectural patterns as well as design flaws and pinpoints to possible system threats. Moreover, a simulation framework is presented, which allows the direct execution of the modeled SoS architecture. Therefore, the analysis rules and the simulation framework can be used to verify the interplay between systems as well as the modeled adaptation effects within the SoS. This thesis realizes the proposed concepts of the modeling language by mapping them to a state of the art standard from the automotive domain and thus, showing their applicability to actual systems. Finally, the modeling language approach is evaluated by remodeling up to date research scenarios from different domains, which demonstrates that the modeling language concepts are powerful enough to cope with a broad range of existing research problems.},
  language  = {en}
}
@phdthesis{Heise2014,
  author    = {Heise, Arvid},
  title     = {Data cleansing and integration operators for a parallel data analytics platform},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-77100},
  school      = {Universit{\"a}t Potsdam},
  pages     = {ii, 179},
  year      = {2014},
  abstract  = {The data quality of real-world datasets need to be constantly monitored and maintained to allow organizations and individuals to reliably use their data. Especially, data integration projects suffer from poor initial data quality and as a consequence consume more effort and money. Commercial products and research prototypes for data cleansing and integration help users to improve the quality of individual and combined datasets. They can be divided into either standalone systems or database management system (DBMS) extensions. On the one hand, standalone systems do not interact well with DBMS and require time-consuming data imports and exports. On the other hand, DBMS extensions are often limited by the underlying system and do not cover the full set of data cleansing and integration tasks. We overcome both limitations by implementing a concise set of five data cleansing and integration operators on the parallel data analytics platform Stratosphere. We define the semantics of the operators, present their parallel implementation, and devise optimization techniques for individual operators and combinations thereof. Users specify declarative queries in our query language METEOR with our new operators to improve the data quality of individual datasets or integrate them to larger datasets. By integrating the data cleansing operators into the higher level language layer of Stratosphere, users can easily combine cleansing operators with operators from other domains, such as information extraction, to complex data flows. Through a generic description of the operators, the Stratosphere optimizer reorders operators even from different domains to find better query plans. As a case study, we reimplemented a part of the large Open Government Data integration project GovWILD with our new operators and show that our queries run significantly faster than the original GovWILD queries, which rely on relational operators. Evaluation reveals that our operators exhibit good scalability on up to 100 cores, so that even larger inputs can be efficiently processed by scaling out to more machines. Finally, our scripts are considerably shorter than the original GovWILD scripts, which results in better maintainability of the scripts.},
  language  = {en}
}
@book{KunzeWeske2016,
  author    = {Kunze, Matthias and Weske, Mathias},
  title     = {Behavioural Models},
  publisher = {Springer},
  address   = {Cham},
  isbn      = {978-3-319-44958-6},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {279},
  year      = {2016},
  abstract  = {This textbook introduces the basis for modelling and analysing discrete dynamic systems, such as computer programmes, soft- and hardware systems, and business processes. The underlying concepts are introduced and concrete modelling techniques are described, such as finite automata, state machines, and Petri nets. The concepts are related to concrete application scenarios, among which business processes play a prominent role. The book consists of three parts, the first of which addresses the foundations of behavioural modelling. After a general introduction to modelling, it introduces transition systems as a basic formalism for representing the behaviour of discrete dynamic systems. This section also discusses causality, a fundamental concept for modelling and reasoning about behaviour. In turn, Part II forms the heart of the book and is devoted to models of behaviour. It details both sequential and concurrent systems and introduces finite automata, state machines and several different types of Petri nets. One chapter is especially devoted to business process models, workflow patterns and BPMN, the industry standard for modelling business processes. Lastly, Part III investigates how the behaviour of systems can be analysed. To this end, it introduces readers to the concept of state spaces. Further chapters cover the comparison of behaviour and the formal analysis and verification of behavioural models. The book was written for students of computer science and software engineering, as well as for programmers and system analysts interested in the behaviour of the systems they work on. It takes readers on a journey from the fundamentals of behavioural modelling to advanced techniques for modelling and analysing sequential and concurrent systems, and thus provides them a deep understanding of the concepts and techniques introduced and how they can be applied to concrete application scenarios.},
  language  = {en}
}
@book{SmirnovReijersNugterenetal.2010,
  author    = {Smirnov, Sergey and Reijers, Hajo A. and Nugteren, Thijs and Weske, Mathias},
  title     = {Business process model abstraction : theory and practice},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-054-0},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-41782},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {17},
  year      = {2010},
  abstract  = {Business process management aims at capturing, understanding, and improving work in organizations. The central artifacts are process models, which serve different purposes. Detailed process models are used to analyze concrete working procedures, while high-level models show, for instance, handovers between departments. To provide different views on process models, business process model abstraction has emerged. While several approaches have been proposed, a number of abstraction use case that are both relevant for industry and scientifically challenging are yet to be addressed. In this paper we systematically develop, classify, and consolidate different use cases for business process model abstraction. The reported work is based on a study with BPM users in the health insurance sector and validated with a BPM consultancy company and a large BPM vendor. The identified fifteen abstraction use cases reflect the industry demand. The related work on business process model abstraction is evaluated against the use cases, which leads to a research agenda.},
  language  = {en}
}
@phdthesis{Lorey2014,
  author    = {Lorey, Johannes},
  title     = {What's in a query : analyzing, predicting, and managing linked data access},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-72312},
  school      = {Universit{\"a}t Potsdam},
  year      = {2014},
  abstract  = {The term Linked Data refers to connected information sources comprising structured data about a wide range of topics and for a multitude of applications. In recent years, the conceptional and technical foundations of Linked Data have been formalized and refined. To this end, well-known technologies have been established, such as the Resource Description Framework (RDF) as a Linked Data model or the SPARQL Protocol and RDF Query Language (SPARQL) for retrieving this information. Whereas most research has been conducted in the area of generating and publishing Linked Data, this thesis presents novel approaches for improved management. In particular, we illustrate new methods for analyzing and processing SPARQL queries. Here, we present two algorithms suitable for identifying structural relationships between these queries. Both algorithms are applied to a large number of real-world requests to evaluate the performance of the approaches and the quality of their results. Based on this, we introduce different strategies enabling optimized access of Linked Data sources. We demonstrate how the presented approach facilitates effective utilization of SPARQL endpoints by prefetching results relevant for multiple subsequent requests. Furthermore, we contribute a set of metrics for determining technical characteristics of such knowledge bases. To this end, we devise practical heuristics and validate them through thorough analysis of real-world data sources. We discuss the findings and evaluate their impact on utilizing the endpoints. Moreover, we detail the adoption of a scalable infrastructure for improving Linked Data discovery and consumption. As we outline in an exemplary use case, this platform is eligible both for processing and provisioning the corresponding information.},
  language  = {en}
}
@phdthesis{Steinert2014,
  author    = {Steinert, Bastian},
  title     = {Built-in recovery support for explorative programming},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-71305},
  school      = {Universit{\"a}t Potsdam},
  year      = {2014},
  abstract  = {This work introduces concepts and corresponding tool support to enable a complementary approach in dealing with recovery. Programmers need to recover a development state, or a part thereof, when previously made changes reveal undesired implications. However, when the need arises suddenly and unexpectedly, recovery often involves expensive and tedious work. To avoid tedious work, literature recommends keeping away from unexpected recovery demands by following a structured and disciplined approach, which consists of the application of various best practices including working only on one thing at a time, performing small steps, as well as making proper use of versioning and testing tools. However, the attempt to avoid unexpected recovery is both time-consuming and error-prone. On the one hand, it requires disproportionate effort to minimize the risk of unexpected situations. On the other hand, applying recommended practices selectively, which saves time, can hardly avoid recovery. In addition, the constant need for foresight and self-control has unfavorable implications. It is exhaustive and impedes creative problem solving. This work proposes to make recovery fast and easy and introduces corresponding support called CoExist. Such dedicated support turns situations of unanticipated recovery from tedious experiences into pleasant ones. It makes recovery fast and easy to accomplish, even if explicit commits are unavailable or tests have been ignored for some time. When mistakes and unexpected insights are no longer associated with tedious corrective actions, programmers are encouraged to change source code as a means to reason about it, as opposed to making changes only after structuring and evaluating them mentally. This work further reports on an implementation of the proposed tool support in the Squeak/Smalltalk development environment. The development of the tools has been accompanied by regular performance and usability tests. In addition, this work investigates whether the proposed tools affect programmers' performance. In a controlled lab study, 22 participants improved the design of two different applications. Using a repeated measurement setup, the study examined the effect of providing CoExist on programming performance. The result of analyzing 88 hours of programming suggests that built-in recovery support as provided with CoExist positively has a positive effect on programming performance in explorative programming tasks.},
  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{GieseHildebrandtNeumannetal.2012,
  author    = {Giese, Holger and Hildebrandt, Stephan and Neumann, Stefan and W{\"a}tzoldt, Sebastian},
  title     = {Industrial case study on the integration of SysML and AUTOSAR with triple graph grammars},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-191-2},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-60184},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {vi, 51},
  year      = {2012},
  abstract  = {During the overall development of complex engineering systems different modeling notations are employed. For example, in the domain of automotive systems system engineering models are employed quite early to capture the requirements and basic structuring of the entire system, while software engineering models are used later on to describe the concrete software architecture. Each model helps in addressing the specific design issue with appropriate notations and at a suitable level of abstraction. However, when we step forward from system design to the software design, the engineers have to ensure that all decisions captured in the system design model are correctly transferred to the software engineering model. Even worse, when changes occur later on in either model, today the consistency has to be reestablished in a cumbersome manual step. In this report, we present in an extended version of [Holger Giese, Stefan Neumann, and Stephan Hildebrandt. Model Synchronization at Work: Keeping SysML and AUTOSAR Models Consistent. In Gregor Engels, Claus Lewerentz, Wilhelm Sch{\"a}fer, Andy Sch{\"u}rr, and B. Westfechtel, editors, Graph Transformations and Model Driven Enginering - Essays Dedicated to Manfred Nagl on the Occasion of his 65th Birthday, volume 5765 of Lecture Notes in Computer Science, pages 555-579. Springer Berlin / Heidelberg, 2010.] how model synchronization and consistency rules can be applied to automate this task and ensure that the different models are kept consistent. We also introduce a general approach for model synchronization. Besides synchronization, the approach consists of tool adapters as well as consistency rules covering the overlap between the synchronized parts of a model and the rest. We present the model synchronization algorithm based on triple graph grammars in detail and further exemplify the general approach by means of a model synchronization solution between system engineering models in SysML and software engineering models in AUTOSAR which has been developed for an industrial partner. In the appendix as extension to [19] the meta-models and all TGG rules for the SysML to AUTOSAR model synchronization are documented.},
  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}
}
@book{HauptMarrHirschfeld2011,
  author    = {Haupt, Michael and Marr, Stefan and Hirschfeld, Robert},
  title     = {CSOM/PL : a virtual machine product line},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-134-9},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-52332},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {26},
  year      = {2011},
  abstract  = {CSOM/PL is a software product line (SPL) derived from applying multi-dimensional separation of concerns (MDSOC) techniques to the domain of high-level language virtual machine (VM) implementations. For CSOM/PL, we modularised CSOM, a Smalltalk VM implemented in C, using VMADL (virtual machine architecture description language). Several features of the original CSOM were encapsulated in VMADL modules and composed in various combinations. In an evaluation of our approach, we show that applying MDSOC and SPL principles to a domain as complex as that of VMs is not only feasible but beneficial, as it improves understandability, maintainability, and configurability of VM implementations without harming performance.},
  language  = {en}
}
@phdthesis{Bauckmann2013,
  author    = {Bauckmann, Jana},
  title     = {Dependency discovery for data integration},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-66645},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {Data integration aims to combine data of different sources and to provide users with a unified view on these data. This task is as challenging as valuable. In this thesis we propose algorithms for dependency discovery to provide necessary information for data integration. We focus on inclusion dependencies (INDs) in general and a special form named conditional inclusion dependencies (CINDs): (i) INDs enable the discovery of structure in a given schema. (ii) INDs and CINDs support the discovery of cross-references or links between schemas. An IND "A in B" simply states that all values of attribute A are included in the set of values of attribute B. We propose an algorithm that discovers all inclusion dependencies in a relational data source. The challenge of this task is the complexity of testing all attribute pairs and further of comparing all of each attribute pair's values. The complexity of existing approaches depends on the number of attribute pairs, while ours depends only on the number of attributes. Thus, our algorithm enables to profile entirely unknown data sources with large schemas by discovering all INDs. Further, we provide an approach to extract foreign keys from the identified INDs. We extend our IND discovery algorithm to also find three special types of INDs: (i) Composite INDs, such as "AB in CD", (ii) approximate INDs that allow a certain amount of values of A to be not included in B, and (iii) prefix and suffix INDs that represent special cross-references between schemas. Conditional inclusion dependencies are inclusion dependencies with a limited scope defined by conditions over several attributes. Only the matching part of the instance must adhere the dependency. We generalize the definition of CINDs distinguishing covering and completeness conditions and define quality measures for conditions. We propose efficient algorithms that identify covering and completeness conditions conforming to given quality thresholds. The challenge for this task is twofold: (i) Which (and how many) attributes should be used for the conditions? (ii) Which attribute values should be chosen for the conditions? Previous approaches rely on pre-selected condition attributes or can only discover conditions applying to quality thresholds of 100\%. Our approaches were motivated by two application domains: data integration in the life sciences and link discovery for linked open data. We show the efficiency and the benefits of our approaches for use cases in these domains.},
  language  = {en}
}
@book{MeyerPufahlFahlandetal.2013,
  author    = {Meyer, Andreas and Pufahl, Luise and Fahland, Dirk and Weske, Mathias},
  title     = {Modeling and enacting complex data dependencies in business processes},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-245-2},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-65103},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {40},
  year      = {2013},
  abstract  = {Enacting business processes in process engines requires the coverage of control flow, resource assignments, and process data. While the first two aspects are well supported in current process engines, data dependencies need to be added and maintained manually by a process engineer. Thus, this task is error-prone and time-consuming. In this report, we address the problem of modeling processes with complex data dependencies, e.g., m:n relationships, and their automatic enactment from process models. First, we extend BPMN data objects with few annotations to allow data dependency handling as well as data instance differentiation. Second, we introduce a pattern-based approach to derive SQL queries from process models utilizing the above mentioned extensions. Therewith, we allow automatic enactment of data-aware BPMN process models. We implemented our approach for the Activiti process engine to show applicability.},
  language  = {en}
}
@phdthesis{Tinnefeld2014,
  author    = {Tinnefeld, Christian},
  title     = {Building a columnar database on shared main memory-based storage},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-72063},
  school      = {Universit{\"a}t Potsdam},
  pages     = {175},
  year      = {2014},
  abstract  = {In the field of disk-based parallel database management systems exists a great variety of solutions based on a shared-storage or a shared-nothing architecture. In contrast, main memory-based parallel database management systems are dominated solely by the shared-nothing approach as it preserves the in-memory performance advantage by processing data locally on each server. We argue that this unilateral development is going to cease due to the combination of the following three trends: a) Nowadays network technology features remote direct memory access (RDMA) and narrows the performance gap between accessing main memory inside a server and of a remote server to and even below a single order of magnitude. b) Modern storage systems scale gracefully, are elastic, and provide high-availability. c) A modern storage system such as Stanford's RAMCloud even keeps all data resident in main memory. Exploiting these characteristics in the context of a main-memory parallel database management system is desirable. The advent of RDMA-enabled network technology makes the creation of a parallel main memory DBMS based on a shared-storage approach feasible. This thesis describes building a columnar database on shared main memory-based storage. The thesis discusses the resulting architecture (Part I), the implications on query processing (Part II), and presents an evaluation of the resulting solution in terms of performance, high-availability, and elasticity (Part III). In our architecture, we use Stanford's RAMCloud as shared-storage, and the self-designed and developed in-memory AnalyticsDB as relational query processor on top. AnalyticsDB encapsulates data access and operator execution via an interface which allows seamless switching between local and remote main memory, while RAMCloud provides not only storage capacity, but also processing power. Combining both aspects allows pushing-down the execution of database operators into the storage system. We describe how the columnar data processed by AnalyticsDB is mapped to RAMCloud's key-value data model and how the performance advantages of columnar data storage can be preserved. The combination of fast network technology and the possibility to execute database operators in the storage system opens the discussion for site selection. We construct a system model that allows the estimation of operator execution costs in terms of network transfer, data processed in memory, and wall time. This can be used for database operators that work on one relation at a time - such as a scan or materialize operation - to discuss the site selection problem (data pull vs. operator push). Since a database query translates to the execution of several database operators, it is possible that the optimal site selection varies per operator. For the execution of a database operator that works on two (or more) relations at a time, such as a join, the system model is enriched by additional factors such as the chosen algorithm (e.g. Grace- vs. Distributed Block Nested Loop Join vs. Cyclo-Join), the data partitioning of the respective relations, and their overlapping as well as the allowed resource allocation. We present an evaluation on a cluster with 60 nodes where all nodes are connected via RDMA-enabled network equipment. We show that query processing performance is about 2.4x slower if everything is done via the data pull operator execution strategy (i.e. RAMCloud is being used only for data access) and about 27\% slower if operator execution is also supported inside RAMCloud (in comparison to operating only on main memory inside a server without any network communication at all). The fast-crash recovery feature of RAMCloud can be leveraged to provide high-availability, e.g. a server crash during query execution only delays the query response for about one second. Our solution is elastic in a way that it can adapt to changing workloads a) within seconds, b) without interruption of the ongoing query processing, and c) without manual intervention.},
  language  = {en}
}
@book{HebigGieseBatoulisetal.2015,
  author    = {Hebig, Regina and Giese, Holger and Batoulis, Kimon and Langer, Philipp and Zamani Farahani, Armin and Yao, Gary and Wolowyk, Mychajlo},
  title     = {Development of AUTOSAR standard documents at Carmeq GmbH},
  number    = {92},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-317-6},
  issn      = {1613-5652},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-71535},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {52},
  year      = {2015},
  abstract  = {This report documents the captured MDE history of Carmeq GmbH, in context of the project Evolution of MDE Settings in Practice. The goal of the project is the elicitation of MDE approaches and their evolution.},
  language  = {en}
}
@phdthesis{Becker2013,
  author    = {Becker, Basil},
  title     = {Architectural modelling and verification of open service-oriented systems of systems},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-70158},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {Systems of Systems (SoS) have received a lot of attention recently. In this thesis we will focus on SoS that are built atop the techniques of Service-Oriented Architectures and thus combine the benefits and challenges of both paradigms. For this thesis we will understand SoS as ensembles of single autonomous systems that are integrated to a larger system, the SoS. The interesting fact about these systems is that the previously isolated systems are still maintained, improved and developed on their own. Structural dynamics is an issue in SoS, as at every point in time systems can join and leave the ensemble. This and the fact that the cooperation among the constituent systems is not necessarily observable means that we will consider these systems as open systems. Of course, the system has a clear boundary at each point in time, but this can only be identified by halting the complete SoS. However, halting a system of that size is practically impossible. Often SoS are combinations of software systems and physical systems. Hence a failure in the software system can have a serious physical impact what makes an SoS of this kind easily a safety-critical system. The contribution of this thesis is a modelling approach that extends OMG's SoaML and basically relies on collaborations and roles as an abstraction layer above the components. This will allow us to describe SoS at an architectural level. We will also give a formal semantics for our modelling approach which employs hybrid graph-transformation systems. The modelling approach is accompanied by a modular verification scheme that will be able to cope with the complexity constraints implied by the SoS' structural dynamics and size. Building such autonomous systems as SoS without evolution at the architectural level --- i. e. adding and removing of components and services --- is inadequate. Therefore our approach directly supports the modelling and verification of evolution.},
  language  = {en}
}
@phdthesis{Hebig2014,
  author    = {Hebig, Regina},
  title     = {Evolution of model-driven engineering settings in practice},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-70761},
  school      = {Universit{\"a}t Potsdam},
  year      = {2014},
  abstract  = {Nowadays, software systems are getting more and more complex. To tackle this challenge most diverse techniques, such as design patterns, service oriented architectures (SOA), software development processes, and model-driven engineering (MDE), are used to improve productivity, while time to market and quality of the products stay stable. Multiple of these techniques are used in parallel to profit from their benefits. While the use of sophisticated software development processes is standard, today, MDE is just adopted in practice. However, research has shown that the application of MDE is not always successful. It is not fully understood when advantages of MDE can be used and to what degree MDE can also be disadvantageous for productivity. Further, when combining different techniques that aim to affect the same factor (e.g. productivity) the question arises whether these techniques really complement each other or, in contrast, compensate their effects. Due to that, there is the concrete question how MDE and other techniques, such as software development process, are interrelated. Both aspects (advantages and disadvantages for productivity as well as the interrelation to other techniques) need to be understood to identify risks relating to the productivity impact of MDE. Before studying MDE's impact on productivity, it is necessary to investigate the range of validity that can be reached for the results. This includes two questions. First, there is the question whether MDE's impact on productivity is similar for all approaches of adopting MDE in practice. Second, there is the question whether MDE's impact on productivity for an approach of using MDE in practice remains stable over time. The answers for both questions are crucial for handling risks of MDE, but also for the design of future studies on MDE success. This thesis addresses these questions with the goal to support adoption of MDE in future. To enable a differentiated discussion about MDE, the term MDE setting'' is introduced. MDE setting refers to the applied technical setting, i.e. the employed manual and automated activities, artifacts, languages, and tools. An MDE setting's possible impact on productivity is studied with a focus on changeability and the interrelation to software development processes. This is done by introducing a taxonomy of changeability concerns that might be affected by an MDE setting. Further, three MDE traits are identified and it is studied for which manifestations of these MDE traits software development processes are impacted. To enable the assessment and evaluation of an MDE setting's impacts, the Software Manufacture Model language is introduced. This is a process modeling language that allows to reason about how relations between (modeling) artifacts (e.g. models or code files) change during application of manual or automated development activities. On that basis, risk analysis techniques are provided. These techniques allow identifying changeability risks and assessing the manifestations of the MDE traits (and with it an MDE setting's impact on software development processes). To address the range of validity, MDE settings from practice and their evolution histories were capture in context of this thesis. First, this data is used to show that MDE settings cover the whole spectrum concerning their impact on changeability or interrelation to software development processes. Neither it is seldom that MDE settings are neutral for processes nor is it seldom that MDE settings have impact on processes. Similarly, the impact on changeability differs relevantly. Second, a taxonomy of evolution of MDE settings is introduced. In that context it is discussed to what extent different types of changes on an MDE setting can influence this MDE setting's impact on changeability and the interrelation to processes. The category of structural evolution, which can change these characteristics of an MDE setting, is identified. The captured MDE settings from practice are used to show that structural evolution exists and is common. In addition, some examples of structural evolution steps are collected that actually led to a change in the characteristics of the respective MDE settings. Two implications are: First, the assessed diversity of MDE settings evaluates the need for the analysis techniques that shall be presented in this thesis. Second, evolution is one explanation for the diversity of MDE settings in practice. To summarize, this thesis studies the nature and evolution of MDE settings in practice. As a result support for the adoption of MDE settings is provided in form of techniques for the identification of risks relating to productivity impacts.},
  language  = {en}
}
@phdthesis{Lange2013,
  author    = {Lange, Dustin},
  title     = {Effective and efficient similarity search in databases},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-65712},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {Given a large set of records in a database and a query record, similarity search aims to find all records sufficiently similar to the query record. To solve this problem, two main aspects need to be considered: First, to perform effective search, the set of relevant records is defined using a similarity measure. Second, an efficient access method is to be found that performs only few database accesses and comparisons using the similarity measure. This thesis solves both aspects with an emphasis on the latter. In the first part of this thesis, a frequency-aware similarity measure is introduced. Compared record pairs are partitioned according to frequencies of attribute values. For each partition, a different similarity measure is created: machine learning techniques combine a set of base similarity measures into an overall similarity measure. After that, a similarity index for string attributes is proposed, the State Set Index (SSI), which is based on a trie (prefix tree) that is interpreted as a nondeterministic finite automaton. For processing range queries, the notion of query plans is introduced in this thesis to describe which similarity indexes to access and which thresholds to apply. The query result should be as complete as possible under some cost threshold. Two query planning variants are introduced: (1) Static planning selects a plan at compile time that is used for all queries. (2) Query-specific planning selects a different plan for each query. For answering top-k queries, the Bulk Sorted Access Algorithm (BSA) is introduced, which retrieves large chunks of records from the similarity indexes using fixed thresholds, and which focuses its efforts on records that are ranked high in more than one attribute and thus promising candidates. The described components form a complete similarity search system. Based on prototypical implementations, this thesis shows comparative evaluation results for all proposed approaches on different real-world data sets, one of which is a large person data set from a German credit rating agency.},
  language  = {en}
}
@book{CalmezHesseSiegmundetal.2013,
  author    = {Calmez, Conrad and Hesse, Hubert and Siegmund, Benjamin and Stamm, Sebastian and Thomschke, Astrid and Hirschfeld, Robert and Ingalls, Dan and Lincke, Jens},
  title     = {Explorative authoring of Active Web content in a mobile environment},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-232-2},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64054},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {132},
  year      = {2013},
  abstract  = {Developing rich Web applications can be a complex job - especially when it comes to mobile device support. Web-based environments such as Lively Webwerkstatt can help developers implement such applications by making the development process more direct and interactive. Further the process of developing software is collaborative which creates the need that the development environment offers collaboration facilities. This report describes extensions of the webbased development environment Lively Webwerkstatt such that it can be used in a mobile environment. The extensions are collaboration mechanisms, user interface adaptations but as well event processing and performance measuring on mobile devices.},
  language  = {en}
}
@book{WistWollowski2007,
  author    = {Wist, Dominic and Wollowski, Ralf},
  title     = {STG decomposition : avoiding irreducible CSC conflicts by internal communication},
  isbn      = {978-3-940793-02-7},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-32968},
  publisher      = {Universit{\"a}t Potsdam},
  year      = {2007},
  abstract  = {Inhalt: 1 Introduction 2 Basic Definitions 3 Achieving SI Implementability by Internal Communication 4 Towards a Structural Method 5 Examples 6 Conclusions and Future Work},
  language  = {en}
}
@book{OPUS4-3141,
  title     = {Java language conversion assistant : an analysis},
  editor    = {Richter, Stefan and Henze, Stefan and B{\"u}ttner, Eiko and Bach, Steffen and Polze, Andreas},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-937786-10-0},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-33151},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {166},
  year      = {2004},
  abstract  = {This document is an analysis of the 'Java Language Conversion Assistant'. Itr will also cover a language analysis of the Java Programming Language as well as a survey of related work concerning Java and C\# interoperability on the one hand and language conversion in general on the other. Part I deals with language analysis. Part II covers the JLCA tool and tests used to analyse the tool. Additionally, it gives an overview of the above mentioned related work. Part III presents a complete project that has been translated using the JLCA.},
  language  = {en}
}
@book{OPUS4-3143,
  title     = {Conceptual architecture patterns : FMC-based representations},
  editor    = {Gr{\"o}ne, Bernhard and Keller, Frank},
  isbn      = {978-3-935024-98-3},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-33173},
  publisher      = {Universit{\"a}t Potsdam},
  year      = {2004},
  abstract  = {This document presents the results of the seminar "Coneptual Arachitecture Patterns" of the winter term 2002 in the Hasso-Plattner-Institute. It is a compilation of the student's elaborations dealing with some conceptual architecture patterns which can be found in literature. One important focus laid on the runtime structures and the presentation of the patterns. 1. Introduction 1.1. The Seminar 1.2. Literature 2 Pipes and Filters (Andr{\´e} Langhorst and Martin Steinle) 3 Broker (Konrad H{\"u}bner and Einar L{\"u}ck) 4 Microkernel (Eiko B{\"u}ttner and Stefan Richter) 5 Component Configurator (Stefan R{\"o}ck and Alexander Gierak) 6 Interceptor (Marc F{\"o}rster and Peter Aschenbrenner) 7 Reactor (Nikolai Cieslak and Dennis Eder) 8 Half-Sync/Half-Async (Robert Mitschke and Harald Schubert) 9 Leader/Followers (Dennis Klemann and Steffen Schmidt)},
  language  = {en}
}
@book{KuropkaMeyer2005,
  author    = {Kuropka, Dominik and Meyer, Harald},
  title     = {Survey on Service Composition},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {3-937786-78-3},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-33787},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {35},
  year      = {2005},
  abstract  = {It is predicted that Service-oriented Architectures (SOA) will have a high impact on future electronic business and markets. Services will provide an self-contained and standardised interface towards business and are considered as the future platform for business-to-business and business-toconsumer trades. Founded by the complexity of real world business scenarios a huge need for an easy, flexible and automated creation and enactment of service compositions is observed. This survey explores the relationship of service composition with workflow management—a technology/ concept already in use in many business environments. The similarities between the both and the key differences between them are elaborated. Furthermore methods for composition of services ranging from manual, semi- to full-automated composition are sketched. This survey concludes that current tools for service composition are in an immature state and that there is still much research to do before service composition can be used easily and conveniently in real world scenarios. However, since automated service composition is a key enabler for the full potential of Service-oriented Architectures, further research on this field is imperative. This survey closes with a formal sample scenario presented in appendix A to give the reader an impression on how full-automated service composition works.},
  language  = {en}
}
@book{GroeneKnoepfelKugeletal.2004,
  author    = {Gr{\"o}ne, Bernhard and Kn{\"o}pfel, Andreas and Kugel, Rudolf and Schmidt, Oliver},
  title     = {The Apache Modeling Project},
  isbn      = {978-3-937786-14-8},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-33147},
  publisher      = {Universit{\"a}t Potsdam},
  year      = {2004},
  abstract  = {This document presents an introduction to the Apache HTTP Server, covering both an overview and implementation details. It presents results of the Apache Modelling Project done by research assistants and students of the Hasso-Plattner-Institute in 2001, 2002 and 2003. The Apache HTTP Server was used to introduce students to the application of the modeling technique FMC, a method that supports transporting knowledge about complex systems in the domain of information processing (software and hardware as well). After an introduction to HTTP servers in general, we will focus on protocols and web technology. Then we will discuss Apache, its operational environment and its extension capabilities— the module API. Finally we will guide the reader through parts of the Apache source code and explain the most important pieces.},
  language  = {en}
}
@inproceedings{PalixLawallThomasetal.2010,
  author    = {Palix, Nicolas and Lawall, Julia L. and Thomas, Ga{\"e}l and Muller, Gilles},
  title     = {How Often do Experts Make Mistakes?},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-41327},
  year      = {2010},
  abstract  = {Large open-source software projects involve developers with a wide variety of backgrounds and expertise. Such software projects furthermore include many internal APIs that developers must understand and use properly. According to the intended purpose of these APIs, they are more or less frequently used, and used by developers with more or less expertise. In this paper, we study the impact of usage patterns and developer expertise on the rate of defects occurring in the use of internal APIs. For this preliminary study, we focus on memory management APIs in the Linux kernel, as the use of these has been shown to be highly error prone in previous work. We study defect rates and developer expertise, to consider e.g., whether widely used APIs are more defect prone because they are used by less experienced developers, or whether defects in widely used APIs are more likely to be fixed.},
  language  = {en}
}
@inproceedings{OPUS4-3948,
  title     = {Preface},
  editor    = {Adams, Bram and Haupt, Michael and Lohmann, Daniel},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-41338},
  year      = {2010},
  abstract  = {Aspect-oriented programming, component models, and design patterns are modern and actively evolving techniques for improving the modularization of complex software. In particular, these techniques hold great promise for the development of "systems infrastructure" software, e.g., application servers, middleware, virtual machines, compilers, operating systems, and other software that provides general services for higher-level applications. The developers of infrastructure software are faced with increasing demands from application programmers needing higher-level support for application development. Meeting these demands requires careful use of software modularization techniques, since infrastructural concerns are notoriously hard to modularize. Aspects, components, and patterns provide very different means to deal with infrastructure software, but despite their differences, they have much in common. For instance, component models try to free the developer from the need to deal directly with services like security or transactions. These are primary examples of crosscutting concerns, and modularizing such concerns are the main target of aspect-oriented languages. Similarly, design patterns like Visitor and Interceptor facilitate the clean modularization of otherwise tangled concerns. Building on the ACP4IS meetings at AOSD 2002-2009, this workshop aims to provide a highly interactive forum for researchers and developers to discuss the application of and relationships between aspects, components, and patterns within modern infrastructure software. The goal is to put aspects, components, and patterns into a common reference frame and to build connections between the software engineering and systems communities.},
  language  = {en}
}
@inproceedings{BynensVanLanduytTruyenetal.2010,
  author    = {Bynens, Maarten and Van Landuyt, Dimitri and Truyen, Eddy and Joosen, Wouter},
  title     = {Towards reusable aspects: the callback mismatch problem},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-41347},
  year      = {2010},
  abstract  = {Because software development is increasingly expensive and timeconsuming, software reuse gains importance. Aspect-oriented software development modularizes crosscutting concerns which enables their systematic reuse. Literature provides a number of AOP patterns and best practices for developing reusable aspects based on compelling examples for concerns like tracing, transactions and persistence. However, such best practices are lacking for systematically reusing invasive aspects. In this paper, we present the 'callback mismatch problem'. This problem arises in the context of abstraction mismatch, in which the aspect is required to issue a callback to the base application. As a consequence, the composition of invasive aspects is cumbersome to implement, difficult to maintain and impossible to reuse. We motivate this problem in a real-world example, show that it persists in the current state-of-the-art, and outline the need for advanced aspectual composition mechanisms to deal with this.},
  language  = {en}
}
@inproceedings{Harrison2010,
  author    = {Harrison, William},
  title     = {Malleability, obliviousness and aspects for broadcast service attachment},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-41389},
  year      = {2010},
  abstract  = {An important characteristic of Service-Oriented Architectures is that clients do not depend on the service implementation's internal assignment of methods to objects. It is perhaps the most important technical characteristic that differentiates them from more common object-oriented solutions. This characteristic makes clients and services malleable, allowing them to be rearranged at run-time as circumstances change. That improvement in malleability is impaired by requiring clients to direct service requests to particular services. Ideally, the clients are totally oblivious to the service structure, as they are to aspect structure in aspect-oriented software. Removing knowledge of a method implementation's location, whether in object or service, requires re-defining the boundary line between programming language and middleware, making clearer specification of dependence on protocols, and bringing the transaction-like concept of failure scopes into language semantics as well. This paper explores consequences and advantages of a transition from object-request brokering to service-request brokering, including the potential to improve our ability to write more parallel software.},
  language  = {en}
}
@book{GellerHirschfeldBracha2010,
  author    = {Geller, Felix and Hirschfeld, Robert and Bracha, Gilad},
  title     = {Pattern Matching for an object-oriented and dynamically typed programming language},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-065-6},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-43035},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {81},
  year      = {2010},
  abstract  = {Pattern matching is a well-established concept in the functional programming community. It provides the means for concisely identifying and destructuring values of interest. This enables a clean separation of data structures and respective functionality, as well as dispatching functionality based on more than a single value. Unfortunately, expressive pattern matching facilities are seldomly incorporated in present object-oriented programming languages. We present a seamless integration of pattern matching facilities in an object-oriented and dynamically typed programming language: Newspeak. We describe language extensions to improve the practicability and integrate our additions with the existing programming environment for Newspeak. This report is based on the first author's master's thesis.},
  language  = {en}
}
@phdthesis{Semmo2016,
  author    = {Semmo, Amir},
  title     = {Design and implementation of non-photorealistic rendering techniques for 3D geospatial data},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-99525},
  school      = {Universit{\"a}t Potsdam},
  pages     = {XVI, 155},
  year      = {2016},
  abstract  = {Geospatial data has become a natural part of a growing number of information systems and services in the economy, society, and people's personal lives. In particular, virtual 3D city and landscape models constitute valuable information sources within a wide variety of applications such as urban planning, navigation, tourist information, and disaster management. Today, these models are often visualized in detail to provide realistic imagery. However, a photorealistic rendering does not automatically lead to high image quality, with respect to an effective information transfer, which requires important or prioritized information to be interactively highlighted in a context-dependent manner. Approaches in non-photorealistic renderings particularly consider a user's task and camera perspective when attempting optimal expression, recognition, and communication of important or prioritized information. However, the design and implementation of non-photorealistic rendering techniques for 3D geospatial data pose a number of challenges, especially when inherently complex geometry, appearance, and thematic data must be processed interactively. Hence, a promising technical foundation is established by the programmable and parallel computing architecture of graphics processing units. This thesis proposes non-photorealistic rendering techniques that enable both the computation and selection of the abstraction level of 3D geospatial model contents according to user interaction and dynamically changing thematic information. To achieve this goal, the techniques integrate with hardware-accelerated rendering pipelines using shader technologies of graphics processing units for real-time image synthesis. The techniques employ principles of artistic rendering, cartographic generalization, and 3D semiotics—unlike photorealistic rendering—to synthesize illustrative renditions of geospatial feature type entities such as water surfaces, buildings, and infrastructure networks. In addition, this thesis contributes a generic system that enables to integrate different graphic styles—photorealistic and non-photorealistic—and provide their seamless transition according to user tasks, camera view, and image resolution. Evaluations of the proposed techniques have demonstrated their significance to the field of geospatial information visualization including topics such as spatial perception, cognition, and mapping. In addition, the applications in illustrative and focus+context visualization have reflected their potential impact on optimizing the information transfer regarding factors such as cognitive load, integration of non-realistic information, visualization of uncertainty, and visualization on small displays.},
  language  = {en}
}
@phdthesis{Kyprianidis2013,
  author    = {Kyprianidis, Jan Eric},
  title     = {Structure adaptive stylization of images and video},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64104},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {In the early days of computer graphics, research was mainly driven by the goal to create realistic synthetic imagery. By contrast, non-photorealistic computer graphics, established as its own branch of computer graphics in the early 1990s, is mainly motivated by concepts and principles found in traditional art forms, such as painting, illustration, and graphic design, and it investigates concepts and techniques that abstract from reality using expressive, stylized, or illustrative rendering techniques. This thesis focuses on the artistic stylization of two-dimensional content and presents several novel automatic techniques for the creation of simplified stylistic illustrations from color images, video, and 3D renderings. Primary innovation of these novel techniques is that they utilize the smooth structure tensor as a simple and efficient way to obtain information about the local structure of an image. More specifically, this thesis contributes to knowledge in this field in the following ways. First, a comprehensive review of the structure tensor is provided. In particular, different methods for integrating the minor eigenvector field of the smoothed structure tensor are developed, and the superiority of the smoothed structure tensor over the popular edge tangent flow is demonstrated. Second, separable implementations of the popular bilateral and difference of Gaussians filters that adapt to the local structure are presented. These filters avoid artifacts while being computationally highly efficient. Taken together, both provide an effective way to create a cartoon-style effect. Third, a generalization of the Kuwahara filter is presented that avoids artifacts by adapting the shape, scale, and orientation of the filter to the local structure. This causes directional image features to be better preserved and emphasized, resulting in overall sharper edges and a more feature-abiding painterly effect. In addition to the single-scale variant, a multi-scale variant is presented, which is capable of performing a highly aggressive abstraction. Fourth, a technique that builds upon the idea of combining flow-guided smoothing with shock filtering is presented, allowing for an aggressive exaggeration and an emphasis of directional image features. All presented techniques are suitable for temporally coherent per-frame filtering of video or dynamic 3D renderings, without requiring expensive extra processing, such as optical flow. Moreover, they can be efficiently implemented to process content in real-time on a GPU.},
  language  = {en}
}
@phdthesis{Truemper2014,
  author    = {Tr{\"u}mper, Jonas},
  title     = {Visualization techniques for the analysis of software behavior and related structures},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-72145},
  school      = {Universit{\"a}t Potsdam},
  year      = {2014},
  abstract  = {Software maintenance encompasses any changes made to a software system after its initial deployment and is thereby one of the key phases in the typical software-engineering lifecycle. In software maintenance, we primarily need to understand structural and behavioral aspects, which are difficult to obtain, e.g., by code reading. Software analysis is therefore a vital tool for maintaining these systems: It provides - the preferably automated - means to extract and evaluate information from their artifacts such as software structure, runtime behavior, and related processes. However, such analysis typically results in massive raw data, so that even experienced engineers face difficulties directly examining, assessing, and understanding these data. Among other things, they require tools with which to explore the data if no clear question can be formulated beforehand. For this, software analysis and visualization provide its users with powerful interactive means. These enable the automation of tasks and, particularly, the acquisition of valuable and actionable insights into the raw data. For instance, one means for exploring runtime behavior is trace visualization. This thesis aims at extending and improving the tool set for visual software analysis by concentrating on several open challenges in the fields of dynamic and static analysis of software systems. This work develops a series of concepts and tools for the exploratory visualization of the respective data to support users in finding and retrieving information on the system artifacts concerned. This is a difficult task, due to the lack of appropriate visualization metaphors; in particular, the visualization of complex runtime behavior poses various questions and challenges of both a technical and conceptual nature. This work focuses on a set of visualization techniques for visually representing control-flow related aspects of software traces from shared-memory software systems: A trace-visualization concept based on icicle plots aids in understanding both single-threaded as well as multi-threaded runtime behavior on the function level. The concept's extensibility further allows the visualization and analysis of specific aspects of multi-threading such as synchronization, the correlation of such traces with data from static software analysis, and a comparison between traces. Moreover, complementary techniques for simultaneously analyzing system structures and the evolution of related attributes are proposed. These aim at facilitating long-term planning of software architecture and supporting management decisions in software projects by extensions to the circular-bundle-view technique: An extension to 3-dimensional space allows for the use of additional variables simultaneously; interaction techniques allow for the modification of structures in a visual manner. The concepts and techniques presented here are generic and, as such, can be applied beyond software analysis for the visualization of similarly structured data. The techniques' practicability is demonstrated by several qualitative studies using subject data from industry-scale software systems. The studies provide initial evidence that the techniques' application yields useful insights into the subject data and its interrelationships in several scenarios.},
  language  = {en}
}
@book{DoellnerKirschNienhaus2005,
  author    = {D{\"o}llner, J{\"u}rgen Roland Friedrich and Kirsch, Florian and Nienhaus, Marc},
  title     = {Visualizing Design and Spatial Assembly of Interactive CSG},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-937786-56-2},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-33771},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {8},
  year      = {2005},
  abstract  = {For interactive construction of CSG models understanding the layout of a model is essential for its efficient manipulation. To understand position and orientation of aggregated components of a CSG model, we need to realize its visible and occluded parts as a whole. Hence, transparency and enhanced outlines are key techniques to assist comprehension. We present a novel real-time rendering technique for visualizing design and spatial assembly of CSG models. As enabling technology we combine an image-space CSG rendering algorithm with blueprint rendering. Blueprint rendering applies depth peeling for extracting layers of ordered depth from polygonal models and then composes them in sorted order facilitating a clear insight of the models. We develop a solution for implementing depth peeling for CSG models considering their depth complexity. Capturing surface colors of each layer and later combining the results allows for generating order-independent transparency as one major rendering technique for CSG models. We further define visually important edges for CSG models and integrate an image-space edgeenhancement technique for detecting them in each layer. In this way, we extract visually important edges that are directly and not directly visible to outline a model's layout. Combining edges with transparency rendering, finally, generates edge-enhanced depictions of image-based CSG models and allows us to realize their complex, spatial assembly.},
  language  = {en}
}
@article{SchmidlPapenbrock2022,
  author    = {Schmidl, Sebastian and Papenbrock, Thorsten},
  title     = {Efficient distributed discovery of bidirectional order dependencies},
  series = {The VLDB journal},
  volume    = {31},
  journal   = {The VLDB journal},
  number    = {1},
  publisher = {Springer},
  address   = {Berlin ; Heidelberg ; New York},
  issn      = {1066-8888},
  doi       = {10.1007/s00778-021-00683-4},
  pages     = {49 -- 74},
  year      = {2022},
  abstract  = {Bidirectional order dependencies (bODs) capture order relationships between lists of attributes in a relational table. They can express that, for example, sorting books by publication date in ascending order also sorts them by age in descending order. The knowledge about order relationships is useful for many data management tasks, such as query optimization, data cleaning, or consistency checking. Because the bODs of a specific dataset are usually not explicitly given, they need to be discovered. The discovery of all minimal bODs (in set-based canonical form) is a task with exponential complexity in the number of attributes, though, which is why existing bOD discovery algorithms cannot process datasets of practically relevant size in a reasonable time. In this paper, we propose the distributed bOD discovery algorithm DISTOD, whose execution time scales with the available hardware. DISTOD is a scalable, robust, and elastic bOD discovery approach that combines efficient pruning techniques for bOD candidates in set-based canonical form with a novel, reactive, and distributed search strategy. Our evaluation on various datasets shows that DISTOD outperforms both single-threaded and distributed state-of-the-art bOD discovery algorithms by up to orders of magnitude; it can, in particular, process much larger datasets.},
  language  = {en}
}
@article{ChauhanFriedrichRothenberger2020,
  author    = {Chauhan, Ankit and Friedrich, Tobias and Rothenberger, Ralf},
  title     = {Greed is good for deterministic scale-free networks},
  series = {Algorithmica : an international journal in computer science},
  volume    = {82},
  journal   = {Algorithmica : an international journal in computer science},
  number    = {11},
  publisher = {Springer},
  address   = {New York},
  issn      = {0178-4617},
  doi       = {10.1007/s00453-020-00729-z},
  pages     = {3338 -- 3389},
  year      = {2020},
  abstract  = {Large real-world networks typically follow a power-law degree distribution. To study such networks, numerous random graph models have been proposed. However, real-world networks are not drawn at random. Therefore, Brach et al. (27th symposium on discrete algorithms (SODA), pp 1306-1325, 2016) introduced two natural deterministic conditions: (1) a power-law upper bound on the degree distribution (PLB-U) and (2) power-law neighborhoods, that is, the degree distribution of neighbors of each vertex is also upper bounded by a power law (PLB-N). They showed that many real-world networks satisfy both properties and exploit them to design faster algorithms for a number of classical graph problems. We complement their work by showing that some well-studied random graph models exhibit both of the mentioned PLB properties. PLB-U and PLB-N hold with high probability for Chung-Lu Random Graphs and Geometric Inhomogeneous Random Graphs and almost surely for Hyperbolic Random Graphs. As a consequence, all results of Brach et al. also hold with high probability or almost surely for those random graph classes. In the second part we study three classical NP-hard optimization problems on PLB networks. It is known that on general graphs with maximum degree Delta, a greedy algorithm, which chooses nodes in the order of their degree, only achieves a Omega (ln Delta)-approximation forMinimum Vertex Cover and Minimum Dominating Set, and a Omega(Delta)-approximation forMaximum Independent Set. We prove that the PLB-U property with beta>2 suffices for the greedy approach to achieve a constant-factor approximation for all three problems. We also show that these problems are APX-hard even if PLB-U, PLB-N, and an additional power-law lower bound on the degree distribution hold. Hence, a PTAS cannot be expected unless P = NP. Furthermore, we prove that all three problems are in MAX SNP if the PLB-U property holds.},
  language  = {en}
}
@article{BarkowskyGiese2020,
  author    = {Barkowsky, Matthias and Giese, Holger},
  title     = {Hybrid search plan generation for generalized graph pattern matching},
  series = {Journal of logical and algebraic methods in programming},
  volume    = {114},
  journal   = {Journal of logical and algebraic methods in programming},
  publisher = {Elsevier},
  address   = {New York},
  issn      = {2352-2208},
  doi       = {10.1016/j.jlamp.2020.100563},
  pages     = {29},
  year      = {2020},
  abstract  = {In recent years, the increased interest in application areas such as social networks has resulted in a rising popularity of graph-based approaches for storing and processing large amounts of interconnected data. To extract useful information from the growing network structures, efficient querying techniques are required. In this paper, we propose an approach for graph pattern matching that allows a uniform handling of arbitrary constraints over the query vertices. Our technique builds on a previously introduced matching algorithm, which takes concrete host graph information into account to dynamically adapt the employed search plan during query execution. The dynamic algorithm is combined with an existing static approach for search plan generation, resulting in a hybrid technique which we further extend by a more sophisticated handling of filtering effects caused by constraint checks. We evaluate the presented concepts empirically based on an implementation for our graph pattern matching tool, the Story Diagram Interpreter, with queries and data provided by the LDBC Social Network Benchmark. Our results suggest that the hybrid technique may improve search efficiency in several cases, and rarely reduces efficiency.},
  language  = {en}
}
@article{HackerKrestelGrundmannetal.2020,
  author    = {Hacker, Philipp and Krestel, Ralf and Grundmann, Stefan and Naumann, Felix},
  title     = {Explainable AI under contract and tort law},
  series = {Artificial intelligence and law},
  volume    = {28},
  journal   = {Artificial intelligence and law},
  number    = {4},
  publisher = {Springer},
  address   = {Dordrecht},
  issn      = {0924-8463},
  doi       = {10.1007/s10506-020-09260-6},
  pages     = {415 -- 439},
  year      = {2020},
  abstract  = {This paper shows that the law, in subtle ways, may set hitherto unrecognized incentives for the adoption of explainable machine learning applications. In doing so, we make two novel contributions. First, on the legal side, we show that to avoid liability, professional actors, such as doctors and managers, may soon be legally compelled to use explainable ML models. We argue that the importance of explainability reaches far beyond data protection law, and crucially influences questions of contractual and tort liability for the use of ML models. To this effect, we conduct two legal case studies, in medical and corporate merger applications of ML. As a second contribution, we discuss the (legally required) trade-off between accuracy and explainability and demonstrate the effect in a technical case study in the context of spam classification.},
  language  = {en}
}
@phdthesis{Trapp2013,
  author    = {Trapp, Matthias},
  title     = {Interactive rendering techniques for focus+context visualization of 3D geovirtual environments},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-66824},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {This thesis introduces a collection of new real-time rendering techniques and applications for focus+context visualization of interactive 3D geovirtual environments such as virtual 3D city and landscape models. These environments are generally characterized by a large number of objects and are of high complexity with respect to geometry and textures. For these reasons, their interactive 3D rendering represents a major challenge. Their 3D depiction implies a number of weaknesses such as occlusions, cluttered image contents, and partial screen-space usage. To overcome these limitations and, thus, to facilitate the effective communication of geo-information, principles of focus+context visualization can be used for the design of real-time 3D rendering techniques for 3D geovirtual environments (see Figure). In general, detailed views of a 3D geovirtual environment are combined seamlessly with abstracted views of the context within a single image. To perform the real-time image synthesis required for interactive visualization, dedicated parallel processors (GPUs) for rasterization of computer graphics primitives are used. For this purpose, the design and implementation of appropriate data structures and rendering pipelines are necessary. The contribution of this work comprises the following five real-time rendering methods: • The rendering technique for 3D generalization lenses enables the combination of different 3D city geometries (e.g., generalized versions of a 3D city model) in a single image in real time. The method is based on a generalized and fragment-precise clipping approach, which uses a compressible, raster-based data structure. It enables the combination of detailed views in the focus area with the representation of abstracted variants in the context area. • The rendering technique for the interactive visualization of dynamic raster data in 3D geovirtual environments facilitates the rendering of 2D surface lenses. It enables a flexible combination of different raster layers (e.g., aerial images or videos) using projective texturing for decoupling image and geometry data. Thus, various overlapping and nested 2D surface lenses of different contents can be visualized interactively. • The interactive rendering technique for image-based deformation of 3D geovirtual environments enables the real-time image synthesis of non-planar projections, such as cylindrical and spherical projections, as well as multi-focal 3D fisheye-lenses and the combination of planar and non-planar projections. • The rendering technique for view-dependent multi-perspective views of 3D geovirtual environments, based on the application of global deformations to the 3D scene geometry, can be used for synthesizing interactive panorama maps to combine detailed views close to the camera (focus) with abstract views in the background (context). This approach reduces occlusions, increases the usage the available screen space, and reduces the overload of image contents. • The object-based and image-based rendering techniques for highlighting objects and focus areas inside and outside the view frustum facilitate preattentive perception. The concepts and implementations of interactive image synthesis for focus+context visualization and their selected applications enable a more effective communication of spatial information, and provide building blocks for design and development of new applications and systems in the field of 3D geovirtual environments.},
  language  = {en}
}
@article{LambersWeber2020,
  author    = {Lambers, Leen and Weber, Jens},
  title     = {Preface to the special issue on the 11th International Conference on Graph Transformation},
  series = {Journal of Logical and Algebraic Methods in Programming},
  volume    = {112},
  journal   = {Journal of Logical and Algebraic Methods in Programming},
  publisher = {Elsevier},
  address   = {Amsterdam},
  issn      = {2352-2208},
  doi       = {10.1016/j.jlamp.2020.100525},
  pages     = {2},
  year      = {2020},
  abstract  = {This special issue contains extended versions of four selected papers from the 11th International Conference on Graph Transformation (ICGT 2018). The articles cover a tool for computing core graphs via SAT/SMT solvers (graph language definition), graph transformation through graph surfing in reaction systems (a new graph transformation formalism), the essence and initiality of conflicts in M-adhesive transformation systems, and a calculus of concurrent graph-rewriting processes (theory on conflicts and parallel independence).},
  language  = {en}
}
@book{LangeBoehmNaumann2010,
  author    = {Lange, Dustin and B{\"o}hm, Christoph and Naumann, Felix},
  title     = {Extracting structured information from Wikipedia articles to populate infoboxes},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-081-6},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-45714},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {27},
  year      = {2010},
  abstract  = {Roughly every third Wikipedia article contains an infobox - a table that displays important facts about the subject in attribute-value form. The schema of an infobox, i.e., the attributes that can be expressed for a concept, is defined by an infobox template. Often, authors do not specify all template attributes, resulting in incomplete infoboxes. With iPopulator, we introduce a system that automatically populates infoboxes of Wikipedia articles by extracting attribute values from the article's text. In contrast to prior work, iPopulator detects and exploits the structure of attribute values for independently extracting value parts. We have tested iPopulator on the entire set of infobox templates and provide a detailed analysis of its effectiveness. For instance, we achieve an average extraction precision of 91\% for 1,727 distinct infobox template attributes.},
  language  = {en}
}