@phdthesis{Holz2013,
author = {Holz, Christian},
title = {3D from 2D touch},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-67796},
school = {Universit{\"a}t Potsdam},
year = {2013},
abstract = {While interaction with computers used to be dominated by mice and keyboards, new types of sensors now allow users to interact through touch, speech, or using their whole body in 3D space. These new interaction modalities are often referred to as "natural user interfaces" or "NUIs." While 2D NUIs have experienced major success on billions of mobile touch devices sold, 3D NUI systems have so far been unable to deliver a mobile form factor, mainly due to their use of cameras. The fact that cameras require a certain distance from the capture volume has prevented 3D NUI systems from reaching the flat form factor mobile users expect. In this dissertation, we address this issue by sensing 3D input using flat 2D sensors. The systems we present observe the input from 3D objects as 2D imprints upon physical contact. By sampling these imprints at very high resolutions, we obtain the objects' textures. In some cases, a texture uniquely identifies a biometric feature, such as the user's fingerprint. In other cases, an imprint stems from the user's clothing, such as when walking on multitouch floors. By analyzing from which part of the 3D object the 2D imprint results, we reconstruct the object's pose in 3D space. While our main contribution is a general approach to sensing 3D input on 2D sensors upon physical contact, we also demonstrate three applications of our approach. (1) We present high-accuracy touch devices that allow users to reliably touch targets that are a third of the size of those on current touch devices. We show that different users and 3D finger poses systematically affect touch sensing, which current devices perceive as random input noise. We introduce a model for touch that compensates for this systematic effect by deriving the 3D finger pose and the user's identity from each touch imprint. We then investigate this systematic effect in detail and explore how users conceptually touch targets. Our findings indicate that users aim by aligning visual features of their fingers with the target. We present a visual model for touch input that eliminates virtually all systematic effects on touch accuracy. (2) From each touch, we identify users biometrically by analyzing their fingerprints. Our prototype Fiberio integrates fingerprint scanning and a display into the same flat surface, solving a long-standing problem in human-computer interaction: secure authentication on touchscreens. Sensing 3D input and authenticating users upon touch allows Fiberio to implement a variety of applications that traditionally require the bulky setups of current 3D NUI systems. (3) To demonstrate the versatility of 3D reconstruction on larger touch surfaces, we present a high-resolution pressure-sensitive floor that resolves the texture of objects upon touch. Using the same principles as before, our system GravitySpace analyzes all imprints and identifies users based on their shoe soles, detects furniture, and enables accurate touch input using feet. By classifying all imprints, GravitySpace detects the users' body parts that are in contact with the floor and then reconstructs their 3D body poses using inverse kinematics. GravitySpace thus enables a range of applications for future 3D NUI systems based on a flat sensor, such as smart rooms in future homes. We conclude this dissertation by projecting into the future of mobile devices. Focusing on the mobility aspect of our work, we explore how NUI devices may one day augment users directly in the form of implanted devices.},
language = {en}
}
@phdthesis{Awad2010,
author = {Awad, Ahmed Mahmoud Hany Aly},
title = {A compliance management framework for business process models},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-49222},
school = {Universit{\"a}t Potsdam},
year = {2010},
abstract = {Companies develop process models to explicitly describe their business operations. In the same time, business operations, business processes, must adhere to various types of compliance requirements. Regulations, e.g., Sarbanes Oxley Act of 2002, internal policies, best practices are just a few sources of compliance requirements. In some cases, non-adherence to compliance requirements makes the organization subject to legal punishment. In other cases, non-adherence to compliance leads to loss of competitive advantage and thus loss of market share. Unlike the classical domain-independent behavioral correctness of business processes, compliance requirements are domain-specific. Moreover, compliance requirements change over time. New requirements might appear due to change in laws and adoption of new policies. Compliance requirements are offered or enforced by different entities that have different objectives behind these requirements. Finally, compliance requirements might affect different aspects of business processes, e.g., control flow and data flow. As a result, it is infeasible to hard-code compliance checks in tools. Rather, a repeatable process of modeling compliance rules and checking them against business processes automatically is needed. This thesis provides a formal approach to support process design-time compliance checking. Using visual patterns, it is possible to model compliance requirements concerning control flow, data flow and conditional flow rules. Each pattern is mapped into a temporal logic formula. The thesis addresses the problem of consistency checking among various compliance requirements, as they might stem from divergent sources. Also, the thesis contributes to automatically check compliance requirements against process models using model checking. We show that extra domain knowledge, other than expressed in compliance rules, is needed to reach correct decisions. In case of violations, we are able to provide a useful feedback to the user. The feedback is in the form of parts of the process model whose execution causes the violation. In some cases, our approach is capable of providing automated remedy of the violation.},
language = {en}
}
@article{KaitouaRablMarkl2020,
author = {Kaitoua, Abdulrahman and Rabl, Tilmann and Markl, Volker},
title = {A distributed data exchange engine for polystores},
series = {Information technology : methods and applications of informatics and information technology},
volume = {62},
journal = {Information technology : methods and applications of informatics and information technology},
number = {3-4},
publisher = {De Gruyter},
address = {Berlin},
issn = {1611-2776},
doi = {10.1515/itit-2019-0037},
pages = {145 -- 156},
year = {2020},
abstract = {There is an increasing interest in fusing data from heterogeneous sources. Combining data sources increases the utility of existing datasets, generating new information and creating services of higher quality. A central issue in working with heterogeneous sources is data migration: In order to share and process data in different engines, resource intensive and complex movements and transformations between computing engines, services, and stores are necessary. Muses is a distributed, high-performance data migration engine that is able to interconnect distributed data stores by forwarding, transforming, repartitioning, or broadcasting data among distributed engines' instances in a resource-, cost-, and performance-adaptive manner. As such, it performs seamless information sharing across all participating resources in a standard, modular manner. We show an overall improvement of 30 \% for pipelining jobs across multiple engines, even when we count the overhead of Muses in the execution time. This performance gain implies that Muses can be used to optimise large pipelines that leverage multiple engines.},
language = {en}
}
@article{SchneiderLambersOrejas2021,
author = {Schneider, Sven and Lambers, Leen and Orejas, Fernando},
title = {A logic-based incremental approach to graph repair featuring delta preservation},
series = {International journal on software tools for technology transfer : STTT},
volume = {23},
journal = {International journal on software tools for technology transfer : STTT},
number = {3},
publisher = {Springer},
address = {Berlin ; Heidelberg},
issn = {1433-2779},
doi = {10.1007/s10009-020-00584-x},
pages = {369 -- 410},
year = {2021},
abstract = {We introduce a logic-based incremental approach to graph repair, generating a sound and complete (upon termination) overview of least-changing graph repairs from which a user may select a graph repair based on non-formalized further requirements. This incremental approach features delta preservation as it allows to restrict the generation of graph repairs to delta-preserving graph repairs, which do not revert the additions and deletions of the most recent consistency-violating graph update. We specify consistency of graphs using the logic of nested graph conditions, which is equivalent to first-order logic on graphs. Technically, the incremental approach encodes if and how the graph under repair satisfies a graph condition using the novel data structure of satisfaction trees, which are adapted incrementally according to the graph updates applied. In addition to the incremental approach, we also present two state-based graph repair algorithms, which restore consistency of a graph independent of the most recent graph update and which generate additional graph repairs using a global perspective on the graph under repair. We evaluate the developed algorithms using our prototypical implementation in the tool AutoGraph and illustrate our incremental approach using a case study from the graph database domain.},
language = {en}
}
@inproceedings{GruenerMuehleGayvoronskayaetal.2019,
author = {Gr{\"u}ner, Andreas and M{\"u}hle, Alexander and Gayvoronskaya, Tatiana and Meinel, Christoph},
title = {A quantifiable trustmModel for Blockchain-based identity management},
series = {IEEE 2018 International Congress on Cybermatics / 2018 IEEE Conferences on Internet of Things, Green Computing and Communications, cyber, physical and Social Computing, Smart Data, Blockchain, Computer and Information Technology},
booktitle = {IEEE 2018 International Congress on Cybermatics / 2018 IEEE Conferences on Internet of Things, Green Computing and Communications, cyber, physical and Social Computing, Smart Data, Blockchain, Computer and Information Technology},
publisher = {IEEE},
address = {New York},
isbn = {978-1-5386-7975-3},
doi = {10.1109/Cybermatics_2018.2018.00250},
pages = {1475 -- 1482},
year = {2019},
language = {en}
}
@book{PolyvyanyyKuropka2007,
author = {Polyvyanyy, Artem and Kuropka, Dominik},
title = {A quantitative evaluation of the enhanced topic-based vector space model},
isbn = {978-3-939469-95-7},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-33816},
publisher = {Universit{\"a}t Potsdam},
year = {2007},
abstract = {This contribution presents a quantitative evaluation procedure for Information Retrieval models and the results of this procedure applied on the enhanced Topic-based Vector Space Model (eTVSM). Since the eTVSM is an ontology-based model, its effectiveness heavily depends on the quality of the underlaying ontology. Therefore the model has been tested with different ontologies to evaluate the impact of those ontologies on the effectiveness of the eTVSM. On the highest level of abstraction, the following results have been observed during our evaluation: First, the theoretically deduced statement that the eTVSM has a similar effecitivity like the classic Vector Space Model if a trivial ontology (every term is a concept and it is independet of any other concepts) is used has been approved. Second, we were able to show that the effectiveness of the eTVSM raises if an ontology is used which is only able to resolve synonyms. We were able to derive such kind of ontology automatically from the WordNet ontology. Third, we observed that more powerful ontologies automatically derived from the WordNet, dramatically dropped the effectiveness of the eTVSM model even clearly below the effectiveness level of the Vector Space Model. Fourth, we were able to show that a manually created and optimized ontology is able to raise the effectiveness of the eTVSM to a level which is clearly above the best effectiveness levels we have found in the literature for the Latent Semantic Index model with compareable document sets.},
language = {en}
}
@article{DoerrKrejca2021,
author = {Doerr, Benjamin and Krejca, Martin Stefan},
title = {A simplified run time analysis of the univariate marginal distribution algorithm on LeadingOnes},
series = {Theoretical computer science},
volume = {851},
journal = {Theoretical computer science},
publisher = {Elsevier},
address = {Amsterdam},
issn = {0304-3975},
doi = {10.1016/j.tcs.2020.11.028},
pages = {121 -- 128},
year = {2021},
abstract = {With elementary means, we prove a stronger run time guarantee for the univariate marginal distribution algorithm (UMDA) optimizing the LEADINGONES benchmark function in the desirable regime with low genetic drift. If the population size is at least quasilinear, then, with high probability, the UMDA samples the optimum in a number of iterations that is linear in the problem size divided by the logarithm of the UMDA's selection rate. This improves over the previous guarantee, obtained by Dang and Lehre (2015) via the deep level-based population method, both in terms of the run time and by demonstrating further run time gains from small selection rates. Under similar assumptions, we prove a lower bound that matches our upper bound up to constant factors.},
language = {en}
}
@book{HuCordelMeinel2006,
author = {Hu, Ji and Cordel, Dirk and Meinel, Christoph},
title = {A virtual machine architecture for creating IT-security laboratories},
publisher = {Universit{\"a}tsverlag Potsdam},
address = {Potsdam},
isbn = {978-3-939469-13-1},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-33077},
publisher = {Universit{\"a}t Potsdam},
pages = {50},
year = {2006},
abstract = {E-learning is a flexible and personalized alternative to traditional education. Nonetheless, existing e-learning systems for IT security education have difficulties in delivering hands-on experience because of the lack of proximity. Laboratory environments and practical exercises are indispensable instruction tools to IT security education, but security education in con-ventional computer laboratories poses the problem of immobility as well as high creation and maintenance costs. Hence, there is a need to effectively transform security laboratories and practical exercises into e-learning forms. This report introduces the Tele-Lab IT-Security architecture that allows students not only to learn IT security principles, but also to gain hands-on security experience by exercises in an online laboratory environment. In this architecture, virtual machines are used to provide safe user work environments instead of real computers. Thus, traditional laboratory environments can be cloned onto the Internet by software, which increases accessibilities to laboratory resources and greatly reduces investment and maintenance costs. Under the Tele-Lab IT-Security framework, a set of technical solutions is also proposed to provide effective functionalities, reliability, security, and performance. The virtual machines with appropriate resource allocation, software installation, and system configurations are used to build lightweight security laboratories on a hosting computer. Reliability and availability of laboratory platforms are covered by the virtual machine management framework. This management framework provides necessary monitoring and administration services to detect and recover critical failures of virtual machines at run time. Considering the risk that virtual machines can be misused for compromising production networks, we present security management solutions to prevent misuse of laboratory resources by security isolation at the system and network levels. This work is an attempt to bridge the gap between e-learning/tele-teaching and practical IT security education. It is not to substitute conventional teaching in laboratories but to add practical features to e-learning. This report demonstrates the possibility to implement hands-on security laboratories on the Internet reliably, securely, and economically.},
language = {en}
}
@book{SmirnovWeidlichMendlingetal.2009,
author = {Smirnov, Sergey and Weidlich, Matthias and Mendling, Jan and Weske, Mathias},
title = {Action patterns in business process models},
publisher = {Universit{\"a}tsverlag Potsdam},
address = {Potsdam},
isbn = {978-3-86956-009-0},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-33586},
publisher = {Universit{\"a}t Potsdam},
pages = {19},
year = {2009},
abstract = {Business process management experiences a large uptake by the industry, and process models play an important role in the analysis and improvement of processes. While an increasing number of staff becomes involved in actual modeling practice, it is crucial to assure model quality and homogeneity along with providing suitable aids for creating models. In this paper we consider the problem of offering recommendations to the user during the act of modeling. Our key contribution is a concept for defining and identifying so-called action patterns - chunks of actions often appearing together in business processes. In particular, we specify action patterns and demonstrate how they can be identified from existing process model repositories using association rule mining techniques. Action patterns can then be used to suggest additional actions for a process model. Our approach is challenged by applying it to the collection of process models from the SAP Reference Model.},
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}
}
@misc{HesseMatthiesSinzigetal.2019,
author = {Hesse, G{\"u}nter and Matthies, Christoph and Sinzig, Werner and Uflacker, Matthias},
title = {Adding Value by Combining Business and Sensor Data},
series = {Database Systems for Advanced Applications},
volume = {11448},
journal = {Database Systems for Advanced Applications},
publisher = {Springer},
address = {Cham},
isbn = {978-3-030-18590-9},
issn = {0302-9743},
doi = {10.1007/978-3-030-18590-9_80},
pages = {528 -- 532},
year = {2019},
abstract = {Industry 4.0 and the Internet of Things are recent developments that have lead to the creation of new kinds of manufacturing data. Linking this new kind of sensor data to traditional business information is crucial for enterprises to take advantage of the data's full potential. In this paper, we present a demo which allows experiencing this data integration, both vertically between technical and business contexts and horizontally along the value chain. The tool simulates a manufacturing company, continuously producing both business and sensor data, and supports issuing ad-hoc queries that answer specific questions related to the business. In order to adapt to different environments, users can configure sensor characteristics to their needs.},
language = {en}
}
@book{AbedjanNaumann2011,
author = {Abedjan, Ziawasch and Naumann, Felix},
title = {Advancing the discovery of unique column combinations},
publisher = {Universit{\"a}tsverlag Potsdam},
address = {Potsdam},
isbn = {978-3-86956-148-6},
issn = {1613-5652},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-53564},
publisher = {Universit{\"a}t Potsdam},
pages = {25},
year = {2011},
abstract = {Unique column combinations of a relational database table are sets of columns that contain only unique values. Discovering such combinations is a fundamental research problem and has many different data management and knowledge discovery applications. Existing discovery algorithms are either brute force or have a high memory load and can thus be applied only to small datasets or samples. In this paper, the wellknown GORDIAN algorithm and "Apriori-based" algorithms are compared and analyzed for further optimization. We greatly improve the Apriori algorithms through efficient candidate generation and statistics-based pruning methods. A hybrid solution HCAGORDIAN combines the advantages of GORDIAN and our new algorithm HCA, and it significantly outperforms all previous work in many situations.},
language = {en}
}
@book{KleineHirschfeldBracha2011,
author = {Kleine, Matthias and Hirschfeld, Robert and Bracha, Gilad},
title = {An abstraction for version control systems},
series = {Technische Berichte des Hasso-Plattner-Instituts f{\"u}r Softwaresystemtechnik an der Universit{\"a}t Potsdam},
journal = {Technische Berichte des Hasso-Plattner-Instituts f{\"u}r Softwaresystemtechnik an der Universit{\"a}t Potsdam},
number = {54},
publisher = {Universit{\"a}tsverlag Potsdam},
address = {Potsdam},
isbn = {978-3-86956-158-5},
issn = {1613-5652},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-55629},
publisher = {Universit{\"a}t Potsdam},
pages = {77},
year = {2011},
abstract = {Versionsverwaltungssysteme (VCS) erm{\"o}glichen es Entwicklern, {\"A}nderungen an Softwareartifakten zu verwalten. VCS werden mit Hilfe einer Vielzahl verschiedener Werkzeuge bedient, wie z.\,B. graphische Front-ends oder Kommandozeilenwerkzeuge. Es ist w{\"u}nschenswert mit einzelnen solcher Werkzeuge unterschiedliche VCS bedienen zu k{\"o}nnen. Bislang hat sich jedoch keine Abstraktion f{\"u}r Versionsverwaltungssysteme durchgesetzt, mit deren Hilfe solche Werkzeuge erstellt werden k{\"o}nnen. Stattdessen implementieren Werkzeuge zur Interaktion mit mehreren VCS ad-hoc L{\"o}sungen. Diese Masterarbeit stellt Pur vor, eine Abstraktion {\"u}ber Versionsverwaltungskonzepte. Mit Hilfe von Pur k{\"o}nnen Anwendungsprogramme entwickelt werden, die mit mehreren Versionsverwaltungssystemen interagieren k{\"o}nnen. Im Rahmen dieser Arbeit wird eine Implementierung dieser Abstraktion bereitgestellt und mit Hilfe eines Anwendungsprogramms validiert.},
language = {en}
}
@book{LinckelsMeinel2005,
author = {Linckels, Serge and Meinel, Christoph},
title = {An e-librarian service : natural language interface for an efficient semantic search within multimedia resources},
publisher = {Universit{\"a}tsverlag Potsdam},
address = {Potsdam},
isbn = {978-3-937786-89-6},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-33088},
publisher = {Universit{\"a}t Potsdam},
pages = {40},
year = {2005},
abstract = {1 Introduction 1.1 Project formulation 1.2 Our contribution 2 Pedagogical Aspect 4 2.1 Modern teaching 2.2 Our Contribution 2.2.1 Autonomous and exploratory learning 2.2.2 Human machine interaction 2.2.3 Short multimedia clips 3 Ontology Aspect 3.1 Ontology driven expert systems 3.2 Our contribution 3.2.1 Ontology language 3.2.2 Concept Taxonomy 3.2.3 Knowledge base annotation 3.2.4 Description Logics 4 Natural language approach 4.1 Natural language processing in computer science 4.2 Our contribution 4.2.1 Explored strategies 4.2.2 Word equivalence 4.2.3 Semantic interpretation 4.2.4 Various problems 5 Information Retrieval Aspect 5.1 Modern information retrieval 5.2 Our contribution 5.2.1 Semantic query generation 5.2.2 Semantic relatedness 6 Implementation 6.1 Prototypes 6.2 Semantic layer architecture 6.3 Development 7 Experiments 7.1 Description of the experiments 7.2 General characteristics of the three sessions, instructions and procedure 7.3 First Session 7.4 Second Session 7.5 Third Session 7.6 Discussion and conclusion 8 Conclusion and future work 8.1 Conclusion 8.2 Open questions A Description Logics B Probabilistic context-free grammars},
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}
}
@inproceedings{FanMasuharaAotanietal.2010,
author = {Fan, Yang and Masuhara, Hidehiko and Aotani, Tomoyuki and Nielson, Flemming and Nielson, Hanne Riis},
title = {AspectKE*: Security aspects with program analysis for distributed systems},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-41369},
year = {2010},
abstract = {Enforcing security policies to distributed systems is difficult, in particular, when a system contains untrusted components. We designed AspectKE*, a distributed AOP language based on a tuple space, to tackle this issue. In AspectKE*, aspects can enforce access control policies that depend on future behavior of running processes. One of the key language features is the predicates and functions that extract results of static program analysis, which are useful for defining security aspects that have to know about future behavior of a program. AspectKE* also provides a novel variable binding mechanism for pointcuts, so that pointcuts can uniformly specify join points based on both static and dynamic information about the program. Our implementation strategy performs fundamental static analysis at load-time, so as to retain runtime overheads minimal. We implemented a compiler for AspectKE*, and demonstrate usefulness of AspectKE* through a security aspect for a distributed chat system.},
language = {en}
}
@article{GruenerMuehleMeinel2021,
author = {Gr{\"u}ner, Andreas and M{\"u}hle, Alexander and Meinel, Christoph},
title = {ATIB},
series = {IEEE access : practical research, open solutions / Institute of Electrical and Electronics Engineers},
volume = {9},
journal = {IEEE access : practical research, open solutions / Institute of Electrical and Electronics Engineers},
publisher = {Institute of Electrical and Electronics Engineers},
address = {New York, NY},
issn = {2169-3536},
doi = {10.1109/ACCESS.2021.3116095},
pages = {138553 -- 138570},
year = {2021},
abstract = {Identity management is a principle component of securing online services. In the advancement of traditional identity management patterns, the identity provider remained a Trusted Third Party (TTP). The service provider and the user need to trust a particular identity provider for correct attributes amongst other demands. This paradigm changed with the invention of blockchain-based Self-Sovereign Identity (SSI) solutions that primarily focus on the users. SSI reduces the functional scope of the identity provider to an attribute provider while enabling attribute aggregation. Besides that, the development of new protocols, disregarding established protocols and a significantly fragmented landscape of SSI solutions pose considerable challenges for an adoption by service providers. We propose an Attribute Trust-enhancing Identity Broker (ATIB) to leverage the potential of SSI for trust-enhancing attribute aggregation. Furthermore, ATIB abstracts from a dedicated SSI solution and offers standard protocols. Therefore, it facilitates the adoption by service providers. Despite the brokered integration approach, we show that ATIB provides a high security posture. Additionally, ATIB does not compromise the ten foundational SSI principles for the users.},
language = {en}
}
@phdthesis{Wist2011,
author = {Wist, Dominic},
title = {Attacking complexity in logic synthesis of asynchronous circuits},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-59706},
school = {Universit{\"a}t Potsdam},
year = {2011},
abstract = {Most of the microelectronic circuits fabricated today are synchronous, i.e. they are driven by one or several clock signals. Synchronous circuit design faces several fundamental challenges such as high-speed clock distribution, integration of multiple cores operating at different clock rates, reduction of power consumption and dealing with voltage, temperature, manufacturing and runtime variations. Asynchronous or clockless design plays a key role in alleviating these challenges, however the design and test of asynchronous circuits is much more difficult in comparison to their synchronous counterparts. A driving force for a widespread use of asynchronous technology is the availability of mature EDA (Electronic Design Automation) tools which provide an entire automated design flow starting from an HDL (Hardware Description Language) specification yielding the final circuit layout. Even though there was much progress in developing such EDA tools for asynchronous circuit design during the last two decades, the maturity level as well as the acceptance of them is still not comparable with tools for synchronous circuit design. In particular, logic synthesis (which implies the application of Boolean minimisation techniques) for the entire system's control path can significantly improve the efficiency of the resulting asynchronous implementation, e.g. in terms of chip area and performance. However, logic synthesis, in particular for asynchronous circuits, suffers from complexity problems. Signal Transitions Graphs (STGs) are labelled Petri nets which are a widely used to specify the interface behaviour of speed independent (SI) circuits - a robust subclass of asynchronous circuits. STG decomposition is a promising approach to tackle complexity problems like state space explosion in logic synthesis of SI circuits. The (structural) decomposition of STGs is guided by a partition of the output signals and generates a usually much smaller component STG for each partition member, i.e. a component STG with a much smaller state space than the initial specification. However, decomposition can result in component STGs that in isolation have so-called irreducible CSC conflicts (i.e. these components are not SI synthesisable anymore) even if the specification has none of them. A new approach is presented to avoid such conflicts by introducing internal communication between the components. So far, STG decompositions are guided by the finest output partitions, i.e. one output per component. However, this might not yield optimal circuit implementations. Efficient heuristics are presented to determine coarser partitions leading to improved circuits in terms of chip area. For the new algorithms correctness proofs are given and their implementations are incorporated into the decomposition tool DESIJ. The presented techniques are successfully applied to some benchmarks - including 'real-life' specifications arising in the context of control resynthesis - which delivered promising results.},
language = {en}
}
@book{DyckGieseLambers2017,
author = {Dyck, Johannes and Giese, Holger and Lambers, Leen},
title = {Automatic verification of behavior preservation at the transformation level for relational model transformation},
number = {112},
publisher = {Universit{\"a}tsverlag Potsdam},
address = {Potsdam},
isbn = {978-3-86956-391-6},
issn = {1613-5652},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-100279},
publisher = {Universit{\"a}t Potsdam},
pages = {viii, 112},
year = {2017},
abstract = {The correctness of model transformations is a crucial element for model-driven engineering of high quality software. In particular, behavior preservation is the most important correctness property avoiding the introduction of semantic errors during the model-driven engineering process. Behavior preservation verification techniques either show that specific properties are preserved, or more generally and complex, they show some kind of behavioral equivalence or refinement between source and target model of the transformation. Both kinds of behavior preservation verification goals have been presented with automatic tool support for the instance level, i.e. for a given source and target model specified by the model transformation. However, up until now there is no automatic verification approach available at the transformation level, i.e. for all source and target models specified by the model transformation. In this report, we extend our results presented in [27] and outline a new sophisticated approach for the automatic verification of behavior preservation captured by bisimulation resp. simulation for model transformations specified by triple graph grammars and semantic definitions given by graph transformation rules. In particular, we show that the behavior preservation problem can be reduced to invariant checking for graph transformation and that the resulting checking problem can be addressed by our own invariant checker even for a complex example where a sequence chart is transformed into communicating automata. We further discuss today's limitations of invariant checking for graph transformation and motivate further lines of future work in this direction.},
language = {en}
}
@book{FelgentreffBorningHirschfeld2013,
author = {Felgentreff, Tim and Borning, Alan and Hirschfeld, Robert},
title = {Babelsberg : specifying and solving constraints on object behavior},
publisher = {Universit{\"a}tsverlag Potsdam},
address = {Potsdam},
isbn = {978-3-86956-265-0},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-67296},
publisher = {Universit{\"a}t Potsdam},
pages = {53},
year = {2013},
abstract = {Constraints allow developers to specify desired properties of systems in a number of domains, and have those properties be maintained automatically. This results in compact, declarative code, avoiding scattered code to check and imperatively re-satisfy invariants. Despite these advantages, constraint programming is not yet widespread, with standard imperative programming still the norm. There is a long history of research on integrating constraint programming with the imperative paradigm. However, this integration typically does not unify the constructs for encapsulation and abstraction from both paradigms. This impedes re-use of modules, as client code written in one paradigm can only use modules written to support that paradigm. Modules require redundant definitions if they are to be used in both paradigms. We present a language - Babelsberg - that unifies the constructs for en- capsulation and abstraction by using only object-oriented method definitions for both declarative and imperative code. Our prototype - Babelsberg/R - is an extension to Ruby, and continues to support Ruby's object-oriented se- mantics. It allows programmers to add constraints to existing Ruby programs in incremental steps by placing them on the results of normal object-oriented message sends. It is implemented by modifying a state-of-the-art Ruby virtual machine. The performance of standard object-oriented code without con- straints is only modestly impacted, with typically less than 10\% overhead compared with the unmodified virtual machine. Furthermore, our architec- ture for adding multiple constraint solvers allows Babelsberg to deal with constraints in a variety of domains. We argue that our approach provides a useful step toward making con- straint solving a generic tool for object-oriented programmers. We also provide example applications, written in our Ruby-based implementation, which use constraints in a variety of application domains, including interactive graphics, circuit simulations, data streaming with both hard and soft constraints on performance, and configuration file Management.},
language = {en}
}
@book{FelgentreffHirschfeldMillsteinetal.2015,
author = {Felgentreff, Tim and Hirschfeld, Robert and Millstein, Todd and Borning, Alan},
title = {Babelsberg/RML},
number = {103},
publisher = {Universit{\"a}tsverlag Potsdam},
address = {Potsdam},
isbn = {978-3-86956-348-0},
issn = {1613-5652},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-83826},
publisher = {Universit{\"a}t Potsdam},
pages = {68},
year = {2015},
abstract = {New programming language designs are often evaluated on concrete implementations. However, in order to draw conclusions about the language design from the evaluation of concrete programming languages, these implementations need to be verified against the formalism of the design. To that end, we also have to ensure that the design actually meets its stated goals. A useful tool for the latter has been to create an executable semantics from a formalism that can execute a test suite of examples. However, this mechanism so far did not allow to verify an implementation against the design. Babelsberg is a new design for a family of object-constraint languages. Recently, we have developed a formal semantics to clarify some issues in the design of those languages. Supplementing this work, we report here on how this formalism is turned into an executable operational semantics using the RML system. Furthermore, we show how we extended the executable semantics to create a framework that can generate test suites for the concrete Babelsberg implementations that provide traceability from the design to the language. Finally, we discuss how these test suites helped us find and correct mistakes in the Babelsberg implementation for JavaScript.},
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}
}
@phdthesis{Weidlich2011,
author = {Weidlich, Matthias},
title = {Behavioural profiles : a relational approach to behaviour consistency},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-55590},
school = {Universit{\"a}t Potsdam},
year = {2011},
abstract = {Business Process Management (BPM) emerged as a means to control, analyse, and optimise business operations. Conceptual models are of central importance for BPM. Most prominently, process models define the behaviour that is performed to achieve a business value. In essence, a process model is a mapping of properties of the original business process to the model, created for a purpose. Different modelling purposes, therefore, result in different models of a business process. Against this background, the misalignment of process models often observed in the field of BPM is no surprise. Even if the same business scenario is considered, models created for strategic decision making differ in content significantly from models created for process automation. Despite their differences, process models that refer to the same business process should be consistent, i.e., free of contradictions. Apparently, there is a trade-off between strictness of a notion of consistency and appropriateness of process models serving different purposes. Existing work on consistency analysis builds upon behaviour equivalences and hierarchical refinements between process models. Hence, these approaches are computationally hard and do not offer the flexibility to gradually relax consistency requirements towards a certain setting. This thesis presents a framework for the analysis of behaviour consistency that takes a fundamentally different approach. As a first step, an alignment between corresponding elements of related process models is constructed. Then, this thesis conducts behavioural analysis grounded on a relational abstraction of the behaviour of a process model, its behavioural profile. Different variants of these profiles are proposed, along with efficient computation techniques for a broad class of process models. Using behavioural profiles, consistency of an alignment between process models is judged by different notions and measures. The consistency measures are also adjusted to assess conformance of process logs that capture the observed execution of a process. Further, this thesis proposes various complementary techniques to support consistency management. It elaborates on how to implement consistent change propagation between process models, addresses the exploration of behavioural commonalities and differences, and proposes a model synthesis for behavioural profiles.},
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}
}
@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}
}
@phdthesis{EidSabbagh2015,
author = {Eid-Sabbagh, Rami-Habib},
title = {Business process architectures},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-79719},
school = {Universit{\"a}t Potsdam},
pages = {xvii, 256},
year = {2015},
abstract = {Business Process Management has become an integral part of modern organizations in the private and public sector for improving their operations. In the course of Business Process Management efforts, companies and organizations assemble large process model repositories with many hundreds and thousands of business process models bearing a large amount of information. With the advent of large business process model collections, new challenges arise as structuring and managing a large amount of process models, their maintenance, and their quality assurance. This is covered by business process architectures that have been introduced for organizing and structuring business process model collections. A variety of business process architecture approaches have been proposed that align business processes along aspects of interest, e. g., goals, functions, or objects. They provide a high level categorization of single processes ignoring their interdependencies, thus hiding valuable information. The production of goods or the delivery of services are often realized by a complex system of interdependent business processes. Hence, taking a holistic view at business processes interdependencies becomes a major necessity to organize, analyze, and assess the impact of their re-/design. Visualizing business processes interdependencies reveals hidden and implicit information from a process model collection. In this thesis, we present a novel Business Process Architecture approach for representing and analyzing business process interdependencies on an abstract level. We propose a formal definition of our Business Process Architecture approach, design correctness criteria, and develop analysis techniques for assessing their quality. We describe a methodology for applying our Business Process Architecture approach top-down and bottom-up. This includes techniques for Business Process Architecture extraction from, and decomposition to process models while considering consistency issues between business process architecture and process model level. Using our extraction algorithm, we present a novel technique to identify and visualize data interdependencies in Business Process Data Architectures. Our Business Process Architecture approach provides business process experts,managers, and other users of a process model collection with an overview that allows reasoning about a large set of process models, understanding, and analyzing their interdependencies in a facilitated way. In this regard we evaluated our Business Process Architecture approach in an experiment and provide implementations of selected techniques.},
language = {en}
}
@book{EidSabbaghHeweltWeske2013,
author = {Eid-Sabbagh, Rami-Habib and Hewelt, Marcin and Weske, Mathias},
title = {Business process architectures with multiplicities : transformation and correctness},
publisher = {Universit{\"a}tsverlag Potsdam},
address = {Potsdam},
isbn = {978-3-86956-257-5},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-66780},
publisher = {Universit{\"a}t Potsdam},
pages = {18},
year = {2013},
abstract = {Business processes are instrumental to manage work in organisations. To study the interdependencies between business processes, Business Process Architectures have been introduced. These express trigger and message ow relations between business processes. When we investigate real world Business Process Architectures, we find complex interdependencies, involving multiple process instances. These aspects have not been studied in detail so far, especially concerning correctness properties. In this paper, we propose a modular transformation of BPAs to open nets for the analysis of behavior involving multiple business processes with multiplicities. For this purpose we introduce intermediary nets to portray semantics of multiplicity specifications. We evaluate our approach on a use case from the public sector.},
language = {en}
}
@phdthesis{Smirnov2011,
author = {Smirnov, Sergey},
title = {Business process model abstraction},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-60258},
school = {Universit{\"a}t Potsdam},
year = {2011},
abstract = {Business process models are used within a range of organizational initiatives, where every stakeholder has a unique perspective on a process and demands the respective model. As a consequence, multiple process models capturing the very same business process coexist. Keeping such models in sync is a challenge within an ever changing business environment: once a process is changed, all its models have to be updated. Due to a large number of models and their complex relations, model maintenance becomes error-prone and expensive. Against this background, business process model abstraction emerged as an operation reducing the number of stored process models and facilitating model management. Business process model abstraction is an operation preserving essential process properties and leaving out insignificant details in order to retain information relevant for a particular purpose. Process model abstraction has been addressed by several researchers. The focus of their studies has been on particular use cases and model transformations supporting these use cases. This thesis systematically approaches the problem of business process model abstraction shaping the outcome into a framework. We investigate the current industry demand in abstraction summarizing it in a catalog of business process model abstraction use cases. The thesis focuses on one prominent use case where the user demands a model with coarse-grained activities and overall process ordering constraints. We develop model transformations that support this use case starting with the transformations based on process model structure analysis. Further, abstraction methods considering the semantics of process model elements are investigated. First, we suggest how semantically related activities can be discovered in process models-a barely researched challenge. The thesis validates the designed abstraction methods against sets of industrial process models and discusses the method implementation aspects. Second, we develop a novel model transformation, which combined with the related activity discovery allows flexible non-hierarchical abstraction. In this way this thesis advocates novel model transformations that facilitate business process model management and provides the foundations for innovative tool support.},
language = {en}
}
@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}
}
@book{SchwalbKruegerPlattner2013,
author = {Schwalb, David and Kr{\"u}ger, Jens and Plattner, Hasso},
title = {Cache conscious column organization in in-memory column stores},
publisher = {Universit{\"a}tsverlag Potsdam},
address = {Potsdam},
isbn = {978-3-86956-228-5},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-63890},
publisher = {Universit{\"a}t Potsdam},
pages = {v, 84},
year = {2013},
abstract = {Cost models are an essential part of database systems, as they are the basis of query performance optimization. Based on predictions made by cost models, the fastest query execution plan can be chosen and executed or algorithms can be tuned and optimised. In-memory databases shifts the focus from disk to main memory accesses and CPU costs, compared to disk based systems where input and output costs dominate the overall costs and other processing costs are often neglected. However, modelling memory accesses is fundamentally different and common models do not apply anymore. This work presents a detailed parameter evaluation for the plan operators scan with equality selection, scan with range selection, positional lookup and insert in in-memory column stores. Based on this evaluation, a cost model based on cache misses for estimating the runtime of the considered plan operators using different data structures is developed. Considered are uncompressed columns, bit compressed and dictionary encoded columns with sorted and unsorted dictionaries. Furthermore, tree indices on the columns and dictionaries are discussed. Finally, partitioned columns consisting of one partition with a sorted and one with an unsorted dictionary are investigated. New values are inserted in the unsorted dictionary partition and moved periodically by a merge process to the sorted partition. An efficient attribute merge algorithm is described, supporting the update performance required to run enterprise applications on read-optimised databases. Further, a memory traffic based cost model for the merge process is provided.},
language = {en}
}
@book{OPUS4-6813,
title = {Cloud security mechanisms},
number = {87},
editor = {Neuhaus, Christian and Polze, Andreas},
publisher = {Universit{\"a}tsverlag Potsdam},
address = {Potsdam},
isbn = {978-3-86956-281-0},
issn = {1613-5652},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-68168},
publisher = {Universit{\"a}t Potsdam},
pages = {78},
year = {2014},
abstract = {Cloud computing has brought great benefits in cost and flexibility for provisioning services. The greatest challenge of cloud computing remains however the question of security. The current standard tools in access control mechanisms and cryptography can only partly solve the security challenges of cloud infrastructures. In the recent years of research in security and cryptography, novel mechanisms, protocols and algorithms have emerged that offer new ways to create secure services atop cloud infrastructures. This report provides introductions to a selection of security mechanisms that were part of the "Cloud Security Mechanisms" seminar in summer term 2013 at HPI.},
language = {en}
}
@article{TorkuraSukmanaChengetal.2020,
author = {Torkura, Kennedy A. and Sukmana, Muhammad Ihsan Haikal and Cheng, Feng and Meinel, Christoph},
title = {CloudStrike},
series = {IEEE access : practical research, open solutions},
volume = {8},
journal = {IEEE access : practical research, open solutions},
publisher = {Institute of Electrical and Electronics Engineers },
address = {Piscataway},
issn = {2169-3536},
doi = {10.1109/ACCESS.2020.3007338},
pages = {123044 -- 123060},
year = {2020},
abstract = {Most cyber-attacks and data breaches in cloud infrastructure are due to human errors and misconfiguration vulnerabilities. Cloud customer-centric tools are imperative for mitigating these issues, however existing cloud security models are largely unable to tackle these security challenges. Therefore, novel security mechanisms are imperative, we propose Risk-driven Fault Injection (RDFI) techniques to address these challenges. RDFI applies the principles of chaos engineering to cloud security and leverages feedback loops to execute, monitor, analyze and plan security fault injection campaigns, based on a knowledge-base. The knowledge-base consists of fault models designed from secure baselines, cloud security best practices and observations derived during iterative fault injection campaigns. These observations are helpful for identifying vulnerabilities while verifying the correctness of security attributes (integrity, confidentiality and availability). Furthermore, RDFI proactively supports risk analysis and security hardening efforts by sharing security information with security mechanisms. We have designed and implemented the RDFI strategies including various chaos engineering algorithms as a software tool: CloudStrike. Several evaluations have been conducted with CloudStrike against infrastructure deployed on two major public cloud infrastructure: Amazon Web Services and Google Cloud Platform. The time performance linearly increases, proportional to increasing attack rates. Also, the analysis of vulnerabilities detected via security fault injection has been used to harden the security of cloud resources to demonstrate the effectiveness of the security information provided by CloudStrike. Therefore, we opine that our approaches are suitable for overcoming contemporary cloud security issues.},
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}
}
@phdthesis{Steinmetz2013,
author = {Steinmetz, Nadine},
title = {Context-aware semantic analysis of video metadata},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-70551},
school = {Universit{\"a}t Potsdam},
year = {2013},
abstract = {Im Vergleich zu einer stichwortbasierten Suche erm{\"o}glicht die semantische Suche ein pr{\"a}ziseres und anspruchsvolleres Durchsuchen von (Web)-Dokumenten, weil durch die explizite Semantik Mehrdeutigkeiten von nat{\"u}rlicher Sprache vermieden und semantische Beziehungen in das Suchergebnis einbezogen werden k{\"o}nnen. Eine semantische, Entit{\"a}ten-basierte Suche geht von einer Anfrage mit festgelegter Bedeutung aus und liefert nur Dokumente, die mit dieser Entit{\"a}t annotiert sind als Suchergebnis. Die wichtigste Voraussetzung f{\"u}r eine Entit{\"a}ten-zentrierte Suche stellt die Annotation der Dokumente im Archiv mit Entit{\"a}ten und Kategorien dar. Textuelle Informationen werden analysiert und mit den entsprechenden Entit{\"a}ten und Kategorien versehen, um den Inhalt semantisch erschließen zu k{\"o}nnen. Eine manuelle Annotation erfordert Dom{\"a}nenwissen und ist sehr zeitaufwendig. Die semantische Annotation von Videodokumenten erfordert besondere Aufmerksamkeit, da inhaltsbasierte Metadaten von Videos aus verschiedenen Quellen stammen, verschiedene Eigenschaften und Zuverl{\"a}ssigkeiten besitzen und daher nicht wie Fließtext behandelt werden k{\"o}nnen. Die vorliegende Arbeit stellt einen semantischen Analyseprozess f{\"u}r Video-Metadaten vor. Die Eigenschaften der verschiedenen Metadatentypen werden analysiert und ein Konfidenzwert ermittelt. Dieser Wert spiegelt die Korrektheit und die wahrscheinliche Mehrdeutigkeit eines Metadatums wieder. Beginnend mit dem Metadatum mit dem h{\"o}chsten Konfidenzwert wird der Analyseprozess innerhalb eines Kontexts in absteigender Reihenfolge des Konfidenzwerts durchgef{\"u}hrt. Die bereits analysierten Metadaten dienen als Referenzpunkt f{\"u}r die weiteren Analysen. So kann eine m{\"o}glichst korrekte Analyse der heterogen strukturierten Daten eines Kontexts sichergestellt werden. Am Ende der Analyse eines Metadatums wird die f{\"u}r den Kontext relevanteste Entit{\"a}t aus einer Liste von Kandidaten identifiziert - das Metadatum wird disambiguiert. Hierf{\"u}r wurden verschiedene Disambiguierungsalgorithmen entwickelt, die Beschreibungstexte und semantische Beziehungen der Entit{\"a}tenkandidaten zum gegebenen Kontext in Betracht ziehen. Der Kontext f{\"u}r die Disambiguierung wird f{\"u}r jedes Metadatum anhand der Eigenschaften und Konfidenzwerte zusammengestellt. Der vorgestellte Analyseprozess ist an zwei Hypothesen angelehnt: Um die Analyseergebnisse verbessern zu k{\"o}nnen, sollten die Metadaten eines Kontexts in absteigender Reihenfolge ihres Konfidenzwertes verarbeitet werden und die Kontextgrenzen von Videometadaten sollten durch Segmentgrenzen definiert werden, um m{\"o}glichst Kontexte mit koh{\"a}rentem Inhalt zu erhalten. Durch ausf{\"u}hrliche Evaluationen konnten die gestellten Hypothesen best{\"a}tigt werden. Der Analyseprozess wurden gegen mehrere State-of-the-Art Methoden verglichen und erzielt verbesserte Ergebnisse in Bezug auf Recall und Precision, besonders f{\"u}r Metadaten, die aus weniger zuverl{\"a}ssigen Quellen stammen. Der Analyseprozess ist Teil eines Videoanalyse-Frameworks und wurde bereits erfolgreich in verschiedenen Projekten eingesetzt.},
language = {en}
}
@book{BeckerGieseNeumann2009,
author = {Becker, Basil and Giese, Holger and Neumann, Stefan},
title = {Correct dynamic service-oriented architectures : modeling and compositional verification with dynamic collaborations},
organization = {System Analysis and Modeling Group},
isbn = {978-3-940793-91-1},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-30473},
publisher = {Universit{\"a}t Potsdam},
year = {2009},
abstract = {Service-oriented modeling employs collaborations to capture the coordination of multiple roles in form of service contracts. In case of dynamic collaborations the roles may join and leave the collaboration at runtime and therefore complex structural dynamics can result, which makes it very hard to ensure their correct and safe operation. We present in this paper our approach for modeling and verifying such dynamic collaborations. Modeling is supported using a well-defined subset of UML class diagrams, behavioral rules for the structural dynamics, and UML state machines for the role behavior. To be also able to verify the resulting service-oriented systems, we extended our former results for the automated verification of systems with structural dynamics [7, 8] and developed a compositional reasoning scheme, which enables the reuse of verification results. We outline our approach using the example of autonomous vehicles that use such dynamic collaborations via ad-hoc networking to coordinate and optimize their joint behavior.},
language = {en}
}
@article{BorchertMockTomczaketal.2021,
author = {Borchert, Florian and Mock, Andreas and Tomczak, Aurelie and H{\"u}gel, Jonas and Alkarkoukly, Samer and Knurr, Alexander and Volckmar, Anna-Lena and Stenzinger, Albrecht and Schirmacher, Peter and Debus, J{\"u}rgen and J{\"a}ger, Dirk and Longerich, Thomas and Fr{\"o}hling, Stefan and Eils, Roland and Bougatf, Nina and Sax, Ulrich and Schapranow, Matthieu-Patrick},
title = {Correction to: Knowledge bases and software support for variant interpretation in precision oncology},
series = {Briefings in bioinformatics},
volume = {22},
journal = {Briefings in bioinformatics},
number = {6},
publisher = {Oxford Univ. Press},
address = {Oxford},
issn = {1467-5463},
doi = {10.1093/bib/bbab246},
pages = {1},
year = {2021},
language = {en}
}
@article{GoebelLagodzinskiSeidel2021,
author = {G{\"o}bel, Andreas and Lagodzinski, Gregor J. A. and Seidel, Karen},
title = {Counting homomorphisms to trees modulo a prime},
series = {ACM transactions on computation theory : TOCT / Association for Computing Machinery},
volume = {13},
journal = {ACM transactions on computation theory : TOCT / Association for Computing Machinery},
number = {3},
publisher = {Association for Computing Machinery},
address = {New York},
issn = {1942-3454},
doi = {10.1145/3460958},
pages = {1 -- 33},
year = {2021},
abstract = {Many important graph-theoretic notions can be encoded as counting graph homomorphism problems, such as partition functions in statistical physics, in particular independent sets and colourings. In this article, we study the complexity of \#(p) HOMSTOH, the problem of counting graph homomorphisms from an input graph to a graph H modulo a prime number p. Dyer and Greenhill proved a dichotomy stating that the tractability of non-modular counting graph homomorphisms depends on the structure of the target graph. Many intractable cases in non-modular counting become tractable in modular counting due to the common phenomenon of cancellation. In subsequent studies on counting modulo 2, however, the influence of the structure of H on the tractability was shown to persist, which yields similar dichotomies.
Our main result states that for every tree H and every prime p the problem \#pHOMSTOH is either polynomial time computable or \#P-p-complete. This relates to the conjecture of Faben and Jerrum stating that this dichotomy holds for every graph H when counting modulo 2. In contrast to previous results on modular counting, the tractable cases of \#pHOMSTOH are essentially the same for all values of the modulo when H is a tree. To prove this result, we study the structural properties of a homomorphism. As an important interim result, our study yields a dichotomy for the problem of counting weighted independent sets in a bipartite graph modulo some prime p. These results are the first suggesting that such dichotomies hold not only for the modulo 2 case but also for the modular counting functions of all primes p.},
language = {en}
}
@book{BauckmannAbedjanLeseretal.2012,
author = {Bauckmann, Jana and Abedjan, Ziawasch and Leser, Ulf and M{\"u}ller, Heiko and Naumann, Felix},
title = {Covering or complete? : Discovering conditional inclusion dependencies},
publisher = {Universit{\"a}tsverlag Potsdam},
address = {Potsdam},
isbn = {978-3-86956-212-4},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-62089},
publisher = {Universit{\"a}t Potsdam},
pages = {34},
year = {2012},
abstract = {Data dependencies, or integrity constraints, are used to improve the quality of a database schema, to optimize queries, and to ensure consistency in a database. In the last years conditional dependencies have been introduced to analyze and improve data quality. In short, a conditional dependency is a dependency with a limited scope defined by conditions over one or more attributes. Only the matching part of the instance must adhere to the dependency. In this paper we focus on conditional inclusion dependencies (CINDs). We generalize the definition of CINDs, distinguishing covering and completeness conditions. We present a new use case for such CINDs showing their value for solving complex data quality tasks. Further, we define quality measures for conditions inspired by precision and recall. We propose efficient algorithms that identify covering and completeness conditions conforming to given quality thresholds. Our algorithms choose not only the condition values but also the condition attributes automatically. Finally, we show that our approach efficiently provides meaningful and helpful results for our use case.},
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}
}
@article{OosthoekDoerr2021,
author = {Oosthoek, Kris and D{\"o}rr, Christian},
title = {Cyber security threats to bitcoin exchanges},
series = {IEEE transactions on network and service management : a publication of the IEEE},
volume = {18},
journal = {IEEE transactions on network and service management : a publication of the IEEE},
number = {2},
publisher = {IEEE},
address = {New York},
issn = {1932-4537},
doi = {10.1109/TNSM.2020.3046145},
pages = {1616 -- 1628},
year = {2021},
abstract = {Bitcoin is gaining traction as an alternative store of value. Its market capitalization transcends all other cryptocurrencies in the market. But its high monetary value also makes it an attractive target to cyber criminal actors. Hacking campaigns usually target an ecosystem's weakest points. In Bitcoin, the exchange platforms are one of them. Each exchange breach is a threat not only to direct victims, but to the credibility of Bitcoin's entire ecosystem. Based on an extensive analysis of 36 breaches of Bitcoin exchanges, we show the attack patterns used to exploit Bitcoin exchange platforms using an industry standard for reporting intelligence on cyber security breaches. Based on this we are able to provide an overview of the most common attack vectors, showing that all except three hacks were possible due to relatively lax security. We show that while the security regimen of Bitcoin exchanges is subpar compared to other financial service providers, the use of stolen credentials, which does not require any hacking, is decreasing. We also show that the amount of BTC taken during a breach is decreasing, as well as the exchanges that terminate after being breached. Furthermore we show that overall security posture has improved, but still has major flaws. To discover adversarial methods post-breach, we have analyzed two cases of BTC laundering. Through this analysis we provide insight into how exchange platforms with lax cyber security even further increase the intermediary risk introduced by them into the Bitcoin ecosystem.},
language = {en}
}
@book{BeckerGiese2012,
author = {Becker, Basil and Giese, Holger},
title = {Cyber-physical systems with dynamic structure : towards modeling and verification of inductive invariants},
publisher = {Universit{\"a}tsverlag Potsdam},
address = {Potsdam},
isbn = {978-3-86956-217-9},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-62437},
publisher = {Universit{\"a}t Potsdam},
pages = {iv, 27},
year = {2012},
abstract = {Cyber-physical systems achieve sophisticated system behavior exploring the tight interconnection of physical coupling present in classical engineering systems and information technology based coupling. A particular challenging case are systems where these cyber-physical systems are formed ad hoc according to the specific local topology, the available networking capabilities, and the goals and constraints of the subsystems captured by the information processing part. In this paper we present a formalism that permits to model the sketched class of cyber-physical systems. The ad hoc formation of tightly coupled subsystems of arbitrary size are specified using a UML-based graph transformation system approach. Differential equations are employed to define the resulting tightly coupled behavior. Together, both form hybrid graph transformation systems where the graph transformation rules define the discrete steps where the topology or modes may change, while the differential equations capture the continuous behavior in between such discrete changes. In addition, we demonstrate that automated analysis techniques known for timed graph transformation systems for inductive invariants can be extended to also cover the hybrid case for an expressive case of hybrid models where the formed tightly coupled subsystems are restricted to smaller local networks.},
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}
}
@article{KossmannPapenbrockNaumann2021,
author = {Koßmann, Jan and Papenbrock, Thorsten and Naumann, Felix},
title = {Data dependencies for query optimization},
series = {The VLDB journal : the international journal on very large data bases / publ. on behalf of the VLDB Endowment},
volume = {31},
journal = {The VLDB journal : the international journal on very large data bases / publ. on behalf of the VLDB Endowment},
number = {1},
publisher = {Springer},
address = {Berlin ; Heidelberg ; New York},
issn = {1066-8888},
doi = {10.1007/s00778-021-00676-3},
pages = {1 -- 22},
year = {2021},
abstract = {Effective query optimization is a core feature of any database management system. While most query optimization techniques make use of simple metadata, such as cardinalities and other basic statistics, other optimization techniques are based on more advanced metadata including data dependencies, such as functional, uniqueness, order, or inclusion dependencies. This survey provides an overview, intuitive descriptions, and classifications of query optimization and execution strategies that are enabled by data dependencies. We consider the most popular types of data dependencies and focus on optimization strategies that target the optimization of relational database queries. The survey supports database vendors to identify optimization opportunities as well as DBMS researchers to find related work and open research questions.},
language = {en}
}
@phdthesis{Meyer2015,
author = {Meyer, Andreas},
title = {Data perspective in business process management},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-84806},
school = {Universit{\"a}t Potsdam},
pages = {xxi, 362},
year = {2015},
abstract = {Gesch{\"a}ftsprozessmanagement ist ein strukturierter Ansatz zur Modellierung, Analyse, Steuerung und Ausf{\"u}hrung von Gesch{\"a}ftsprozessen, um Gesch{\"a}ftsziele zu erreichen. Es st{\"u}tzt sich dabei auf konzeptionelle Modelle, von denen Prozessmodelle am weitesten verbreitet sind. Prozessmodelle beschreiben wer welche Aufgabe auszuf{\"u}hren hat, um das Gesch{\"a}ftsziel zu erreichen, und welche Informationen daf{\"u}r ben{\"o}tigt werden. Damit beinhalten Prozessmodelle Informationen {\"u}ber den Kontrollfluss, die Zuweisung von Verantwortlichkeiten, den Datenfluss und Informationssysteme. Die Automatisierung von Gesch{\"a}ftsprozessen erh{\"o}ht die Effizienz der Arbeitserledigung und wird durch Process Engines unterst{\"u}tzt. Daf{\"u}r werden jedoch Informationen {\"u}ber den Kontrollfluss, die Zuweisung von Verantwortlichkeiten f{\"u}r Aufgaben und den Datenfluss ben{\"o}tigt. W{\"a}hrend aktuelle Process Engines die ersten beiden Informationen weitgehend automatisiert verarbeiten k{\"o}nnen, m{\"u}ssen Daten manuell implementiert und gewartet werden. Dem entgegen verspricht ein modell-getriebenes Behandeln von Daten eine vereinfachte Implementation in der Process Engine und verringert gleichzeitig die Fehleranf{\"a}lligkeit dank einer graphischen Visualisierung und reduziert den Entwicklungsaufwand durch Codegenerierung. Die vorliegende Dissertation besch{\"a}ftigt sich mit der Modellierung, der Analyse und der Ausf{\"u}hrung von Daten in Gesch{\"a}ftsprozessen. Als formale Basis f{\"u}r die Prozessausf{\"u}hrung wird ein konzeptuelles Framework f{\"u}r die Integration von Prozessen und Daten eingef{\"u}hrt. Dieses Framework wird durch operationelle Semantik erg{\"a}nzt, die mittels einem um Daten erweiterten Petrinetz-Mapping vorgestellt wird. Die modellgetriebene Ausf{\"u}hrung von Daten muss komplexe Datenabh{\"a}ngigkeiten, Prozessdaten und den Datenaustausch ber{\"u}cksichtigen. Letzterer tritt bei der Kommunikation zwischen mehreren Prozessteilnehmern auf. Diese Arbeit nutzt Konzepte aus dem Bereich der Datenbanken und {\"u}berf{\"u}hrt diese ins Gesch{\"a}ftsprozessmanagement, um Datenoperationen zu unterscheiden, um Abh{\"a}ngigkeiten zwischen Datenobjekten des gleichen und verschiedenen Typs zu spezifizieren, um modellierte Datenknoten sowie empfangene Nachrichten zur richtigen laufenden Prozessinstanz zu korrelieren und um Nachrichten f{\"u}r die Prozess{\"u}bergreifende Kommunikation zu generieren. Der entsprechende Ansatz ist nicht auf eine bestimmte Prozessbeschreibungssprache begrenzt und wurde prototypisch implementiert. Die Automatisierung der Datenbehandlung in Gesch{\"a}ftsprozessen erfordert entsprechend annotierte und korrekte Prozessmodelle. Als Unterst{\"u}tzung zur Datenannotierung f{\"u}hrt diese Arbeit einen Algorithmus ein, welcher Informationen {\"u}ber Datenknoten, deren Zust{\"a}nde und Datenabh{\"a}ngigkeiten aus Kontrollflussinformationen extrahiert und die Prozessmodelle entsprechend annotiert. Allerdings k{\"o}nnen gew{\"o}hnlich nicht alle erforderlichen Informationen aus Kontrollflussinformationen extrahiert werden, da detaillierte Angaben {\"u}ber m{\"o}gliche Datenmanipulationen fehlen. Deshalb sind weitere Prozessmodellverfeinerungen notwendig. Basierend auf einer Menge von Objektlebenszyklen kann ein Prozessmodell derart verfeinert werden, dass die in den Objektlebenszyklen spezifizierten Datenmanipulationen automatisiert in ein Prozessmodell {\"u}berf{\"u}hrt werden k{\"o}nnen. Prozessmodelle stellen eine Abstraktion dar. Somit fokussieren sie auf verschiedene Teilbereiche und stellen diese im Detail dar. Solche Detailbereiche sind beispielsweise die Kontrollflusssicht und die Datenflusssicht, welche oft durch Aktivit{\"a}ts-zentrierte beziehungsweise Objekt-zentrierte Prozessmodelle abgebildet werden. In der vorliegenden Arbeit werden Algorithmen zur Transformation zwischen diesen Sichten beschrieben. Zur Sicherstellung der Modellkorrektheit wird das Konzept der „weak conformance" zur {\"U}berpr{\"u}fung der Konsistenz zwischen Objektlebenszyklen und dem Prozessmodell eingef{\"u}hrt. Dabei darf das Prozessmodell nur Datenmanipulationen enthalten, die auch in einem Objektlebenszyklus spezifiziert sind. Die Korrektheit wird mittels Soundness-{\"U}berpr{\"u}fung einer hybriden Darstellung ermittelt, so dass Kontrollfluss- und Datenkorrektheit integriert {\"u}berpr{\"u}ft werden. Um eine korrekte Ausf{\"u}hrung des Prozessmodells zu gew{\"a}hrleisten, m{\"u}ssen gefundene Inkonsistenzen korrigiert werden. Daf{\"u}r werden f{\"u}r jede Inkonsistenz alternative Vorschl{\"a}ge zur Modelladaption identifiziert und vorgeschlagen. Zusammengefasst, unter Einsatz der Ergebnisse dieser Dissertation k{\"o}nnen Gesch{\"a}ftsprozesse modellgetrieben ausgef{\"u}hrt werden unter Ber{\"u}cksichtigung sowohl von Daten als auch den zuvor bereits unterst{\"u}tzten Perspektiven bez{\"u}glich Kontrollfluss und Verantwortlichkeiten. Dabei wird die Modellerstellung teilweise mit automatisierten Algorithmen unterst{\"u}tzt und die Modellkonsistenz durch Datenkorrektheits{\"u}berpr{\"u}fungen gew{\"a}hrleistet.},
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.
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}
}
@phdthesis{Wang2016,
author = {Wang, Cheng},
title = {Deep Learning of Multimodal Representations},
school = {Universit{\"a}t Potsdam},
pages = {142},
year = {2016},
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}
}
@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}
}
@article{VitaglianoJiangNaumann2021,
author = {Vitagliano, Gerardo and Jiang, Lan and Naumann, Felix},
title = {Detecting layout templates in complex multiregion files},
series = {Proceedings of the VLDB Endowment},
volume = {15},
journal = {Proceedings of the VLDB Endowment},
number = {3},
publisher = {Association for Computing Machinery},
address = {New York},
issn = {2150-8097},
doi = {10.14778/3494124.3494145},
pages = {646 -- 658},
year = {2021},
abstract = {Spreadsheets are among the most commonly used file formats for data management, distribution, and analysis. Their widespread employment makes it easy to gather large collections of data, but their flexible canvas-based structure makes automated analysis difficult without heavy preparation. One of the common problems that practitioners face is the presence of multiple, independent regions in a single spreadsheet, possibly separated by repeated empty cells. We define such files as "multiregion" files. In collections of various spreadsheets, we can observe that some share the same layout. We present the Mondrian approach to automatically identify layout templates across multiple files and systematically extract the corresponding regions. Our approach is composed of three phases: first, each file is rendered as an image and inspected for elements that could form regions; then, using a clustering algorithm, the identified elements are grouped to form regions; finally, every file layout is represented as a graph and compared with others to find layout templates. We compare our method to state-of-the-art table recognition algorithms on two corpora of real-world enterprise spreadsheets. Our approach shows the best performances in detecting reliable region boundaries within each file and can correctly identify recurring layouts across files.},
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}
}