@article{ZhouFischerBrahmsetal.2023, author = {Zhou, Lin and Fischer, Eric and Brahms, Clemens Markus and Granacher, Urs and Arnrich, Bert}, title = {DUO-GAIT}, series = {Scientific data}, volume = {10}, journal = {Scientific data}, number = {1}, publisher = {Nature Publ. Group}, address = {London}, issn = {2052-4463}, doi = {10.1038/s41597-023-02391-w}, pages = {10}, year = {2023}, abstract = {In recent years, there has been a growing interest in developing and evaluating gait analysis algorithms based on inertial measurement unit (IMU) data, which has important implications, including sports, assessment of diseases, and rehabilitation. Multi-tasking and physical fatigue are two relevant aspects of daily life gait monitoring, but there is a lack of publicly available datasets to support the development and testing of methods using a mobile IMU setup. We present a dataset consisting of 6-minute walks under single- (only walking) and dual-task (walking while performing a cognitive task) conditions in unfatigued and fatigued states from sixteen healthy adults. Especially, nine IMUs were placed on the head, chest, lower back, wrists, legs, and feet to record under each of the above-mentioned conditions. The dataset also includes a rich set of spatio-temporal gait parameters that capture the aspects of pace, symmetry, and variability, as well as additional study-related information to support further analysis. This dataset can serve as a foundation for future research on gait monitoring in free-living environments.}, language = {en} } @article{YousfiWeske2019, author = {Yousfi, Alaaeddine and Weske, Mathias}, title = {Discovering commute patterns via process mining}, series = {Knowledge and Information Systems}, volume = {60}, journal = {Knowledge and Information Systems}, number = {2}, publisher = {Springer}, address = {London}, issn = {0219-1377}, doi = {10.1007/s10115-018-1255-1}, pages = {691 -- 713}, year = {2019}, abstract = {Ubiquitous computing has proven its relevance and efficiency in improving the user experience across a myriad of situations. It is now the ineluctable solution to keep pace with the ever-changing environments in which current systems operate. Despite the achievements of ubiquitous computing, this discipline is still overlooked in business process management. This is surprising, since many of today's challenges, in this domain, can be addressed by methods and techniques from ubiquitous computing, for instance user context and dynamic aspects of resource locations. This paper takes a first step to integrate methods and techniques from ubiquitous computing in business process management. To do so, we propose discovering commute patterns via process mining. Through our proposition, we can deduce the users' significant locations, routes, travel times and travel modes. This information can be a stepping-stone toward helping the business process management community embrace the latest achievements in ubiquitous computing, mainly in location-based service. To corroborate our claims, a user study was conducted. The significant places, routes, travel modes and commuting times of our test subjects were inferred with high accuracies. All in all, ubiquitous computing can enrich the processes with new capabilities that go beyond what has been established in business process management so far.}, language = {en} } @article{YeungNollGibbinsetal.2011, author = {Yeung, Ching-man Au and Noll, Michael G. and Gibbins, Nicholas and Meinel, Christoph and Shadbolt, Nigel}, title = {Spear spamming-resistant expertise analysis and ranking incollaborative tagging systems}, series = {Computational intelligence}, volume = {27}, journal = {Computational intelligence}, number = {3}, publisher = {Wiley-Blackwell}, address = {Hoboken}, issn = {0824-7935}, doi = {10.1111/j.1467-8640.2011.00384.x}, pages = {458 -- 488}, year = {2011}, abstract = {In this article, we discuss the notions of experts and expertise in resource discovery in the context of collaborative tagging systems. We propose that the level of expertise of a user with respect to a particular topic is mainly determined by two factors. First, an expert should possess a high-quality collection of resources, while the quality of a Web resource in turn depends on the expertise of the users who have assigned tags to it, forming a mutual reinforcement relationship. Second, an expert should be one who tends to identify interesting or useful resources before other users discover them, thus bringing these resources to the attention of the community of users. We propose a graph-based algorithm, SPEAR (spamming-resistant expertise analysis and ranking), which implements the above ideas for ranking users in a folksonomy. Our experiments show that our assumptions on expertise in resource discovery, and SPEAR as an implementation of these ideas, allow us to promote experts and demote spammers at the same time, with performance significantly better than the original hypertext-induced topic search algorithm and simple statistical measures currently used in most collaborative tagging systems.}, language = {en} } @article{YangDumasGarciaBanuelosetal.2012, author = {Yang, Yong and Dumas, Marlon and Garcia-Banuelos, Luciano and Polyvyanyy, Artem and Zhang, Liang}, title = {Generalized aggregate quality of service computation for composite services}, series = {The journal of systems and software}, volume = {85}, journal = {The journal of systems and software}, number = {8}, publisher = {Elsevier}, address = {New York}, issn = {0164-1212}, doi = {10.1016/j.jss.2012.03.005}, pages = {1818 -- 1830}, year = {2012}, abstract = {This article addresses the problem of estimating the Quality of Service (QoS) of a composite service given the QoS of the services participating in the composition. Previous solutions to this problem impose restrictions on the topology of the orchestration models, limiting their applicability to well-structured orchestration models for example. This article lifts these restrictions by proposing a method for aggregate QoS computation that deals with more general types of unstructured orchestration models. The applicability and scalability of the proposed method are validated using a collection of models from industrial practice.}, language = {en} } @article{YangQuehlSack2014, author = {Yang, Haojin and Quehl, Bernhard and Sack, Harald}, title = {A framework for improved video text detection and recognition}, series = {Multimedia tools and applications : an international journal}, volume = {69}, journal = {Multimedia tools and applications : an international journal}, number = {1}, publisher = {Springer}, address = {Dordrecht}, issn = {1380-7501}, doi = {10.1007/s11042-012-1250-6}, pages = {217 -- 245}, year = {2014}, abstract = {Text displayed in a video is an essential part for the high-level semantic information of the video content. Therefore, video text can be used as a valuable source for automated video indexing in digital video libraries. In this paper, we propose a workflow for video text detection and recognition. In the text detection stage, we have developed a fast localization-verification scheme, in which an edge-based multi-scale text detector first identifies potential text candidates with high recall rate. Then, detected candidate text lines are refined by using an image entropy-based filter. Finally, Stroke Width Transform (SWT)- and Support Vector Machine (SVM)-based verification procedures are applied to eliminate the false alarms. For text recognition, we have developed a novel skeleton-based binarization method in order to separate text from complex backgrounds to make it processible for standard OCR (Optical Character Recognition) software. Operability and accuracy of proposed text detection and binarization methods have been evaluated by using publicly available test data sets.}, language = {en} } @book{WaetzoldtGiese2015, author = {W{\"a}tzoldt, Sebastian and Giese, Holger}, title = {Modeling collaborations in self-adaptive systems of systems}, number = {96}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-324-4}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-73036}, publisher = {Universit{\"a}t Potsdam}, pages = {72}, year = {2015}, abstract = {An increasing demand on functionality and flexibility leads to an integration of beforehand isolated system solutions building a so-called System of Systems (SoS). Furthermore, the overall SoS should be adaptive to react on changing requirements and environmental conditions. Due SoS are composed of different independent systems that may join or leave the overall SoS at arbitrary point in times, the SoS structure varies during the systems lifetime and the overall SoS behavior emerges from the capabilities of the contained subsystems. In such complex system ensembles new demands of understanding the interaction among subsystems, the coupling of shared system knowledge and the influence of local adaptation strategies to the overall resulting system behavior arise. In this report, we formulate research questions with the focus of modeling interactions between system parts inside a SoS. Furthermore, we define our notion of important system types and terms by retrieving the current state of the art from literature. Having a common understanding of SoS, we discuss a set of typical SoS characteristics and derive general requirements for a collaboration modeling language. Additionally, we retrieve a broad spectrum of real scenarios and frameworks from literature and discuss how these scenarios cope with different characteristics of SoS. Finally, we discuss the state of the art for existing modeling languages that cope with collaborations for different system types such as SoS.}, language = {en} } @phdthesis{Waetzoldt2016, author = {W{\"a}tzoldt, Sebastian}, title = {Modeling collaborations in adaptive systems of systems}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-97494}, school = {Universit{\"a}t Potsdam}, pages = {XII, 380}, year = {2016}, abstract = {Recently, due to an increasing demand on functionality and flexibility, beforehand isolated systems have become interconnected to gain powerful adaptive Systems of Systems (SoS) solutions with an overall robust, flexible and emergent behavior. The adaptive SoS comprises a variety of different system types ranging from small embedded to adaptive cyber-physical systems. On the one hand, each system is independent, follows a local strategy and optimizes its behavior to reach its goals. On the other hand, systems must cooperate with each other to enrich the overall functionality to jointly perform on the SoS level reaching global goals, which cannot be satisfied by one system alone. Due to difficulties of local and global behavior optimizations conflicts may arise between systems that have to be solved by the adaptive SoS. This thesis proposes a modeling language that facilitates the description of an adaptive SoS by considering the adaptation capabilities in form of feedback loops as first class entities. Moreover, this thesis adopts the Models@runtime approach to integrate the available knowledge in the systems as runtime models into the modeled adaptation logic. Furthermore, the modeling language focuses on the description of system interactions within the adaptive SoS to reason about individual system functionality and how it emerges via collaborations to an overall joint SoS behavior. Therefore, the modeling language approach enables the specification of local adaptive system behavior, the integration of knowledge in form of runtime models and the joint interactions via collaboration to place the available adaptive behavior in an overall layered, adaptive SoS architecture. Beside the modeling language, this thesis proposes analysis rules to investigate the modeled adaptive SoS, which enables the detection of architectural patterns as well as design flaws and pinpoints to possible system threats. Moreover, a simulation framework is presented, which allows the direct execution of the modeled SoS architecture. Therefore, the analysis rules and the simulation framework can be used to verify the interplay between systems as well as the modeled adaptation effects within the SoS. This thesis realizes the proposed concepts of the modeling language by mapping them to a state of the art standard from the automotive domain and thus, showing their applicability to actual systems. Finally, the modeling language approach is evaluated by remodeling up to date research scenarios from different domains, which demonstrates that the modeling language concepts are powerful enough to cope with a broad range of existing research problems.}, language = {en} } @article{WistWollowskiSchaeferetal.2009, author = {Wist, Dominic and Wollowski, Ralf and Schaefer, Mark and Vogler, Walter}, title = {Avoiding irreducible CSC conflicts by internal communication}, issn = {0169-2968}, doi = {10.3233/Fi-2009-140}, year = {2009}, abstract = {Resynthesis of handshake specifications obtained e. g. from BALSA or TANGRAM with speed-independent logic synthesis from STGs is a promising approach. To deal with state-space explosion, we suggested STG decomposition; a problem is that decomposition can lead to irreducible CSC conflicts. Here, we present a new approach to solve such conflicts by introducing internal communication between the components. We give some first, very encouraging results for very large STGs concerning synthesis time and circuit area.}, language = {en} } @book{WistWollowski2007, author = {Wist, Dominic and Wollowski, Ralf}, title = {STG decomposition : avoiding irreducible CSC conflicts by internal communication}, isbn = {978-3-940793-02-7}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-32968}, publisher = {Universit{\"a}t Potsdam}, year = {2007}, abstract = {Inhalt: 1 Introduction 2 Basic Definitions 3 Achieving SI Implementability by Internal Communication 4 Towards a Structural Method 5 Examples 6 Conclusions and Future Work}, language = {en} } @book{WistSchaeferVogleretal.2010, author = {Wist, Dominic and Schaefer, Mark and Vogler, Walter and Wollowski, Ralf}, title = {STG decomposition : internal communication for SI implementability}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-037-3}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-40786}, publisher = {Universit{\"a}t Potsdam}, pages = {36}, year = {2010}, abstract = {STG decomposition is a promising approach to tackle the complexity problems arising in logic synthesis of speed independent circuits, a robust asynchronous (i.e. clockless) circuit type. Unfortunately, STG decomposition can result in components that in isolation have irreducible CSC conflicts. Generalising earlier work, it is shown how to resolve such conflicts by introducing internal communication between the components via structural techniques only.}, language = {en} } @article{WistSchaeferVogleretal.2011, author = {Wist, Dominic and Schaefer, Mark and Vogler, Walter and Wollowski, Ralf}, title = {Signal transition graph decomposition internal communication for speed independent circuit implementation}, series = {IET Computers and digital techniques}, volume = {5}, journal = {IET Computers and digital techniques}, number = {6}, publisher = {Institution of Engineering and Technology}, address = {Hertford}, issn = {1751-8601}, doi = {10.1049/iet-cdt.2010.0162}, pages = {440 -- 451}, year = {2011}, abstract = {Logic synthesis of speed independent circuits based on signal transition graph (STG) decomposition is a promising approach to tackle complexity problems like state-space explosion. Unfortunately, decomposition can result in components that in isolation have irreducible complete state coding conflicts. In earlier work, the authors showed how to resolve such conflicts by introducing internal communication between components, but only for very restricted specification structures. Here, they improve their former work by presenting algorithms for identifying delay transitions and inserting gyroscopes for specifications having a much more general structure. Thus, the authors are now able to synthesise controllers from real-life specifications. For all algorithms, they present correctness proofs and show their successful application to benchmarks, including very complex STGs arising in the context of control resynthesis.}, 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{WeyandChromikWolfetal.2017, author = {Weyand, Christopher and Chromik, Jonas and Wolf, Lennard and K{\"o}tte, Steffen and Haase, Konstantin and Felgentreff, Tim and Lincke, Jens and Hirschfeld, Robert}, title = {Improving hosted continuous integration services}, number = {108}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-377-0}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-94251}, publisher = {Universit{\"a}t Potsdam}, pages = {viii, 114}, year = {2017}, abstract = {Developing large software projects is a complicated task and can be demanding for developers. Continuous integration is common practice for reducing complexity. By integrating and testing changes often, changesets are kept small and therefore easily comprehensible. Travis CI is a service that offers continuous integration and continuous deployment in the cloud. Software projects are build, tested, and deployed using the Travis CI infrastructure without interrupting the development process. This report describes how Travis CI works, presents how time-driven, periodic building is implemented as well as how CI data visualization can be done, and proposes a way of dealing with dependency problems.}, language = {en} } @article{WestphalAxelssonNeuhausetal.2014, author = {Westphal, Florian and Axelsson, Stefan and Neuhaus, Christian and Polze, Andreas}, title = {VMI-PL: A monitoring language for virtual platforms using virtual machine introspection}, series = {Digital Investigation : the international journal of digital forensics \& incident response}, volume = {11}, journal = {Digital Investigation : the international journal of digital forensics \& incident response}, publisher = {Elsevier}, address = {Oxford}, issn = {1742-2876}, doi = {10.1016/j.diin.2014.05.016}, pages = {S85 -- S94}, year = {2014}, abstract = {With the growth of virtualization and cloud computing, more and more forensic investigations rely on being able to perform live forensics on a virtual machine using virtual machine introspection (VMI). Inspecting a virtual machine through its hypervisor enables investigation without risking contamination of the evidence, crashing the computer, etc. To further access to these techniques for the investigator/researcher we have developed a new VMI monitoring language. This language is based on a review of the most commonly used VMI-techniques to date, and it enables the user to monitor the virtual machine's memory, events and data streams. A prototype implementation of our monitoring system was implemented in KVM, though implementation on any hypervisor that uses the common x86 virtualization hardware assistance support should be straightforward. Our prototype outperforms the proprietary VMWare VProbes in many cases, with a maximum performance loss of 18\% for a realistic test case, which we consider acceptable. Our implementation is freely available under a liberal software distribution license. (C) 2014 Digital Forensics Research Workshop. Published by Elsevier Ltd. All rights reserved.}, language = {en} } @unpublished{WeskeYangMaglio2012, author = {Weske, Mathias and Yang, Jian and Maglio, Paul P.}, title = {Special issue service oriented computing (ICSOC) guest editors' introduction}, series = {International journal of cooperative information systems}, volume = {21}, journal = {International journal of cooperative information systems}, number = {1}, publisher = {World Scientific}, address = {Singapore}, issn = {0218-8430}, doi = {10.1142/S0218843012020017}, pages = {1 -- 2}, year = {2012}, language = {en} } @book{Wendt2004, author = {Wendt, Siegfried}, title = {Auf dem Weg zu einem Softwareingenieurwesen}, isbn = {978-3-937786-37-7}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-33184}, publisher = {Universit{\"a}t Potsdam}, year = {2004}, abstract = {(1) {\"U}ber die Notwendigkeit, die bisherige Informatik in eine Grundlagenwissenschaft und eine Ingenieurwissenschaft aufzuspalten (2) Was ist Ingenieurskultur? (3) Das Kommunikationsproblem der Informatiker und ihre Unf{\"a}higkeit, es wahrzunehmen (4) Besonderheiten des Softwareingenieurwesens im Vergleich mit den klassischen Ingenieurdisziplinen (5) Softwareingenieurspl{\"a}ne k{\"o}nnen auch f{\"u}r Nichtfachleute verst{\"a}ndlich sein (6) Principles for Planning Curricula in Software Engineering}, language = {de} } @article{WeinsteinCehMeineletal.2022, author = {Weinstein, Theresa Julia and Ceh, Simon Majed and Meinel, Christoph and Benedek, Mathias}, title = {What's creative about sentences?}, series = {Creativity Research Journal}, volume = {34}, journal = {Creativity Research Journal}, number = {4}, publisher = {Routledge, Taylor \& Francis Group}, address = {Abingdon}, issn = {1040-0419}, doi = {10.1080/10400419.2022.2124777}, pages = {419 -- 430}, year = {2022}, abstract = {Evaluating creativity of verbal responses or texts is a challenging task due to psychometric issues associated with subjective ratings and the peculiarities of textual data. We explore an approach to objectively assess the creativity of responses in a sentence generation task to 1) better understand what language-related aspects are valued by human raters and 2) further advance the developments toward automating creativity evaluations. Over the course of two prior studies, participants generated 989 four-word sentences based on a four-letter prompt with the instruction to be creative. We developed an algorithm that scores each sentence on eight different metrics including 1) general word infrequency, 2) word combination infrequency, 3) context-specific word uniqueness, 4) syntax uniqueness, 5) rhyme, 6) phonetic similarity, and similarity of 7) sequence spelling and 8) semantic meaning to the cue. The text metrics were then used to explain the averaged creativity ratings of eight human raters. We found six metrics to be significantly correlated with the human ratings, explaining a total of 16\% of their variance. We conclude that the creative impression of sentences is partly driven by different aspects of novelty in word choice and syntax, as well as rhythm and sound, which are amenable to objective assessment.}, language = {en} } @article{WeidlichZiekowGaletal.2014, author = {Weidlich, Matthias and Ziekow, Holger and Gal, Avigdor and Mendling, Jan and Weske, Mathias}, title = {Optimizing event pattern matching using business process models}, series = {IEEE transactions on knowledge and data engineering}, volume = {26}, journal = {IEEE transactions on knowledge and data engineering}, number = {11}, publisher = {Inst. of Electr. and Electronics Engineers}, address = {Los Alamitos}, issn = {1041-4347}, doi = {10.1109/TKDE.2014.2302306}, pages = {2759 -- 2773}, year = {2014}, abstract = {A growing number of enterprises use complex event processing for monitoring and controlling their operations, while business process models are used to document working procedures. In this work, we propose a comprehensive method for complex event processing optimization using business process models. Our proposed method is based on the extraction of behaviorial constraints that are used, in turn, to rewrite patterns for event detection, and select and transform execution plans. We offer a set of rewriting rules that is shown to be complete with respect to the all, seq, and any patterns. The effectiveness of our method is demonstrated in an experimental evaluation with a large number of processes from an insurance company. We illustrate that the proposed optimization leads to significant savings in query processing. By integrating the optimization in state-of-the-art systems for event pattern matching, we demonstrate that these savings materialize in different technical infrastructures and can be combined with existing optimization techniques.}, language = {en} } @article{WeidlichPolyvyanyyMendlingetal.2011, author = {Weidlich, Matthias and Polyvyanyy, Artem and Mendling, Jan and Weske, Mathias}, title = {Causal behavioural profiles - efficient computation, applications, and evaluation}, series = {Fundamenta informaticae}, volume = {113}, journal = {Fundamenta informaticae}, number = {3-4}, publisher = {IOS Press}, address = {Amsterdam}, issn = {0169-2968}, doi = {10.3233/FI-2011-614}, pages = {399 -- 435}, year = {2011}, abstract = {Analysis of behavioural consistency is an important aspect of software engineering. In process and service management, consistency verification of behavioural models has manifold applications. For instance, a business process model used as system specification and a corresponding workflow model used as implementation have to be consistent. Another example would be the analysis to what degree a process log of executed business operations is consistent with the corresponding normative process model. Typically, existing notions of behaviour equivalence, such as bisimulation and trace equivalence, are applied as consistency notions. Still, these notions are exponential in computation and yield a Boolean result. In many cases, however, a quantification of behavioural deviation is needed along with concepts to isolate the source of deviation. In this article, we propose causal behavioural profiles as the basis for a consistency notion. These profiles capture essential behavioural information, such as order, exclusiveness, and causality between pairs of activities of a process model. Consistency based on these profiles is weaker than trace equivalence, but can be computed efficiently for a broad class of models. In this article, we introduce techniques for the computation of causal behavioural profiles using structural decomposition techniques for sound free-choice workflow systems if unstructured net fragments are acyclic or can be traced back to S-or T-nets. We also elaborate on the findings of applying our technique to three industry model collections.}, language = {en} } @article{WeidlichPolyvyanyyDesaietal.2011, author = {Weidlich, Matthias and Polyvyanyy, Artem and Desai, Nirmit and Mendling, Jan and Weske, Mathias}, title = {Process compliance analysis based on behavioural profiles}, series = {Information systems}, volume = {36}, journal = {Information systems}, number = {7}, publisher = {Elsevier}, address = {Oxford}, issn = {0306-4379}, doi = {10.1016/j.is.2011.04.002}, pages = {1009 -- 1025}, year = {2011}, abstract = {Process compliance measurement is getting increasing attention in companies due to stricter legal requirements and market pressure for operational excellence. In order to judge on compliance of the business processing, the degree of behavioural deviation of a case, i.e., an observed execution sequence, is quantified with respect to a process model (referred to as fitness, or recall). Recently, different compliance measures have been proposed. Still, nearly all of them are grounded on state-based techniques and the trace equivalence criterion, in particular. As a consequence, these approaches have to deal with the state explosion problem. In this paper, we argue that a behavioural abstraction may be leveraged to measure the compliance of a process log - a collection of cases. To this end, we utilise causal behavioural profiles that capture the behavioural characteristics of process models and cases, and can be computed efficiently. We propose different compliance measures based on these profiles, discuss the impact of noise in process logs on our measures, and show how diagnostic information on non-compliance is derived. As a validation, we report on findings of applying our approach in a case study with an international service provider.}, language = {en} } @article{WeidlichMendlingWeske2012, author = {Weidlich, Matthias and Mendling, Jan and Weske, Mathias}, title = {Propagating changes between aligned process models}, series = {The journal of systems and software}, volume = {85}, journal = {The journal of systems and software}, number = {8}, publisher = {Elsevier}, address = {New York}, issn = {0164-1212}, doi = {10.1016/j.jss.2012.02.044}, pages = {1885 -- 1898}, year = {2012}, abstract = {There is a wide variety of drivers for business process modelling initiatives, reaching from organisational redesign to the development of information systems. Consequently, a common business process is often captured in multiple models that overlap in content due to serving different purposes. Business process management aims at flexible adaptation to changing business needs. Hence, changes of business processes occur frequently and have to be incorporated in the respective process models. Once a process model is changed, related process models have to be updated accordingly, despite the fact that those process models may only be loosely coupled. In this article, we introduce an approach that supports change propagation between related process models. Given a change in one process model, we leverage the behavioural abstraction of behavioural profiles for corresponding activities in order to determine a change region in another model. Our approach is able to cope with changes in pairs of models that are not related by hierarchical refinement and show behavioural inconsistencies. We evaluate the applicability of our approach with two real-world process model collections. To this end, we either deduce change operations from different model revisions or rely on synthetic change operations.}, language = {en} } @article{WeidlichMendling2012, author = {Weidlich, Matthias and Mendling, Jan}, title = {Perceived consistency between process models}, series = {Information systems}, volume = {37}, journal = {Information systems}, number = {2}, publisher = {Elsevier}, address = {Oxford}, issn = {0306-4379}, doi = {10.1016/j.is.2010.12.004}, pages = {80 -- 98}, year = {2012}, abstract = {Process-aware information systems typically involve various kinds of process stakeholders. That, in turn, leads to multiple process models that capture a common process from different perspectives and at different levels of abstraction. In order to guarantee a certain degree of uniformity, the consistency of such related process models is evaluated using formal criteria. However, it is unclear how modelling experts assess the consistency between process models, and which kind of notion they perceive to be appropriate. In this paper, we focus on control flow aspects and investigate the adequacy of consistency notions. In particular, we report findings from an online experiment, which allows us to compare in how far trace equivalence and two notions based on behavioural profiles approximate expert perceptions on consistency. Analysing 69 expert statements from process analysts, we conclude that trace equivalence is not suited to be applied as a consistency notion, whereas the notions based on behavioural profiles approximate the perceived consistency of our subjects significantly. Therefore, our contribution is an empirically founded answer to the correlation of behaviour consistency notions and the consistency perception by experts in the field of business process modelling.}, language = {en} } @article{WeidlichDijkmanWeske2012, author = {Weidlich, Matthias and Dijkman, Remco and Weske, Mathias}, title = {Behaviour equivalence and compatibility of business process models with complex correspondences}, series = {The computer journal : a publication of the British Computer Society}, volume = {55}, journal = {The computer journal : a publication of the British Computer Society}, number = {11}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {0010-4620}, doi = {10.1093/comjnl/bxs014}, pages = {1398 -- 1418}, year = {2012}, abstract = {Once multiple models of a business process are created for different purposes or to capture different variants, verification of behaviour equivalence or compatibility is needed. Equivalence verification ensures that two business process models specify the same behaviour. Since different process models are likely to differ with respect to their assumed level of abstraction and the actions that they take into account, equivalence notions have to cope with correspondences between sets of actions and actions that exist in one process but not in the other. In this paper, we present notions of equivalence and compatibility that can handle these problems. In essence, we present a notion of equivalence that works on correspondences between sets of actions rather than single actions. We then integrate our equivalence notion with work on behaviour inheritance that copes with actions that exist in one process but not in the other, leading to notions of behaviour compatibility. Compatibility notions verify that two models have the same behaviour with respect to the actions that they have in common. As such, our contribution is a collection of behaviour equivalence and compatibility notions that are applicable in more general settings than existing ones.}, 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} } @book{WassermannFelgentreffPapeetal.2016, author = {Wassermann, Lars and Felgentreff, Tim and Pape, Tobias and Bolz, Carl Friedrich and Hirschfeld, Robert}, title = {Tracing Algorithmic Primitives in RSqueak/VM}, number = {104}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-355-8}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-91277}, publisher = {Universit{\"a}t Potsdam}, pages = {45}, year = {2016}, abstract = {When realizing a programming language as VM, implementing behavior as part of the VM, as primitive, usually results in reduced execution times. But supporting and developing primitive functions requires more effort than maintaining and using code in the hosted language since debugging is harder, and the turn-around times for VM parts are higher. Furthermore, source artifacts of primitive functions are seldom reused in new implementations of the same language. And if they are reused, the existing API usually is emulated, reducing the performance gains. Because of recent results in tracing dynamic compilation, the trade-off between performance and ease of implementation, reuse, and changeability might now be decided adversely. In this work, we investigate the trade-offs when creating primitives, and in particular how large a difference remains between primitive and hosted function run times in VMs with tracing just-in-time compiler. To that end, we implemented the algorithmic primitive BitBlt three times for RSqueak/VM. RSqueak/VM is a Smalltalk VM utilizing the PyPy RPython toolchain. We compare primitive implementations in C, RPython, and Smalltalk, showing that due to the tracing just-in-time compiler, the performance gap has lessened by one magnitude to one magnitude.}, language = {en} } @phdthesis{Wang2011, author = {Wang, Long}, title = {X-tracking the usage interest on web sites}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-51077}, school = {Universit{\"a}t Potsdam}, year = {2011}, abstract = {The exponential expanding of the numbers of web sites and Internet users makes WWW the most important global information resource. From information publishing and electronic commerce to entertainment and social networking, the Web allows an inexpensive and efficient access to the services provided by individuals and institutions. The basic units for distributing these services are the web sites scattered throughout the world. However, the extreme fragility of web services and content, the high competence between similar services supplied by different sites, and the wide geographic distributions of the web users drive the urgent requirement from the web managers to track and understand the usage interest of their web customers. This thesis, "X-tracking the Usage Interest on Web Sites", aims to fulfill this requirement. "X" stands two meanings: one is that the usage interest differs from various web sites, and the other is that usage interest is depicted from multi aspects: internal and external, structural and conceptual, objective and subjective. "Tracking" shows that our concentration is on locating and measuring the differences and changes among usage patterns. This thesis presents the methodologies on discovering usage interest on three kinds of web sites: the public information portal site, e-learning site that provides kinds of streaming lectures and social site that supplies the public discussions on IT issues. On different sites, we concentrate on different issues related with mining usage interest. The educational information portal sites were the first implementation scenarios on discovering usage patterns and optimizing the organization of web services. In such cases, the usage patterns are modeled as frequent page sets, navigation paths, navigation structures or graphs. However, a necessary requirement is to rebuild the individual behaviors from usage history. We give a systematic study on how to rebuild individual behaviors. Besides, this thesis shows a new strategy on building content clusters based on pair browsing retrieved from usage logs. The difference between such clusters and the original web structure displays the distance between the destinations from usage side and the expectations from design side. Moreover, we study the problem on tracking the changes of usage patterns in their life cycles. The changes are described from internal side integrating conceptual and structure features, and from external side for the physical features; and described from local side measuring the difference between two time spans, and global side showing the change tendency along the life cycle. A platform, Web-Cares, is developed to discover the usage interest, to measure the difference between usage interest and site expectation and to track the changes of usage patterns. E-learning site provides the teaching materials such as slides, recorded lecture videos and exercise sheets. We focus on discovering the learning interest on streaming lectures, such as real medias, mp4 and flash clips. Compared to the information portal site, the usage on streaming lectures encapsulates the variables such as viewing time and actions during learning processes. The learning interest is discovered in the form of answering 6 questions, which covers finding the relations between pieces of lectures and the preference among different forms of lectures. We prefer on detecting the changes of learning interest on the same course from different semesters. The differences on the content and structure between two courses leverage the changes on the learning interest. We give an algorithm on measuring the difference on learning interest integrated with similarity comparison between courses. A search engine, TASK-Moniminer, is created to help the teacher query the learning interest on their streaming lectures on tele-TASK site. Social site acts as an online community attracting web users to discuss the common topics and share their interesting information. Compared to the public information portal site and e-learning web site, the rich interactions among users and web content bring the wider range of content quality, on the other hand, provide more possibilities to express and model usage interest. We propose a framework on finding and recommending high reputation articles in a social site. We observed that the reputation is classified into global and local categories; the quality of the articles having high reputation is related with the content features. Based on these observations, our framework is implemented firstly by finding the articles having global or local reputation, and secondly clustering articles based on their content relations, and then the articles are selected and recommended from each cluster based on their reputation ranks.}, language = {en} } @article{WangYangMeinel2018, author = {Wang, Cheng and Yang, Haojin and Meinel, Christoph}, title = {Image Captioning with Deep Bidirectional LSTMs and Multi-Task Learning}, series = {ACM transactions on multimedia computing, communications, and applications}, volume = {14}, journal = {ACM transactions on multimedia computing, communications, and applications}, number = {2}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {1551-6857}, doi = {10.1145/3115432}, pages = {20}, year = {2018}, abstract = {Generating a novel and descriptive caption of an image is drawing increasing interests in computer vision, natural language processing, and multimedia communities. In this work, we propose an end-to-end trainable deep bidirectional LSTM (Bi-LSTM (Long Short-Term Memory)) model to address the problem. By combining a deep convolutional neural network (CNN) and two separate LSTM networks, our model is capable of learning long-term visual-language interactions by making use of history and future context information at high-level semantic space. We also explore deep multimodal bidirectional models, in which we increase the depth of nonlinearity transition in different ways to learn hierarchical visual-language embeddings. Data augmentation techniques such as multi-crop, multi-scale, and vertical mirror are proposed to prevent over-fitting in training deep models. To understand how our models "translate" image to sentence, we visualize and qualitatively analyze the evolution of Bi-LSTM internal states over time. The effectiveness and generality of proposed models are evaluated on four benchmark datasets: Flickr8K, Flickr30K, MSCOCO, and Pascal1K datasets. We demonstrate that Bi-LSTM models achieve highly competitive performance on both caption generation and image-sentence retrieval even without integrating an additional mechanism (e.g., object detection, attention model). Our experiments also prove that multi-task learning is beneficial to increase model generality and gain performance. We also demonstrate the performance of transfer learning of the Bi-LSTM model significantly outperforms previous methods on the Pascal1K dataset.}, language = {en} } @phdthesis{Wang2016, author = {Wang, Cheng}, title = {Deep Learning of Multimodal Representations}, school = {Universit{\"a}t Potsdam}, pages = {142}, year = {2016}, language = {en} } @article{vonSchorlemerWeiss2019, author = {von Schorlemer, Stephan and Weiß, Christian-Cornelius}, title = {data4life - Eine nutzerkontrollierte Gesundheitsdaten-Infrastruktu}, publisher = {Medizinisch Wissenschaftliche Verlagsgesellschaft}, address = {Berlin}, isbn = {978-3-95466-448-1}, pages = {249 -- 258}, year = {2019}, language = {de} } @article{VogelGiese2014, author = {Vogel, Thomas and Giese, Holger}, title = {Model-Driven engineering of self-adaptive software with EUREMA}, series = {ACM transactions on autonomous and adaptive systems}, volume = {8}, journal = {ACM transactions on autonomous and adaptive systems}, number = {4}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {1556-4665}, doi = {10.1145/2555612}, pages = {33}, year = {2014}, abstract = {The development of self-adaptive software requires the engineering of an adaptation engine that controls the underlying adaptable software by feedback loops. The engine often describes the adaptation by runtime models representing the adaptable software and by activities such as analysis and planning that use these models. To systematically address the interplay between runtime models and adaptation activities, runtime megamodels have been proposed. A runtime megamodel is a specific model capturing runtime models and adaptation activities. In this article, we go one step further and present an executable modeling language for ExecUtable RuntimE MegAmodels (EUREMA) that eases the development of adaptation engines by following a model-driven engineering approach. We provide a domain-specific modeling language and a runtime interpreter for adaptation engines, in particular feedback loops. Megamodels are kept alive at runtime and by interpreting them, they are directly executed to run feedback loops. Additionally, they can be dynamically adjusted to adapt feedback loops. Thus, EUREMA supports development by making feedback loops explicit at a higher level of abstraction and it enables solutions where multiple feedback loops interact or operate on top of each other and self-adaptation co-exists with offline adaptation for evolution.}, language = {en} } @book{VogelGiese2013, author = {Vogel, Thomas and Giese, Holger}, title = {Model-driven engineering of adaptation engines for self-adaptive software : executable runtime megamodels}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-227-8}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-63825}, publisher = {Universit{\"a}t Potsdam}, pages = {vi, 59}, year = {2013}, abstract = {The development of self-adaptive software requires the engineering of an adaptation engine that controls and adapts the underlying adaptable software by means of feedback loops. The adaptation engine often describes the adaptation by using runtime models representing relevant aspects of the adaptable software and particular activities such as analysis and planning that operate on these runtime models. To systematically address the interplay between runtime models and adaptation activities in adaptation engines, runtime megamodels have been proposed for self-adaptive software. A runtime megamodel is a specific runtime model whose elements are runtime models and adaptation activities. Thus, a megamodel captures the interplay between multiple models and between models and activities as well as the activation of the activities. In this article, we go one step further and present a modeling language for ExecUtable RuntimE MegAmodels (EUREMA) that considerably eases the development of adaptation engines by following a model-driven engineering approach. We provide a domain-specific modeling language and a runtime interpreter for adaptation engines, in particular for feedback loops. Megamodels are kept explicit and alive at runtime and by interpreting them, they are directly executed to run feedback loops. Additionally, they can be dynamically adjusted to adapt feedback loops. Thus, EUREMA supports development by making feedback loops, their runtime models, and adaptation activities explicit at a higher level of abstraction. Moreover, it enables complex solutions where multiple feedback loops interact or even operate on top of each other. Finally, it leverages the co-existence of self-adaptation and off-line adaptation for evolution.}, 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} } @article{VerweijNeyThompson2022, author = {Verweij, Marco and Ney, Steven and Thompson, Michael}, title = {Cultural Theory's contributions to climate science}, series = {European journal for philosophy of science}, volume = {12}, journal = {European journal for philosophy of science}, number = {2}, publisher = {Springer}, address = {Dordrecht}, issn = {1879-4912}, doi = {10.1007/s13194-022-00464-y}, pages = {13}, year = {2022}, abstract = {In his article, 'Social constructionism and climate science denial', Hansson claims to present empirical evidence that the cultural theory developed by Dame Mary Douglas, Aaron Wildavsky and ourselves (among others) leads to (climate) science denial. In this reply, we show that there is no validity to these claims. First, we show that Hansson's empirical evidence that cultural theory has led to climate science denial falls apart under closer inspection. Contrary to Hansson's claims, cultural theory has made significant contributions to understanding and addressing climate change. Second, we discuss various features of Douglas' cultural theory that differentiate it from other constructivist approaches and make it compatible with the scientific method. Thus, we also demonstrate that cultural theory cannot be accused of epistemic relativism.}, language = {en} } @article{VaidSomaniRussaketal.2020, author = {Vaid, Akhil and Somani, Sulaiman and Russak, Adam J. and De Freitas, Jessica K. and Chaudhry, Fayzan F. and Paranjpe, Ishan and Johnson, Kipp W. and Lee, Samuel J. and Miotto, Riccardo and Richter, Felix and Zhao, Shan and Beckmann, Noam D. and Naik, Nidhi and Kia, Arash and Timsina, Prem and Lala, Anuradha and Paranjpe, Manish and Golden, Eddye and Danieletto, Matteo and Singh, Manbir and Meyer, Dara and O'Reilly, Paul F. and Huckins, Laura and Kovatch, Patricia and Finkelstein, Joseph and Freeman, Robert M. and Argulian, Edgar and Kasarskis, Andrew and Percha, Bethany and Aberg, Judith A. and Bagiella, Emilia and Horowitz, Carol R. and Murphy, Barbara and Nestler, Eric J. and Schadt, Eric E. and Cho, Judy H. and Cordon-Cardo, Carlos and Fuster, Valentin and Charney, Dennis S. and Reich, David L. and B{\"o}ttinger, Erwin and Levin, Matthew A. and Narula, Jagat and Fayad, Zahi A. and Just, Allan C. and Charney, Alexander W. and Nadkarni, Girish N. and Glicksberg, Benjamin S.}, title = {Machine learning to predict mortality and critical events in a cohort of patients with COVID-19 in New York City: model development and validation}, series = {Journal of medical internet research : international scientific journal for medical research, information and communication on the internet ; JMIR}, volume = {22}, journal = {Journal of medical internet research : international scientific journal for medical research, information and communication on the internet ; JMIR}, number = {11}, publisher = {Healthcare World}, address = {Richmond, Va.}, issn = {1439-4456}, doi = {10.2196/24018}, pages = {19}, year = {2020}, abstract = {Background: COVID-19 has infected millions of people worldwide and is responsible for several hundred thousand fatalities. The COVID-19 pandemic has necessitated thoughtful resource allocation and early identification of high-risk patients. However, effective methods to meet these needs are lacking. Objective: The aims of this study were to analyze the electronic health records (EHRs) of patients who tested positive for COVID-19 and were admitted to hospitals in the Mount Sinai Health System in New York City; to develop machine learning models for making predictions about the hospital course of the patients over clinically meaningful time horizons based on patient characteristics at admission; and to assess the performance of these models at multiple hospitals and time points. Methods: We used Extreme Gradient Boosting (XGBoost) and baseline comparator models to predict in-hospital mortality and critical events at time windows of 3, 5, 7, and 10 days from admission. Our study population included harmonized EHR data from five hospitals in New York City for 4098 COVID-19-positive patients admitted from March 15 to May 22, 2020. The models were first trained on patients from a single hospital (n=1514) before or on May 1, externally validated on patients from four other hospitals (n=2201) before or on May 1, and prospectively validated on all patients after May 1 (n=383). Finally, we established model interpretability to identify and rank variables that drive model predictions. Results: Upon cross-validation, the XGBoost classifier outperformed baseline models, with an area under the receiver operating characteristic curve (AUC-ROC) for mortality of 0.89 at 3 days, 0.85 at 5 and 7 days, and 0.84 at 10 days. XGBoost also performed well for critical event prediction, with an AUC-ROC of 0.80 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. In external validation, XGBoost achieved an AUC-ROC of 0.88 at 3 days, 0.86 at 5 days, 0.86 at 7 days, and 0.84 at 10 days for mortality prediction. Similarly, the unimputed XGBoost model achieved an AUC-ROC of 0.78 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. Trends in performance on prospective validation sets were similar. At 7 days, acute kidney injury on admission, elevated LDH, tachypnea, and hyperglycemia were the strongest drivers of critical event prediction, while higher age, anion gap, and C-reactive protein were the strongest drivers of mortality prediction. Conclusions: We externally and prospectively trained and validated machine learning models for mortality and critical events for patients with COVID-19 at different time horizons. These models identified at-risk patients and uncovered underlying relationships that predicted outcomes.}, language = {en} } @article{VaidChanChaudharyetal.2021, author = {Vaid, Akhil and Chan, Lili and Chaudhary, Kumardeep and Jaladanki, Suraj K. and Paranjpe, Ishan and Russak, Adam J. and Kia, Arash and Timsina, Prem and Levin, Matthew A. and He, John Cijiang and B{\"o}ttinger, Erwin and Charney, Alexander W. and Fayad, Zahi A. and Coca, Steven G. and Glicksberg, Benjamin S. and Nadkarni, Girish N.}, title = {Predictive approaches for acute dialysis requirement and death in COVID-19}, series = {Clinical journal of the American Society of Nephrology : CJASN}, volume = {16}, journal = {Clinical journal of the American Society of Nephrology : CJASN}, number = {8}, publisher = {American Society of Nephrology}, address = {Washington}, organization = {MSCIC}, issn = {1555-9041}, doi = {10.2215/CJN.17311120}, pages = {1158 -- 1168}, year = {2021}, abstract = {Background and objectives AKI treated with dialysis initiation is a common complication of coronavirus disease 2019 (COVID-19) among hospitalized patients. However, dialysis supplies and personnel are often limited. Design, setting, participants, \& measurements Using data from adult patients hospitalized with COVID-19 from five hospitals from theMount Sinai Health System who were admitted between March 10 and December 26, 2020, we developed and validated several models (logistic regression, Least Absolute Shrinkage and Selection Operator (LASSO), random forest, and eXtreme GradientBoosting [XGBoost; with and without imputation]) for predicting treatment with dialysis or death at various time horizons (1, 3, 5, and 7 days) after hospital admission. Patients admitted to theMount Sinai Hospital were used for internal validation, whereas the other hospitals formed part of the external validation cohort. Features included demographics, comorbidities, and laboratory and vital signs within 12 hours of hospital admission. Results A total of 6093 patients (2442 in training and 3651 in external validation) were included in the final cohort. Of the different modeling approaches used, XGBoost without imputation had the highest area under the receiver operating characteristic (AUROC) curve on internal validation (range of 0.93-0.98) and area under the precisionrecall curve (AUPRC; range of 0.78-0.82) for all time points. XGBoost without imputation also had the highest test parameters on external validation (AUROC range of 0.85-0.87, and AUPRC range of 0.27-0.54) across all time windows. XGBoost without imputation outperformed all models with higher precision and recall (mean difference in AUROC of 0.04; mean difference in AUPRC of 0.15). Features of creatinine, BUN, and red cell distribution width were major drivers of the model's prediction. Conclusions An XGBoost model without imputation for prediction of a composite outcome of either death or dialysis in patients positive for COVID-19 had the best performance, as compared with standard and other machine learning models.}, language = {en} } @phdthesis{Truemper2014, author = {Tr{\"u}mper, Jonas}, title = {Visualization techniques for the analysis of software behavior and related structures}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-72145}, school = {Universit{\"a}t Potsdam}, year = {2014}, abstract = {Software maintenance encompasses any changes made to a software system after its initial deployment and is thereby one of the key phases in the typical software-engineering lifecycle. In software maintenance, we primarily need to understand structural and behavioral aspects, which are difficult to obtain, e.g., by code reading. Software analysis is therefore a vital tool for maintaining these systems: It provides - the preferably automated - means to extract and evaluate information from their artifacts such as software structure, runtime behavior, and related processes. However, such analysis typically results in massive raw data, so that even experienced engineers face difficulties directly examining, assessing, and understanding these data. Among other things, they require tools with which to explore the data if no clear question can be formulated beforehand. For this, software analysis and visualization provide its users with powerful interactive means. These enable the automation of tasks and, particularly, the acquisition of valuable and actionable insights into the raw data. For instance, one means for exploring runtime behavior is trace visualization. This thesis aims at extending and improving the tool set for visual software analysis by concentrating on several open challenges in the fields of dynamic and static analysis of software systems. This work develops a series of concepts and tools for the exploratory visualization of the respective data to support users in finding and retrieving information on the system artifacts concerned. This is a difficult task, due to the lack of appropriate visualization metaphors; in particular, the visualization of complex runtime behavior poses various questions and challenges of both a technical and conceptual nature. This work focuses on a set of visualization techniques for visually representing control-flow related aspects of software traces from shared-memory software systems: A trace-visualization concept based on icicle plots aids in understanding both single-threaded as well as multi-threaded runtime behavior on the function level. The concept's extensibility further allows the visualization and analysis of specific aspects of multi-threading such as synchronization, the correlation of such traces with data from static software analysis, and a comparison between traces. Moreover, complementary techniques for simultaneously analyzing system structures and the evolution of related attributes are proposed. These aim at facilitating long-term planning of software architecture and supporting management decisions in software projects by extensions to the circular-bundle-view technique: An extension to 3-dimensional space allows for the use of additional variables simultaneously; interaction techniques allow for the modification of structures in a visual manner. The concepts and techniques presented here are generic and, as such, can be applied beyond software analysis for the visualization of similarly structured data. The techniques' practicability is demonstrated by several qualitative studies using subject data from industry-scale software systems. The studies provide initial evidence that the techniques' application yields useful insights into the subject data and its interrelationships in several scenarios.}, language = {en} } @article{TroegerPolze2009, author = {Troeger, Peter and Polze, Andreas}, title = {Object and process migration in .NET}, issn = {0267-6192}, year = {2009}, abstract = {Many of today's distributed computing systems in the field do not Support the migration of execution entities among computing nodes (luring runtime. The relatively static association between units of processing and computing nodes makes it difficult to implement fault-tolerant behavior or load-balancing schemes. The concept of code migration may provide a solution to the above-mentioned problems. it can be defined as the movement of processes, objects, or components from one computing node to another during system runtime in a distributed environment. With the advent of the virtual machine-based NET framework, many of the cross-language heterogeneity issues have been resolved. With the commercial implementation, the shared source "Rotor", and the open-source "Mono" implementation on hand, we have focused on cross-operating system heterogeneity issues and present interoperability and migration schemes for applications distributed over different operating systems (namely Linux and Windows 2000) as well as various NET implementations. Within this paper, we describe the integration of a migration facility with the hell) of Aspect- Oriented Programming (AOP) into the NET framework. AOP is interesting as it addresses non-functional system properties on the middleware level, without the need to manipulate lower system layers like the operating system itself. Most features required to implement object or process migration (such as reflection mechanisms or a machine-independent executable format) are already present in the NET frameworks, so the integration of such a concept is a natural extension of the system capabilities. We have implemented several proof-of-concept applications for different use case scenarios. The paper contains an experimental evaluation of the performance impact of object migration in context of those applications.}, language = {en} } @misc{TrappDoellner2019, author = {Trapp, Matthias and D{\"o}llner, J{\"u}rgen Roland Friedrich}, title = {Interactive Close-Up Rendering for Detail plus Overview Visualization of 3D Digital Terrain Models}, series = {2019 23rd International Conference Information Visualisation (IV)}, journal = {2019 23rd International Conference Information Visualisation (IV)}, editor = {Banissi, E Ursyn}, publisher = {Inst. of Electr. and Electronics Engineers}, address = {Los Alamitos}, isbn = {978-1-7281-2838-2}, issn = {2375-0138}, doi = {10.1109/IV.2019.00053}, pages = {275 -- 280}, year = {2019}, abstract = {This paper presents an interactive rendering technique for detail+overview visualization of 3D digital terrain models using interactive close-ups. A close-up is an alternative presentation of input data varying with respect to geometrical scale, mapping, appearance, as well as Level-of-Detail (LOD) and Level-of-Abstraction (LOA) used. The presented 3D close-up approach enables in-situ comparison of multiple Regionof-Interests (ROIs) simultaneously. We describe a GPU-based rendering technique for the image-synthesis of multiple close-ups in real-time.}, language = {en} } @misc{TrappDoellner2019, author = {Trapp, Matthias and D{\"o}llner, J{\"u}rgen Roland Friedrich}, title = {Real-time Screen-space Geometry Draping for 3D Digital Terrain Models}, series = {2019 23rd International Conference Information Visualisation (IV)}, journal = {2019 23rd International Conference Information Visualisation (IV)}, publisher = {Inst. of Electr. and Electronics Engineers}, address = {Los Alamitos}, isbn = {978-1-7281-2838-2}, issn = {2375-0138}, doi = {10.1109/IV.2019.00054}, pages = {281 -- 286}, year = {2019}, abstract = {A fundamental task in 3D geovisualization and GIS applications is the visualization of vector data that can represent features such as transportation networks or land use coverage. Mapping or draping vector data represented by geometric primitives (e.g., polylines or polygons) to 3D digital elevation or 3D digital terrain models is a challenging task. We present an interactive GPU-based approach that performs geometry-based draping of vector data on per-frame basis using an image-based representation of a 3D digital elevation or terrain model only.}, language = {en} } @phdthesis{Trapp2013, author = {Trapp, Matthias}, title = {Interactive rendering techniques for focus+context visualization of 3D geovirtual environments}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-66824}, school = {Universit{\"a}t Potsdam}, year = {2013}, abstract = {This thesis introduces a collection of new real-time rendering techniques and applications for focus+context visualization of interactive 3D geovirtual environments such as virtual 3D city and landscape models. These environments are generally characterized by a large number of objects and are of high complexity with respect to geometry and textures. For these reasons, their interactive 3D rendering represents a major challenge. Their 3D depiction implies a number of weaknesses such as occlusions, cluttered image contents, and partial screen-space usage. To overcome these limitations and, thus, to facilitate the effective communication of geo-information, principles of focus+context visualization can be used for the design of real-time 3D rendering techniques for 3D geovirtual environments (see Figure). In general, detailed views of a 3D geovirtual environment are combined seamlessly with abstracted views of the context within a single image. To perform the real-time image synthesis required for interactive visualization, dedicated parallel processors (GPUs) for rasterization of computer graphics primitives are used. For this purpose, the design and implementation of appropriate data structures and rendering pipelines are necessary. The contribution of this work comprises the following five real-time rendering methods: • The rendering technique for 3D generalization lenses enables the combination of different 3D city geometries (e.g., generalized versions of a 3D city model) in a single image in real time. The method is based on a generalized and fragment-precise clipping approach, which uses a compressible, raster-based data structure. It enables the combination of detailed views in the focus area with the representation of abstracted variants in the context area. • The rendering technique for the interactive visualization of dynamic raster data in 3D geovirtual environments facilitates the rendering of 2D surface lenses. It enables a flexible combination of different raster layers (e.g., aerial images or videos) using projective texturing for decoupling image and geometry data. Thus, various overlapping and nested 2D surface lenses of different contents can be visualized interactively. • The interactive rendering technique for image-based deformation of 3D geovirtual environments enables the real-time image synthesis of non-planar projections, such as cylindrical and spherical projections, as well as multi-focal 3D fisheye-lenses and the combination of planar and non-planar projections. • The rendering technique for view-dependent multi-perspective views of 3D geovirtual environments, based on the application of global deformations to the 3D scene geometry, can be used for synthesizing interactive panorama maps to combine detailed views close to the camera (focus) with abstract views in the background (context). This approach reduces occlusions, increases the usage the available screen space, and reduces the overload of image contents. • The object-based and image-based rendering techniques for highlighting objects and focus areas inside and outside the view frustum facilitate preattentive perception. The concepts and implementations of interactive image synthesis for focus+context visualization and their selected applications enable a more effective communication of spatial information, and provide building blocks for design and development of new applications and systems in the field of 3D geovirtual environments.}, language = {en} } @article{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} } @misc{TorkuraSukmanaChengetal.2017, author = {Torkura, Kennedy A. and Sukmana, Muhammad Ihsan Haikal and Cheng, Feng and Meinel, Christoph}, title = {Leveraging cloud native design patterns for security-as-a-service applications}, series = {IEEE International Conference on Smart Cloud (SmartCloud)}, journal = {IEEE International Conference on Smart Cloud (SmartCloud)}, publisher = {Institute of Electrical and Electronics Engineers}, address = {New York}, isbn = {978-1-5386-3684-8}, doi = {10.1109/SmartCloud.2017.21}, pages = {90 -- 97}, year = {2017}, abstract = {This paper discusses a new approach for designing and deploying Security-as-a-Service (SecaaS) applications using cloud native design patterns. Current SecaaS approaches do not efficiently handle the increasing threats to computer systems and applications. For example, requests for security assessments drastically increase after a high-risk security vulnerability is disclosed. In such scenarios, SecaaS applications are unable to dynamically scale to serve requests. A root cause of this challenge is employment of architectures not specifically fitted to cloud environments. Cloud native design patterns resolve this challenge by enabling certain properties e.g. massive scalability and resiliency via the combination of microservice patterns and cloud-focused design patterns. However adopting these patterns is a complex process, during which several security issues are introduced. In this work, we investigate these security issues, we redesign and deploy a monolithic SecaaS application using cloud native design patterns while considering appropriate, layered security counter-measures i.e. at the application and cloud networking layer. Our prototype implementation out-performs traditional, monolithic applications with an average Scanner Time of 6 minutes, without compromising security. Our approach can be employed for designing secure, scalable and performant SecaaS applications that effectively handle unexpected increase in security assessment requests.}, language = {en} } @phdthesis{Tinnefeld2014, author = {Tinnefeld, Christian}, title = {Building a columnar database on shared main memory-based storage}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-72063}, school = {Universit{\"a}t Potsdam}, pages = {175}, year = {2014}, abstract = {In the field of disk-based parallel database management systems exists a great variety of solutions based on a shared-storage or a shared-nothing architecture. In contrast, main memory-based parallel database management systems are dominated solely by the shared-nothing approach as it preserves the in-memory performance advantage by processing data locally on each server. We argue that this unilateral development is going to cease due to the combination of the following three trends: a) Nowadays network technology features remote direct memory access (RDMA) and narrows the performance gap between accessing main memory inside a server and of a remote server to and even below a single order of magnitude. b) Modern storage systems scale gracefully, are elastic, and provide high-availability. c) A modern storage system such as Stanford's RAMCloud even keeps all data resident in main memory. Exploiting these characteristics in the context of a main-memory parallel database management system is desirable. The advent of RDMA-enabled network technology makes the creation of a parallel main memory DBMS based on a shared-storage approach feasible. This thesis describes building a columnar database on shared main memory-based storage. The thesis discusses the resulting architecture (Part I), the implications on query processing (Part II), and presents an evaluation of the resulting solution in terms of performance, high-availability, and elasticity (Part III). In our architecture, we use Stanford's RAMCloud as shared-storage, and the self-designed and developed in-memory AnalyticsDB as relational query processor on top. AnalyticsDB encapsulates data access and operator execution via an interface which allows seamless switching between local and remote main memory, while RAMCloud provides not only storage capacity, but also processing power. Combining both aspects allows pushing-down the execution of database operators into the storage system. We describe how the columnar data processed by AnalyticsDB is mapped to RAMCloud's key-value data model and how the performance advantages of columnar data storage can be preserved. The combination of fast network technology and the possibility to execute database operators in the storage system opens the discussion for site selection. We construct a system model that allows the estimation of operator execution costs in terms of network transfer, data processed in memory, and wall time. This can be used for database operators that work on one relation at a time - such as a scan or materialize operation - to discuss the site selection problem (data pull vs. operator push). Since a database query translates to the execution of several database operators, it is possible that the optimal site selection varies per operator. For the execution of a database operator that works on two (or more) relations at a time, such as a join, the system model is enriched by additional factors such as the chosen algorithm (e.g. Grace- vs. Distributed Block Nested Loop Join vs. Cyclo-Join), the data partitioning of the respective relations, and their overlapping as well as the allowed resource allocation. We present an evaluation on a cluster with 60 nodes where all nodes are connected via RDMA-enabled network equipment. We show that query processing performance is about 2.4x slower if everything is done via the data pull operator execution strategy (i.e. RAMCloud is being used only for data access) and about 27\% slower if operator execution is also supported inside RAMCloud (in comparison to operating only on main memory inside a server without any network communication at all). The fast-crash recovery feature of RAMCloud can be leveraged to provide high-availability, e.g. a server crash during query execution only delays the query response for about one second. Our solution is elastic in a way that it can adapt to changing workloads a) within seconds, b) without interruption of the ongoing query processing, and c) without manual intervention.}, language = {en} } @book{TietzPelchenMeineletal.2017, author = {Tietz, Christian and Pelchen, Chris and Meinel, Christoph and Schnjakin, Maxim}, title = {Management Digitaler Identit{\"a}ten}, number = {114}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-395-4}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-103164}, publisher = {Universit{\"a}t Potsdam}, pages = {65}, year = {2017}, abstract = {Um den zunehmenden Diebstahl digitaler Identit{\"a}ten zu bek{\"a}mpfen, gibt es bereits mehr als ein Dutzend Technologien. Sie sind, vor allem bei der Authentifizierung per Passwort, mit spezifischen Nachteilen behaftet, haben andererseits aber auch jeweils besondere Vorteile. Wie solche Kommunikationsstandards und -Protokolle wirkungsvoll miteinander kombiniert werden k{\"o}nnen, um dadurch mehr Sicherheit zu erreichen, haben die Autoren dieser Studie analysiert. Sie sprechen sich f{\"u}r neuartige Identit{\"a}tsmanagement-Systeme aus, die sich flexibel auf verschiedene Rollen eines einzelnen Nutzers einstellen k{\"o}nnen und bequemer zu nutzen sind als bisherige Verfahren. Als ersten Schritt auf dem Weg hin zu einer solchen Identit{\"a}tsmanagement-Plattform beschreiben sie die M{\"o}glichkeiten einer Analyse, die sich auf das individuelle Verhalten eines Nutzers oder einer Sache st{\"u}tzt. Ausgewertet werden dabei Sensordaten mobiler Ger{\"a}te, welche die Nutzer h{\"a}ufig bei sich tragen und umfassend einsetzen, also z.B. internetf{\"a}hige Mobiltelefone, Fitness-Tracker und Smart Watches. Die Wissenschaftler beschreiben, wie solche Kleincomputer allein z.B. anhand der Analyse von Bewegungsmustern, Positionsund Netzverbindungsdaten kontinuierlich ein „Vertrauens-Niveau" errechnen k{\"o}nnen. Mit diesem ermittelten „Trust Level" kann jedes Ger{\"a}t st{\"a}ndig die Wahrscheinlichkeit angeben, mit der sein aktueller Benutzer auch der tats{\"a}chliche Besitzer ist, dessen typische Verhaltensmuster es genauestens „kennt". Wenn der aktuelle Wert des Vertrauens-Niveaus (nicht aber die biometrischen Einzeldaten) an eine externe Instanz wie einen Identit{\"a}tsprovider {\"u}bermittelt wird, kann dieser das Trust Level allen Diensten bereitstellen, welche der Anwender nutzt und dar{\"u}ber informieren will. Jeder Dienst ist in der Lage, selbst festzulegen, von welchem Vertrauens-Niveau an er einen Nutzer als authentifiziert ansieht. Erf{\"a}hrt er von einem unter das Limit gesunkenen Trust Level, kann der Identit{\"a}tsprovider seine Nutzung und die anderer Services verweigern. Die besonderen Vorteile dieses Identit{\"a}tsmanagement-Ansatzes liegen darin, dass er keine spezifische und teure Hardware ben{\"o}tigt, um spezifische Daten auszuwerten, sondern lediglich Smartphones und so genannte Wearables. Selbst Dinge wie Maschinen, die Daten {\"u}ber ihr eigenes Verhalten per Sensor-Chip ins Internet funken, k{\"o}nnen einbezogen werden. Die Daten werden kontinuierlich im Hintergrund erhoben, ohne dass sich jemand darum k{\"u}mmern muss. Sie sind nur f{\"u}r die Berechnung eines Wahrscheinlichkeits-Messwerts von Belang und verlassen niemals das Ger{\"a}t. Meldet sich ein Internetnutzer bei einem Dienst an, muss er sich nicht zun{\"a}chst an ein vorher festgelegtes Geheimnis - z.B. ein Passwort - erinnern, sondern braucht nur die Weitergabe seines aktuellen Vertrauens-Wertes mit einem „OK" freizugeben. {\"A}ndert sich das Nutzungsverhalten - etwa durch andere Bewegungen oder andere Orte des Einloggens ins Internet als die {\"u}blichen - wird dies schnell erkannt. Unbefugten kann dann sofort der Zugang zum Smartphone oder zu Internetdiensten gesperrt werden. K{\"u}nftig kann die Auswertung von Verhaltens-Faktoren noch erweitert werden, indem z.B. Routinen an Werktagen, an Wochenenden oder im Urlaub erfasst werden. Der Vergleich mit den live erhobenen Daten zeigt dann an, ob das Verhalten in das {\"u}bliche Muster passt, der Benutzer also mit h{\"o}chster Wahrscheinlichkeit auch der ausgewiesene Besitzer des Ger{\"a}ts ist. {\"U}ber die Techniken des Managements digitaler Identit{\"a}ten und die damit verbundenen Herausforderungen gibt diese Studie einen umfassenden {\"U}berblick. Sie beschreibt zun{\"a}chst, welche Arten von Angriffen es gibt, durch die digitale Identit{\"a}ten gestohlen werden k{\"o}nnen. Sodann werden die unterschiedlichen Verfahren von Identit{\"a}tsnachweisen vorgestellt. Schließlich liefert die Studie noch eine zusammenfassende {\"U}bersicht {\"u}ber die 15 wichtigsten Protokolle und technischen Standards f{\"u}r die Kommunikation zwischen den drei beteiligten Akteuren: Service Provider/Dienstanbieter, Identit{\"a}tsprovider und Nutzer. Abschließend wird aktuelle Forschung des Hasso-Plattner-Instituts zum Identit{\"a}tsmanagement vorgestellt.}, language = {de} } @article{ThamsenBeilharzVinhThuyTranetal.2020, author = {Thamsen, Lauritz and Beilharz, Jossekin Jakob and Vinh Thuy Tran, and Nedelkoski, Sasho and Kao, Odej}, title = {Mary, Hugo, and Hugo*}, series = {Concurrency and computation : practice \& experience}, volume = {33}, journal = {Concurrency and computation : practice \& experience}, number = {18}, publisher = {Wiley}, address = {Hoboken}, issn = {1532-0626}, doi = {10.1002/cpe.5823}, pages = {12}, year = {2020}, abstract = {Distributed data-parallel processing systems like MapReduce, Spark, and Flink are popular for analyzing large datasets using cluster resources. Resource management systems like YARN or Mesos in turn allow multiple data-parallel processing jobs to share cluster resources in temporary containers. Often, the containers do not isolate resource usage to achieve high degrees of overall resource utilization despite overprovisioning and the often fluctuating utilization of specific jobs. However, some combinations of jobs utilize resources better and interfere less with each other when running on the same shared nodes than others. This article presents an approach for improving the resource utilization and job throughput when scheduling recurring distributed data-parallel processing jobs in shared clusters. The approach is based on reinforcement learning and a measure of co-location goodness to have cluster schedulers learn over time which jobs are best executed together on shared resources. We evaluated this approach over the last years with three prototype schedulers that build on each other: Mary, Hugo, and Hugo*. For the evaluation we used exemplary Flink and Spark jobs from different application domains and clusters of commodity nodes managed by YARN. The results of these experiments show that our approach can increase resource utilization and job throughput significantly.}, language = {en} } @book{TessenowFelgentreffBrachaetal.2016, author = {Tessenow, Philipp and Felgentreff, Tim and Bracha, Gilad and Hirschfeld, Robert}, title = {Extending a dynamic programming language and runtime environment with access control}, number = {107}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-373-2}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-92560}, publisher = {Universit{\"a}t Potsdam}, pages = {83}, year = {2016}, abstract = {Complexity in software systems is a major factor driving development and maintenance costs. To master this complexity, software is divided into modules that can be developed and tested separately. In order to support this separation of modules, each module should provide a clean and concise public interface. Therefore, the ability to selectively hide functionality using access control is an important feature in a programming language intended for complex software systems. Software systems are increasingly distributed, adding not only to their inherent complexity, but also presenting security challenges. The object-capability approach addresses these challenges by defining language properties providing only minimal capabilities to objects. One programming language that is based on the object-capability approach is Newspeak, a dynamic programming language designed for modularity and security. The Newspeak specification describes access control as one of Newspeak's properties, because it is a requirement for the object-capability approach. However, access control, as defined in the Newspeak specification, is currently not enforced in its implementation. This work introduces an access control implementation for Newspeak, enabling the security of object-capabilities and enhancing modularity. We describe our implementation of access control for Newspeak. We adapted the runtime environment, the reflective system, the compiler toolchain, and the virtual machine. Finally, we describe a migration strategy for the existing Newspeak code base, so that our access control implementation can be integrated with minimal effort.}, language = {en} } @misc{TangNakamotoSternetal.2022, author = {Tang, Mitchell and Nakamoto, Carter H. and Stern, Ariel Dora and Mehrotra, Ateev}, title = {Trends in remote patient monitoring use in traditional medicare}, series = {JAMA internal medicine}, volume = {182}, journal = {JAMA internal medicine}, number = {9}, publisher = {American Medical Association}, address = {Chicago, Ill.}, issn = {2168-6106}, doi = {10.1001/jamainternmed.2022.3043}, pages = {1005 -- 1006}, year = {2022}, language = {en} } @article{TalebRohrerBergneretal.2022, author = {Taleb, Aiham and Rohrer, Csaba and Bergner, Benjamin and De Leon, Guilherme and Rodrigues, Jonas Almeida and Schwendicke, Falk and Lippert, Christoph and Krois, Joachim}, title = {Self-supervised learning methods for label-efficient dental caries classification}, series = {Diagnostics : open access journal}, volume = {12}, journal = {Diagnostics : open access journal}, number = {5}, publisher = {MDPI}, address = {Basel}, issn = {2075-4418}, doi = {10.3390/diagnostics12051237}, pages = {15}, year = {2022}, abstract = {High annotation costs are a substantial bottleneck in applying deep learning architectures to clinically relevant use cases, substantiating the need for algorithms to learn from unlabeled data. In this work, we propose employing self-supervised methods. To that end, we trained with three self-supervised algorithms on a large corpus of unlabeled dental images, which contained 38K bitewing radiographs (BWRs). We then applied the learned neural network representations on tooth-level dental caries classification, for which we utilized labels extracted from electronic health records (EHRs). Finally, a holdout test-set was established, which consisted of 343 BWRs and was annotated by three dental professionals and approved by a senior dentist. This test-set was used to evaluate the fine-tuned caries classification models. Our experimental results demonstrate the obtained gains by pretraining models using self-supervised algorithms. These include improved caries classification performance (6 p.p. increase in sensitivity) and, most importantly, improved label-efficiency. In other words, the resulting models can be fine-tuned using few labels (annotations). Our results show that using as few as 18 annotations can produce >= 45\% sensitivity, which is comparable to human-level diagnostic performance. This study shows that self-supervision can provide gains in medical image analysis, particularly when obtaining labels is costly and expensive.}, language = {en} } @article{TakounaSachsMeinel2014, author = {Takouna, Ibrahim and Sachs, Kai and Meinel, Christoph}, title = {Multiperiod robust optimization for proactive resource provisioning in virtualized data centers}, series = {The journal of supercomputing : an internat. journal of supercomputer design, analysis and use}, volume = {70}, journal = {The journal of supercomputing : an internat. journal of supercomputer design, analysis and use}, number = {3}, publisher = {Springer}, address = {Dordrecht}, issn = {0920-8542}, doi = {10.1007/s11227-014-1246-2}, pages = {1514 -- 1536}, year = {2014}, language = {en} } @phdthesis{Takouna2014, author = {Takouna, Ibrahim}, title = {Energy-efficient and performance-aware virtual machine management for cloud data centers}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-72399}, school = {Universit{\"a}t Potsdam}, year = {2014}, abstract = {Virtualisierte Cloud Datenzentren stellen nach Bedarf Ressourcen zur Verf{\"u}gu-ng, erm{\"o}glichen agile Ressourcenbereitstellung und beherbergen heterogene Applikationen mit verschiedenen Anforderungen an Ressourcen. Solche Datenzentren verbrauchen enorme Mengen an Energie, was die Erh{\"o}hung der Betriebskosten, der W{\"a}rme innerhalb der Zentren und des Kohlendioxidausstoßes verursacht. Der Anstieg des Energieverbrauches kann durch ein ineffektives Ressourcenmanagement, das die ineffiziente Ressourcenausnutzung verursacht, entstehen. Die vorliegende Dissertation stellt detaillierte Modelle und neue Verfahren f{\"u}r virtualisiertes Ressourcenmanagement in Cloud Datenzentren vor. Die vorgestellten Verfahren ziehen das Service-Level-Agreement (SLA) und die Heterogenit{\"a}t der Auslastung bez{\"u}glich des Bedarfs an Speicherzugriffen und Kommunikationsmustern von Web- und HPC- (High Performance Computing) Applikationen in Betracht. Um die pr{\"a}sentierten Techniken zu evaluieren, verwenden wir Simulationen und echte Protokollierung der Auslastungen von Web- und HPC- Applikationen. Außerdem vergleichen wir unser Techniken und Verfahren mit anderen aktuellen Verfahren durch die Anwendung von verschiedenen Performance Metriken. Die Hauptbeitr{\"a}ge dieser Dissertation sind Folgendes: Ein Proaktives auf robuster Optimierung basierendes Ressourcenbereitstellungsverfahren. Dieses Verfahren erh{\"o}ht die F{\"a}higkeit der Hostes zur Verf{\"u}g-ungsstellung von mehr VMs. Gleichzeitig aber wird der unn{\"o}tige Energieverbrauch minimiert. Zus{\"a}tzlich mindert diese Technik unerw{\"u}nschte {\"A}nde-rungen im Energiezustand des Servers. Die vorgestellte Technik nutzt einen auf Intervall basierenden Vorhersagealgorithmus zur Implementierung einer robusten Optimierung. Dabei werden unsichere Anforderungen in Betracht gezogen. Ein adaptives und auf Intervall basierendes Verfahren zur Vorhersage des Arbeitsaufkommens mit hohen, in k{\"u}rzer Zeit auftretenden Schwankungen. Die Intervall basierende Vorhersage ist implementiert in der Standard Abweichung Variante und in der Median absoluter Abweichung Variante. Die Intervall-{\"A}nderungen basieren auf einem adaptiven Vertrauensfenster um die Schwankungen des Arbeitsaufkommens zu bew{\"a}ltigen. Eine robuste VM Zusammenlegung f{\"u}r ein effizientes Energie und Performance Management. Dies erm{\"o}glicht die gegenseitige Abh{\"a}ngigkeit zwischen der Energie und der Performance zu minimieren. Unser Verfahren reduziert die Anzahl der VM-Migrationen im Vergleich mit den neu vor kurzem vorgestellten Verfahren. Dies tr{\"a}gt auch zur Reduzierung des durch das Netzwerk verursachten Energieverbrauches. Außerdem reduziert dieses Verfahren SLA-Verletzungen und die Anzahl von {\"A}nderungen an Energiezus-t{\"a}nden. Ein generisches Modell f{\"u}r das Netzwerk eines Datenzentrums um die verz{\"o}-gerte Kommunikation und ihre Auswirkung auf die VM Performance und auf die Netzwerkenergie zu simulieren. Außerdem wird ein generisches Modell f{\"u}r ein Memory-Bus des Servers vorgestellt. Dieses Modell beinhaltet auch Modelle f{\"u}r die Latenzzeit und den Energieverbrauch f{\"u}r verschiedene Memory Frequenzen. Dies erlaubt eine Simulation der Memory Verz{\"o}gerung und ihre Auswirkung auf die VM-Performance und auf den Memory Energieverbrauch. Kommunikation bewusste und Energie effiziente Zusammenlegung f{\"u}r parallele Applikationen um die dynamische Entdeckung von Kommunikationsmustern und das Umplanen von VMs zu erm{\"o}glichen. Das Umplanen von VMs benutzt eine auf den entdeckten Kommunikationsmustern basierende Migration. Eine neue Technik zur Entdeckung von dynamischen Mustern ist implementiert. Sie basiert auf der Signal Verarbeitung des Netzwerks von VMs, anstatt die Informationen des virtuellen Umstellung der Hosts oder der Initiierung der VMs zu nutzen. Das Ergebnis zeigt, dass unsere Methode die durchschnittliche Anwendung des Netzwerks reduziert und aufgrund der Reduzierung der aktiven Umstellungen Energie gespart. Außerdem bietet sie eine bessere VM Performance im Vergleich zu der CPU-basierten Platzierung. Memory bewusste VM Zusammenlegung f{\"u}r unabh{\"a}ngige VMs. Sie nutzt die Vielfalt des VMs Memory Zuganges um die Anwendung vom Memory-Bus der Hosts zu balancieren. Die vorgestellte Technik, Memory-Bus Load Balancing (MLB), verteilt die VMs reaktiv neu im Bezug auf ihre Anwendung vom Memory-Bus. Sie nutzt die VM Migration um die Performance des gesamtem Systems zu verbessern. Außerdem sind die dynamische Spannung, die Frequenz Skalierung des Memory und die MLB Methode kombiniert um ein besseres Energiesparen zu leisten.}, language = {en} } @inproceedings{SurajbaliGraceCoulson2010, author = {Surajbali, Bholanathsingh and Grace, Paul and Coulson, Geoff}, title = {Preserving dynamic reconfiguration consistency in aspect oriented middleware}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-41379}, year = {2010}, abstract = {Aspect-oriented middleware is a promising technology for the realisation of dynamic reconfiguration in heterogeneous distributed systems. However, like other dynamic reconfiguration approaches, AO-middleware-based reconfiguration requires that the consistency of the system is maintained across reconfigurations. AO-middleware-based reconfiguration is an ongoing research topic and several consistency approaches have been proposed. However, most of these approaches tend to be targeted at specific contexts, whereas for distributed systems it is crucial to cover a wide range of operating conditions. In this paper we propose an approach that offers distributed, dynamic reconfiguration in a consistent manner, and features a flexible framework-based consistency management approach to cover a wide range of operating conditions. We evaluate our approach by investigating the configurability and transparency of our approach and also quantify the performance overheads of the associated consistency mechanisms.}, language = {en} } @misc{SukmanaTorkuraGraupneretal.2019, author = {Sukmana, Muhammad Ihsan Haikal and Torkura, Kennedy A. and Graupner, Hendrik and Cheng, Feng and Meinel, Christoph}, title = {Unified Cloud Access Control Model for Cloud Storage Broker}, series = {33rd International Conference on Information Networking (ICOIN 2019)}, journal = {33rd International Conference on Information Networking (ICOIN 2019)}, publisher = {IEEE}, address = {Los Alamitos}, isbn = {978-1-5386-8350-7}, issn = {1976-7684}, doi = {10.1109/ICOIN.2019.8717982}, pages = {60 -- 65}, year = {2019}, abstract = {Cloud Storage Broker (CSB) provides value-added cloud storage service for enterprise usage by leveraging multi-cloud storage architecture. However, it raises several challenges for managing resources and its access control in multiple Cloud Service Providers (CSPs) for authorized CSB stakeholders. In this paper we propose unified cloud access control model that provides the abstraction of CSP's services for centralized and automated cloud resource and access control management in multiple CSPs. Our proposal offers role-based access control for CSB stakeholders to access cloud resources by assigning necessary privileges and access control list for cloud resources and CSB stakeholders, respectively, following privilege separation concept and least privilege principle. We implement our unified model in a CSB system called CloudRAID for Business (CfB) with the evaluation result shows it provides system-and-cloud level security service for cfB and centralized resource and access control management in multiple CSPs.}, language = {en} } @misc{StojanovicTrappRichteretal.2018, author = {Stojanovic, Vladeta and Trapp, Matthias and Richter, Rico and D{\"o}llner, J{\"u}rgen Roland Friedrich}, title = {A service-oriented approach for classifying 3D points clouds by example of office furniture classification}, series = {Web3D 2018: Proceedings of the 23rd International ACM Conference on 3D Web Technology}, journal = {Web3D 2018: Proceedings of the 23rd International ACM Conference on 3D Web Technology}, publisher = {Association for Computing Machinery}, address = {New York}, isbn = {978-1-4503-5800-2}, doi = {10.1145/3208806.3208810}, pages = {1 -- 9}, year = {2018}, abstract = {The rapid digitalization of the Facility Management (FM) sector has increased the demand for mobile, interactive analytics approaches concerning the operational state of a building. These approaches provide the key to increasing stakeholder engagement associated with Operation and Maintenance (O\&M) procedures of living and working areas, buildings, and other built environment spaces. We present a generic and fast approach to process and analyze given 3D point clouds of typical indoor office spaces to create corresponding up-to-date approximations of classified segments and object-based 3D models that can be used to analyze, record and highlight changes of spatial configurations. The approach is based on machine-learning methods used to classify the scanned 3D point cloud data using 2D images. This approach can be used to primarily track changes of objects over time for comparison, allowing for routine classification, and presentation of results used for decision making. We specifically focus on classification, segmentation, and reconstruction of multiple different object types in a 3D point-cloud scene. We present our current research and describe the implementation of these technologies as a web-based application using a services-oriented methodology.}, 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} } @article{SteinertThamsenFelgentreffetal.2015, author = {Steinert, Bastian and Thamsen, Lauritz and Felgentreff, Tim and Hirschfeld, Robert}, title = {Object Versioning to Support Recovery Needs Using Proxies to Preserve Previous Development States in Lively}, series = {ACM SIGPLAN notices}, volume = {50}, journal = {ACM SIGPLAN notices}, number = {2}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {0362-1340}, doi = {10.1145/2661088.2661093}, pages = {113 -- 124}, year = {2015}, abstract = {We present object versioning as a generic approach to preserve access to previous development and application states. Version-aware references can manage the modifications made to the target object and record versions as desired. Such references can be provided without modifications to the virtual machine. We used proxies to implement the proposed concepts and demonstrate the Lively Kernel running on top of this object versioning layer. This enables Lively users to undo the effects of direct manipulation and other programming actions.}, 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} } @misc{StaubitzWilkinsHagedornetal.2017, author = {Staubitz, Thomas and Wilkins, Christian and Hagedorn, Christiane and Meinel, Christoph}, title = {The Gamification of a MOOC Platform}, series = {Proceedings of 2017 IEEE Global Engineering Education Conference (EDUCON)}, journal = {Proceedings of 2017 IEEE Global Engineering Education Conference (EDUCON)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5090-5467-1}, issn = {2165-9567}, doi = {10.1109/EDUCON.2017.7942952}, pages = {883 -- 892}, year = {2017}, abstract = {Massive Open Online Courses (MOOCs) have left their mark on the face of education during the recent years. At the Hasso Plattner Institute (HPI) in Potsdam, Germany, we are actively developing a MOOC platform, which provides our research with a plethora of e-learning topics, such as learning analytics, automated assessment, peer assessment, team-work, online proctoring, and gamification. We run several instances of this platform. On openHPI, we provide our own courses from within the HPI context. Further instances are openSAP, openWHO, and mooc.HOUSE, which is the smallest of these platforms, targeting customers with a less extensive course portfolio. In 2013, we started to work on the gamification of our platform. By now, we have implemented about two thirds of the features that we initially have evaluated as useful for our purposes. About a year ago we activated the implemented gamification features on mooc.HOUSE. Before activating the features on openHPI as well, we examined, and re-evaluated our initial considerations based on the data we collected so far and the changes in other contexts of our platforms.}, language = {en} } @book{SmirnovZamaniFarahaniWeske2011, author = {Smirnov, Sergey and Zamani Farahani, Armin and Weske, Mathias}, title = {State propagation in abstracted business processes}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-130-1}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-51480}, publisher = {Universit{\"a}t Potsdam}, pages = {16}, year = {2011}, abstract = {Business process models are abstractions of concrete operational procedures that occur in the daily business of organizations. To cope with the complexity of these models, business process model abstraction has been introduced recently. Its goal is to derive from a detailed process model several abstract models that provide a high-level understanding of the process. While techniques for constructing abstract models are reported in the literature, little is known about the relationships between process instances and abstract models. In this paper we show how the state of an abstract activity can be calculated from the states of related, detailed process activities as they happen. The approach uses activity state propagation. With state uniqueness and state transition correctness we introduce formal properties that improve the understanding of state propagation. Algorithms to check these properties are devised. Finally, we use behavioral profiles to identify and classify behavioral inconsistencies in abstract process models that might occur, once activity state propagation is used.}, 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{SmirnovReijersNugterenetal.2010, author = {Smirnov, Sergey and Reijers, Hajo A. and Nugteren, Thijs and Weske, Mathias}, title = {Business process model abstraction : theory and practice}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-054-0}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-41782}, publisher = {Universit{\"a}t Potsdam}, pages = {17}, year = {2010}, abstract = {Business process management aims at capturing, understanding, and improving work in organizations. The central artifacts are process models, which serve different purposes. Detailed process models are used to analyze concrete working procedures, while high-level models show, for instance, handovers between departments. To provide different views on process models, business process model abstraction has emerged. While several approaches have been proposed, a number of abstraction use case that are both relevant for industry and scientifically challenging are yet to be addressed. In this paper we systematically develop, classify, and consolidate different use cases for business process model abstraction. The reported work is based on a study with BPM users in the health insurance sector and validated with a BPM consultancy company and a large BPM vendor. The identified fifteen abstraction use cases reflect the industry demand. The related work on business process model abstraction is evaluated against the use cases, which leads to a research agenda.}, language = {en} } @phdthesis{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} } @article{SinnGieseStuiveretal.2022, author = {Sinn, Ludwig R. and Giese, Sven Hans-Joachim and Stuiver, Marchel and Rappsilber, Juri}, title = {Leveraging parameter dependencies in high-field asymmetric waveform ion-mobility spectrometry and size exclusion chromatography for proteome-wide cross-linking mass spectrometry}, series = {Analytical chemistry : the authoritative voice of the analytical community}, volume = {94}, journal = {Analytical chemistry : the authoritative voice of the analytical community}, number = {11}, publisher = {American Chemical Society}, address = {Columbus, Ohio}, issn = {0003-2700}, doi = {10.1021/acs.analchem.1c04373}, pages = {4627 -- 4634}, year = {2022}, abstract = {Ion-mobility spectrometry shows great promise to tackle analytically challenging research questions by adding another separation dimension to liquid chromatography-mass spectrometry. The understanding of how analyte properties influence ion mobility has increased through recent studies, but no clear rationale for the design of customized experimental settings has emerged. Here, we leverage machine learning to deepen our understanding of field asymmetric waveform ion-mobility spectrometry for the analysis of cross-linked peptides. Knowing that predominantly m/z and then the size and charge state of an analyte influence the separation, we found ideal compensation voltages correlating with the size exclusion chromatography fraction number. The effect of this relationship on the analytical depth can be substantial as exploiting it allowed us to almost double unique residue pair detections in a proteome-wide cross-linking experiment. Other applications involving liquid- and gas-phase separation may also benefit from considering such parameter dependencies.}, language = {en} } @article{SigelSwartzGoldenetal.2020, author = {Sigel, Keith Magnus and Swartz, Talia H. and Golden, Eddye and Paranjpe, Ishan and Somani, Sulaiman and Richter, Felix and De Freitas, Jessica K. and Miotto, Riccardo and Zhao, Shan and Polak, Paz and Mutetwa, Tinaye and Factor, Stephanie and Mehandru, Saurabh and Mullen, Michael and Cossarini, Francesca and B{\"o}ttinger, Erwin and Fayad, Zahi and Merad, Miriam and Gnjatic, Sacha and Aberg, Judith and Charney, Alexander and Nadkarni, Girish and Glicksberg, Benjamin S.}, title = {Coronavirus 2019 and people living with human immunodeficiency virus}, series = {Clinical infectious diseases : electronic edition}, volume = {71}, journal = {Clinical infectious diseases : electronic edition}, number = {11}, publisher = {Oxford Univ. Press}, address = {Cary, NC}, issn = {1058-4838}, doi = {10.1093/cid/ciaa880}, pages = {2933 -- 2938}, year = {2020}, abstract = {Background: There are limited data regarding the clinical impact of coronavirus disease 2019 (COVID-19) on people living with human immunodeficiency virus (PLWH). In this study, we compared outcomes for PLWH with COVID-19 to a matched comparison group. Methods: We identified 88 PLWH hospitalized with laboratory-confirmed COVID-19 in our hospital system in New York City between 12 March and 23 April 2020. We collected data on baseline clinical characteristics, laboratory values, HIV status, treatment, and outcomes from this group and matched comparators (1 PLWH to up to 5 patients by age, sex, race/ethnicity, and calendar week of infection). We compared clinical characteristics and outcomes (death, mechanical ventilation, hospital discharge) for these groups, as well as cumulative incidence of death by HIV status. Results: Patients did not differ significantly by HIV status by age, sex, or race/ethnicity due to the matching algorithm. PLWH hospitalized with COVID-19 had high proportions of HIV virologic control on antiretroviral therapy. PLWH had greater proportions of smoking (P < .001) and comorbid illness than uninfected comparators. There was no difference in COVID-19 severity on admission by HIV status (P = .15). Poor outcomes for hospitalized PLWH were frequent but similar to proportions in comparators; 18\% required mechanical ventilation and 21\% died during follow-up (compared with 23\% and 20\%, respectively). There was similar cumulative incidence of death over time by HIV status (P = .94). Conclusions: We found no differences in adverse outcomes associated with HIV infection for hospitalized COVID-19 patients compared with a demographically similar patient group.}, language = {en} } @article{SiddiqiDoerrStrydis2020, author = {Siddiqi, Muhammad Ali and D{\"o}rr, Christian and Strydis, Christos}, title = {IMDfence}, series = {IEEE access}, volume = {8}, journal = {IEEE access}, publisher = {Institute of Electrical and Electronics Engineers}, address = {Piscataway}, issn = {2169-3536}, doi = {10.1109/ACCESS.2020.3015686}, pages = {147948 -- 147964}, year = {2020}, abstract = {Over the past decade, focus on the security and privacy aspects of implantable medical devices (IMDs) has intensified, driven by the multitude of cybersecurity vulnerabilities found in various existing devices. However, due to their strict computational, energy and physical constraints, conventional security protocols are not directly applicable to IMDs. Custom-tailored schemes have been proposed instead which, however, fail to cover the full spectrum of security features that modern IMDs and their ecosystems so critically require. In this paper we propose IMDfence, a security protocol for IMD ecosystems that provides a comprehensive yet practical security portfolio, which includes availability, non-repudiation, access control, entity authentication, remote monitoring and system scalability. The protocol also allows emergency access that results in the graceful degradation of offered services without compromising security and patient safety. The performance of the security protocol as well as its feasibility and impact on modern IMDs are extensively analyzed and evaluated. We find that IMDfence achieves the above security requirements at a mere less than 7\% increase in total IMD energy consumption, and less than 14 ms and 9 kB increase in system delay and memory footprint, respectively.}, language = {en} } @misc{SianiparWillemsMeinel2019, author = {Sianipar, Johannes Harungguan and Willems, Christian and Meinel, Christoph}, title = {Virtual machine integrity verification in Crowd-Resourcing Virtual Laboratory}, series = {2018 IEEE 11th Conference on Service-Oriented Computing and Applications (SOCA)}, journal = {2018 IEEE 11th Conference on Service-Oriented Computing and Applications (SOCA)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-9133-5}, issn = {2163-2871}, doi = {10.1109/SOCA.2018.00032}, pages = {169 -- 176}, year = {2019}, abstract = {In cloud computing, users are able to use their own operating system (OS) image to run a virtual machine (VM) on a remote host. The virtual machine OS is started by the user using some interfaces provided by a cloud provider in public or private cloud. In peer to peer cloud, the VM is started by the host admin. After the VM is running, the user could get a remote access to the VM to install, configure, and run services. For the security reasons, the user needs to verify the integrity of the running VM, because a malicious host admin could modify the image or even replace the image with a similar image, to be able to get sensitive data from the VM. We propose an approach to verify the integrity of a running VM on a remote host, without using any specific hardware such as Trusted Platform Module (TPM). Our approach is implemented on a Linux platform where the kernel files (vmlinuz and initrd) could be replaced with new files, while the VM is running. kexec is used to reboot the VM with the new kernel files. The new kernel has secret codes that will be used to verify whether the VM was started using the new kernel files. The new kernel is used to further measuring the integrity of the running VM.}, language = {en} } @article{ShekharReimannMayeretal.2021, author = {Shekhar, Sumit and Reimann, Max and Mayer, Maximilian and Semmo, Amir and Pasewaldt, Sebastian and D{\"o}llner, J{\"u}rgen and Trapp, Matthias}, title = {Interactive photo editing on smartphones via intrinsic decomposition}, series = {Computer graphics forum : journal of the European Association for Computer Graphics}, volume = {40}, journal = {Computer graphics forum : journal of the European Association for Computer Graphics}, publisher = {Blackwell}, address = {Oxford}, issn = {0167-7055}, doi = {10.1111/cgf.142650}, pages = {497 -- 510}, year = {2021}, abstract = {Intrinsic decomposition refers to the problem of estimating scene characteristics, such as albedo and shading, when one view or multiple views of a scene are provided. The inverse problem setting, where multiple unknowns are solved given a single known pixel-value, is highly under-constrained. When provided with correlating image and depth data, intrinsic scene decomposition can be facilitated using depth-based priors, which nowadays is easy to acquire with high-end smartphones by utilizing their depth sensors. In this work, we present a system for intrinsic decomposition of RGB-D images on smartphones and the algorithmic as well as design choices therein. Unlike state-of-the-art methods that assume only diffuse reflectance, we consider both diffuse and specular pixels. For this purpose, we present a novel specularity extraction algorithm based on a multi-scale intensity decomposition and chroma inpainting. At this, the diffuse component is further decomposed into albedo and shading components. We use an inertial proximal algorithm for non-convex optimization (iPiano) to ensure albedo sparsity. Our GPU-based visual processing is implemented on iOS via the Metal API and enables interactive performance on an iPhone 11 Pro. Further, a qualitative evaluation shows that we are able to obtain high-quality outputs. Furthermore, our proposed approach for specularity removal outperforms state-of-the-art approaches for real-world images, while our albedo and shading layer decomposition is faster than the prior work at a comparable output quality. Manifold applications such as recoloring, retexturing, relighting, appearance editing, and stylization are shown, each using the intrinsic layers obtained with our method and/or the corresponding depth data.}, language = {en} } @phdthesis{Shaabani2020, author = {Shaabani, Nuhad}, title = {On discovering and incrementally updating inclusion dependencies}, doi = {10.25932/publishup-47186}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-471862}, school = {Universit{\"a}t Potsdam}, pages = {119}, year = {2020}, abstract = {In today's world, many applications produce large amounts of data at an enormous rate. Analyzing such datasets for metadata is indispensable for effectively understanding, storing, querying, manipulating, and mining them. Metadata summarizes technical properties of a dataset which rang from basic statistics to complex structures describing data dependencies. One type of dependencies is inclusion dependency (IND), which expresses subset-relationships between attributes of datasets. Therefore, inclusion dependencies are important for many data management applications in terms of data integration, query optimization, schema redesign, or integrity checking. So, the discovery of inclusion dependencies in unknown or legacy datasets is at the core of any data profiling effort. For exhaustively detecting all INDs in large datasets, we developed S-indd++, a new algorithm that eliminates the shortcomings of existing IND-detection algorithms and significantly outperforms them. S-indd++ is based on a novel concept for the attribute clustering for efficiently deriving INDs. Inferring INDs from our attribute clustering eliminates all redundant operations caused by other algorithms. S-indd++ is also based on a novel partitioning strategy that enables discording a large number of candidates in early phases of the discovering process. Moreover, S-indd++ does not require to fit a partition into the main memory--this is a highly appreciable property in the face of ever-growing datasets. S-indd++ reduces up to 50\% of the runtime of the state-of-the-art approach. None of the approach for discovering INDs is appropriate for the application on dynamic datasets; they can not update the INDs after an update of the dataset without reprocessing it entirely. To this end, we developed the first approach for incrementally updating INDs in frequently changing datasets. We achieved that by reducing the problem of incrementally updating INDs to the incrementally updating the attribute clustering from which all INDs are efficiently derivable. We realized the update of the clusters by designing new operations to be applied to the clusters after every data update. The incremental update of INDs reduces the time of the complete rediscovery by up to 99.999\%. All existing algorithms for discovering n-ary INDs are based on the principle of candidate generation--they generate candidates and test their validity in the given data instance. The major disadvantage of this technique is the exponentially growing number of database accesses in terms of SQL queries required for validation. We devised Mind2, the first approach for discovering n-ary INDs without candidate generation. Mind2 is based on a new mathematical framework developed in this thesis for computing the maximum INDs from which all other n-ary INDs are derivable. The experiments showed that Mind2 is significantly more scalable and effective than hypergraph-based algorithms.}, language = {en} } @misc{SerthPodlesnyBornsteinetal.2017, author = {Serth, Sebastian and Podlesny, Nikolai and Bornstein, Marvin and Lindemann, Jan and Latt, Johanna and Selke, Jan and Schlosser, Rainer and Boissier, Martin and Uflacker, Matthias}, title = {An interactive platform to simulate dynamic pricing competition on online marketplaces}, series = {2017 IEEE 21st International Enterprise Distributed Object Computing Conference (EDOC)}, journal = {2017 IEEE 21st International Enterprise Distributed Object Computing Conference (EDOC)}, publisher = {Institute of Electrical and Electronics Engineers}, address = {New York}, isbn = {978-1-5090-3045-3}, issn = {2325-6354}, doi = {10.1109/EDOC.2017.17}, pages = {61 -- 66}, year = {2017}, abstract = {E-commerce marketplaces are highly dynamic with constant competition. While this competition is challenging for many merchants, it also provides plenty of opportunities, e.g., by allowing them to automatically adjust prices in order to react to changing market situations. For practitioners however, testing automated pricing strategies is time-consuming and potentially hazardously when done in production. Researchers, on the other side, struggle to study how pricing strategies interact under heavy competition. As a consequence, we built an open continuous time framework to simulate dynamic pricing competition called Price Wars. The microservice-based architecture provides a scalable platform for large competitions with dozens of merchants and a large random stream of consumers. Our platform stores each event in a distributed log. This allows to provide different performance measures enabling users to compare profit and revenue of various repricing strategies in real-time. For researchers, price trajectories are shown which ease evaluating mutual price reactions of competing strategies. Furthermore, merchants can access historical marketplace data and apply machine learning. By providing a set of customizable, artificial merchants, users can easily simulate both simple rule-based strategies as well as sophisticated data-driven strategies using demand learning to optimize their pricing strategies.}, language = {en} } @article{SemmoTrappKyprianidisetal.2012, author = {Semmo, Amir and Trapp, Matthias and Kyprianidis, Jan Eric and D{\"o}llner, J{\"u}rgen Roland Friedrich}, title = {Interactive visualization of generalized virtual 3D city models using level-of-abstraction transitions}, series = {Computer graphics forum : journal of the European Association for Computer Graphics}, volume = {31}, journal = {Computer graphics forum : journal of the European Association for Computer Graphics}, number = {3}, publisher = {Wiley-Blackwell}, address = {Hoboken}, issn = {0167-7055}, doi = {10.1111/j.1467-8659.2012.03081.x}, pages = {885 -- 894}, year = {2012}, abstract = {Virtual 3D city models play an important role in the communication of complex geospatial information in a growing number of applications, such as urban planning, navigation, tourist information, and disaster management. In general, homogeneous graphic styles are used for visualization. For instance, photorealism is suitable for detailed presentations, and non-photorealism or abstract stylization is used to facilitate guidance of a viewer's gaze to prioritized information. However, to adapt visualization to different contexts and contents and to support saliency-guided visualization based on user interaction or dynamically changing thematic information, a combination of different graphic styles is necessary. Design and implementation of such combined graphic styles pose a number of challenges, specifically from the perspective of real-time 3D visualization. In this paper, the authors present a concept and an implementation of a system that enables different presentation styles, their seamless integration within a single view, and parametrized transitions between them, which are defined according to tasks, camera view, and image resolution. The paper outlines potential usage scenarios and application fields together with a performance evaluation of the implementation.}, language = {en} } @article{SemmoTrappJobstetal.2015, author = {Semmo, Amir and Trapp, Matthias and Jobst, Markus and D{\"o}llner, J{\"u}rgen Roland Friedrich}, title = {Cartography-Oriented Design of 3D Geospatial Information Visualization - Overview and Techniques}, series = {The cartographic journal}, volume = {52}, journal = {The cartographic journal}, number = {2}, publisher = {Routledge, Taylor \& Francis Group}, address = {Leeds}, issn = {0008-7041}, doi = {10.1080/00087041.2015.1119462}, pages = {95 -- 106}, year = {2015}, abstract = {In economy, society and personal life map-based interactive geospatial visualization becomes a natural element of a growing number of applications and systems. The visualization of 3D geospatial information, however, raises the question how to represent the information in an effective way. Considerable research has been done in technology-driven directions in the fields of cartography and computer graphics (e.g., design principles, visualization techniques). Here, non-photorealistic rendering (NPR) represents a promising visualization category - situated between both fields - that offers a large number of degrees for the cartography-oriented visual design of complex 2D and 3D geospatial information for a given application context. Still today, however, specifications and techniques for mapping cartographic design principles to the state-of-the-art rendering pipeline of 3D computer graphics remain to be explored. This paper revisits cartographic design principles for 3D geospatial visualization and introduces an extended 3D semiotic model that complies with the general, interactive visualization pipeline. Based on this model, we propose NPR techniques to interactively synthesize cartographic renditions of basic feature types, such as terrain, water, and buildings. In particular, it includes a novel iconification concept to seamlessly interpolate between photorealistic and cartographic representations of 3D landmarks. Our work concludes with a discussion of open challenges in this field of research, including topics, such as user interaction and evaluation.}, language = {en} } @article{SemmoHildebrandtTrappetal.2012, author = {Semmo, Amir and Hildebrandt, Dieter and Trapp, Matthias and D{\"o}llner, J{\"u}rgen Roland Friedrich}, title = {Concepts for cartography-oriented visualization of virtual 3D city models}, series = {Photogrammetrie, Fernerkundung, Geoinformation}, journal = {Photogrammetrie, Fernerkundung, Geoinformation}, number = {4}, publisher = {Schweizerbart}, address = {Stuttgart}, issn = {1432-8364}, doi = {10.1127/1432-8364/2012/0131}, pages = {455 -- 465}, year = {2012}, abstract = {Virtual 3D city models serve as an effective medium with manifold applications in geoinformation systems and services. To date, most 3D city models are visualized using photorealistic graphics. But an effective communication of geoinformation significantly depends on how important information is designed and cognitively processed in the given application context. One possibility to visually emphasize important information is based on non-photorealistic rendering, which comprehends artistic depiction styles and is characterized by its expressiveness and communication aspects. However, a direct application of non-photorealistic rendering techniques primarily results in monotonic visualization that lacks cartographic design aspects. In this work, we present concepts for cartography-oriented visualization of virtual 3D city models. These are based on coupling non-photorealistic rendering techniques and semantics-based information for a user, context, and media-dependent representation of thematic information. This work highlights challenges for cartography-oriented visualization of 3D geovirtual environments, presents stylization techniques and discusses their applications and ideas for a standardized visualization. In particular, the presented concepts enable a real-time and dynamic visualization of thematic geoinformation.}, language = {en} } @article{SemmoDoellner2015, author = {Semmo, Amir and D{\"o}llner, J{\"u}rgen Roland Friedrich}, title = {Interactive image filtering for level-of-abstraction texturing of virtual 3D scenes}, series = {Computers \& graphics : CAG ; an international journal of applications in computer graphics}, volume = {52}, journal = {Computers \& graphics : CAG ; an international journal of applications in computer graphics}, publisher = {Elsevier}, address = {Oxford}, issn = {0097-8493}, doi = {10.1016/j.cag.2015.02.001}, pages = {181 -- 198}, year = {2015}, abstract = {Texture mapping is a key technology in computer graphics. For the visual design of 3D scenes, in particular, effective texturing depends significantly on how important contents are expressed, e.g., by preserving global salient structures, and how their depiction is cognitively processed by the user in an application context. Edge-preserving image filtering is one key approach to address these concerns. Much research has focused on applying image filters in a post-process stage to generate artistically stylized depictions. However, these approaches generally do not preserve depth cues, which are important for the perception of 3D visualization (e.g., texture gradient). To this end, filtering is required that processes texture data coherently with respect to linear perspective and spatial relationships. In this work, we present an approach for texturing 3D scenes with perspective coherence by arbitrary image filters. We propose decoupled deferred texturing with (1) caching strategies to interactively perform image filtering prior to texture mapping and (2) for each mipmap level separately to enable a progressive level of abstraction, using (3) direct interaction interfaces to parameterize the visualization according to spatial, semantic, and thematic data. We demonstrate the potentials of our method by several applications using touch or natural language inputs to serve the different interests of users in specific information, including illustrative visualization, focus+context visualization, geometric detail removal, and semantic depth of field. The approach supports frame-to-frame coherence, order-independent transparency, multitexturing, and content-based filtering. In addition, it seamlessly integrates into real-time rendering pipelines and is extensible for custom interaction techniques. (C) 2015 Elsevier Ltd. All rights reserved.}, 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{SeiffertHolsteinSchlosseretal.2017, author = {Seiffert, Martin and Holstein, Flavio and Schlosser, Rainer and Schiller, Jochen}, title = {Next generation cooperative wearables}, series = {IEEE access : practical research, open solutions}, volume = {5}, journal = {IEEE access : practical research, open solutions}, publisher = {Institute of Electrical and Electronics Engineers}, address = {Piscataway}, issn = {2169-3536}, doi = {10.1109/ACCESS.2017.2749005}, pages = {16793 -- 16807}, year = {2017}, abstract = {Currently available wearables are usually based on a single sensor node with integrated capabilities for classifying different activities. The next generation of cooperative wearables could be able to identify not only activities, but also to evaluate them qualitatively using the data of several sensor nodes attached to the body, to provide detailed feedback for the improvement of the execution. Especially within the application domains of sports and health-care, such immediate feedback to the execution of body movements is crucial for (re-) learning and improving motor skills. To enable such systems for a broad range of activities, generalized approaches for human motion assessment within sensor networks are required. In this paper, we present a generalized trainable activity assessment chain (AAC) for the online assessment of periodic human activity within a wireless body area network. AAC evaluates the execution of separate movements of a prior trained activity on a fine-grained quality scale. We connect qualitative assessment with human knowledge by projecting the AAC on the hierarchical decomposition of motion performed by the human body as well as establishing the assessment on a kinematic evaluation of biomechanically distinct motion fragments. We evaluate AAC in a real-world setting and show that AAC successfully delimits the movements of correctly performed activity from faulty executions and provides detailed reasons for the activity assessment.}, language = {en} } @misc{SeidelKrentzMeinel2019, author = {Seidel, Felix and Krentz, Konrad-Felix and Meinel, Christoph}, title = {Deep En-Route Filtering of Constrained Application Protocol (CoAP) Messages on 6LoWPAN Border Routers}, series = {2019 IEEE 5th World Forum on Internet of Things (WF-IoT)}, journal = {2019 IEEE 5th World Forum on Internet of Things (WF-IoT)}, publisher = {Institute of Electrical and Electronics Engineers}, address = {New York}, isbn = {978-1-5386-4980-0}, doi = {10.1109/WF-IoT.2019.8767262}, pages = {201 -- 206}, year = {2019}, abstract = {Devices on the Internet of Things (IoT) are usually battery-powered and have limited resources. Hence, energy-efficient and lightweight protocols were designed for IoT devices, such as the popular Constrained Application Protocol (CoAP). Yet, CoAP itself does not include any defenses against denial-of-sleep attacks, which are attacks that aim at depriving victim devices of entering low-power sleep modes. For example, a denial-of-sleep attack against an IoT device that runs a CoAP server is to send plenty of CoAP messages to it, thereby forcing the IoT device to expend energy for receiving and processing these CoAP messages. All current security solutions for CoAP, namely Datagram Transport Layer Security (DTLS), IPsec, and OSCORE, fail to prevent such attacks. To fill this gap, Seitz et al. proposed a method for filtering out inauthentic and replayed CoAP messages "en-route" on 6LoWPAN border routers. In this paper, we expand on Seitz et al.'s proposal in two ways. First, we revise Seitz et al.'s software architecture so that 6LoWPAN border routers can not only check the authenticity and freshness of CoAP messages, but can also perform a wide range of further checks. Second, we propose a couple of such further checks, which, as compared to Seitz et al.'s original checks, more reliably protect IoT devices that run CoAP servers from remote denial-of-sleep attacks, as well as from remote exploits. We prototyped our solution and successfully tested its compatibility with Contiki-NG's CoAP implementation.}, language = {en} } @article{SeibelNeumannGiese2010, author = {Seibel, Andreas and Neumann, Stefan and Giese, Holger}, title = {Dynamic hierarchical mega models : comprehensive traceability and its efficient maintenance}, issn = {1619-1366}, doi = {10.1007/s10270-009-0146-z}, year = {2010}, abstract = {In the world of model-driven engineering (MDE) support for traceability and maintenance of traceability information is essential. On the one hand, classical traceability approaches for MDE address this need by supporting automated creation of traceability information on the model element level. On the other hand, global model management approaches manually capture traceability information on the model level. However, there is currently no approach that supports comprehensive traceability, comprising traceability information on both levels, and efficient maintenance of traceability information, which requires a high-degree of automation and scalability. In this article, we present a comprehensive traceability approach that combines classical traceability approaches for MDE and global model management in form of dynamic hierarchical mega models. We further integrate efficient maintenance of traceability information based on top of dynamic hierarchical mega models. The proposed approach is further outlined by using an industrial case study and by presenting an implementation of the concepts in form of a prototype.}, language = {en} } @phdthesis{Seibel2012, author = {Seibel, Andreas}, title = {Traceability and model management with executable and dynamic hierarchical megamodels}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64222}, school = {Universit{\"a}t Potsdam}, year = {2012}, abstract = {Nowadays, model-driven engineering (MDE) promises to ease software development by decreasing the inherent complexity of classical software development. In order to deliver on this promise, MDE increases the level of abstraction and automation, through a consideration of domain-specific models (DSMs) and model operations (e.g. model transformations or code generations). DSMs conform to domain-specific modeling languages (DSMLs), which increase the level of abstraction, and model operations are first-class entities of software development because they increase the level of automation. Nevertheless, MDE has to deal with at least two new dimensions of complexity, which are basically caused by the increased linguistic and technological heterogeneity. The first dimension of complexity is setting up an MDE environment, an activity comprised of the implementation or selection of DSMLs and model operations. Setting up an MDE environment is both time-consuming and error-prone because of the implementation or adaptation of model operations. The second dimension of complexity is concerned with applying MDE for actual software development. Applying MDE is challenging because a collection of DSMs, which conform to potentially heterogeneous DSMLs, are required to completely specify a complex software system. A single DSML can only be used to describe a specific aspect of a software system at a certain level of abstraction and from a certain perspective. Additionally, DSMs are usually not independent but instead have inherent interdependencies, reflecting (partial) similar aspects of a software system at different levels of abstraction or from different perspectives. A subset of these dependencies are applications of various model operations, which are necessary to keep the degree of automation high. This becomes even worse when addressing the first dimension of complexity. Due to continuous changes, all kinds of dependencies, including the applications of model operations, must also be managed continuously. This comprises maintaining the existence of these dependencies and the appropriate (re-)application of model operations. The contribution of this thesis is an approach that combines traceability and model management to address the aforementioned challenges of configuring and applying MDE for software development. The approach is considered as a traceability approach because it supports capturing and automatically maintaining dependencies between DSMs. The approach is considered as a model management approach because it supports managing the automated (re-)application of heterogeneous model operations. In addition, the approach is considered as a comprehensive model management. Since the decomposition of model operations is encouraged to alleviate the first dimension of complexity, the subsequent composition of model operations is required to counteract their fragmentation. A significant portion of this thesis concerns itself with providing a method for the specification of decoupled yet still highly cohesive complex compositions of heterogeneous model operations. The approach supports two different kinds of compositions - data-flow compositions and context compositions. Data-flow composition is used to define a network of heterogeneous model operations coupled by sharing input and output DSMs alone. Context composition is related to a concept used in declarative model transformation approaches to compose individual model transformation rules (units) at any level of detail. In this thesis, context composition provides the ability to use a collection of dependencies as context for the composition of other dependencies, including model operations. In addition, the actual implementation of model operations, which are going to be composed, do not need to implement any composition concerns. The approach is realized by means of a formalism called an executable and dynamic hierarchical megamodel, based on the original idea of megamodels. This formalism supports specifying compositions of dependencies (traceability and model operations). On top of this formalism, traceability is realized by means of a localization concept, and model management by means of an execution concept.}, language = {en} } @book{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{SchreiberKrahnIngallsetal.2016, author = {Schreiber, Robin and Krahn, Robert and Ingalls, Daniel H. H. and Hirschfeld, Robert}, title = {Transmorphic}, number = {110}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-387-9}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-98300}, publisher = {Universit{\"a}t Potsdam}, pages = {100}, year = {2016}, abstract = {Defining Graphical User Interfaces (GUIs) through functional abstractions can reduce the complexity that arises from mutable abstractions. Recent examples, such as Facebook's React GUI framework have shown, how modelling the view as a functional projection from the application state to a visual representation can reduce the number of interacting objects and thus help to improve the reliabiliy of the system. This however comes at the price of a more rigid, functional framework where programmers are forced to express visual entities with functional abstractions, detached from the way one intuitively thinks about the physical world. In contrast to that, the GUI Framework Morphic allows interactions in the graphical domain, such as grabbing, dragging or resizing of elements to evolve an application at runtime, providing liveness and directness in the development workflow. Modelling each visual entity through mutable abstractions however makes it difficult to ensure correctness when GUIs start to grow more complex. Furthermore, by evolving morphs at runtime through direct manipulation we diverge more and more from the symbolic description that corresponds to the morph. Given that both of these approaches have their merits and problems, is there a way to combine them in a meaningful way that preserves their respective benefits? As a solution for this problem, we propose to lift Morphic's concept of direct manipulation from the mutation of state to the transformation of source code. In particular, we will explore the design, implementation and integration of a bidirectional mapping between the graphical representation and a functional and declarative symbolic description of a graphical user interface within a self hosted development environment. We will present Transmorphic, a functional take on the Morphic GUI Framework, where the visual and structural properties of morphs are defined in a purely functional, declarative fashion. In Transmorphic, the developer is able to assemble different morphs at runtime through direct manipulation which is automatically translated into changes in the code of the application. In this way, the comprehensiveness and predictability of direct manipulation can be used in the context of a purely functional GUI, while the effects of the manipulation are reflected in a medium that is always in reach for the programmer and can even be used to incorporate the source transformations into the source files of the application.}, language = {en} } @article{SchneiderLambersOrejas2018, author = {Schneider, Sven and Lambers, Leen and Orejas, Fernando}, title = {Automated reasoning for attributed graph properties}, series = {International Journal on Software Tools for Technology Transfer}, volume = {20}, journal = {International Journal on Software Tools for Technology Transfer}, number = {6}, publisher = {Springer}, address = {Heidelberg}, issn = {1433-2779}, doi = {10.1007/s10009-018-0496-3}, pages = {705 -- 737}, year = {2018}, abstract = {Graphs are ubiquitous in computer science. Moreover, in various application fields, graphs are equipped with attributes to express additional information such as names of entities or weights of relationships. Due to the pervasiveness of attributed graphs, it is highly important to have the means to express properties on attributed graphs to strengthen modeling capabilities and to enable analysis. Firstly, we introduce a new logic of attributed graph properties, where the graph part and attribution part are neatly separated. The graph part is equivalent to first-order logic on graphs as introduced by Courcelle. It employs graph morphisms to allow the specification of complex graph patterns. The attribution part is added to this graph part by reverting to the symbolic approach to graph attribution, where attributes are represented symbolically by variables whose possible values are specified by a set of constraints making use of algebraic specifications. Secondly, we extend our refutationally complete tableau-based reasoning method as well as our symbolic model generation approach for graph properties to attributed graph properties. Due to the new logic mentioned above, neatly separating the graph and attribution parts, and the categorical constructions employed only on a more abstract level, we can leave the graph part of the algorithms seemingly unchanged. For the integration of the attribution part into the algorithms, we use an oracle, allowing for flexible adoption of different available SMT solvers in the actual implementation. Finally, our automated reasoning approach for attributed graph properties is implemented in the tool AutoGraph integrating in particular the SMT solver Z3 for the attribute part of the properties. We motivate and illustrate our work with a particular application scenario on graph database query validation.}, 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} } @book{SchneiderLambersOrejas2017, author = {Schneider, Sven and Lambers, Leen and Orejas, Fernando}, title = {Symbolic model generation for graph properties}, number = {115}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-396-1}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-103171}, publisher = {Universit{\"a}t Potsdam}, pages = {48}, year = {2017}, abstract = {Graphs are ubiquitous in Computer Science. For this reason, in many areas, it is very important to have the means to express and reason about graph properties. In particular, we want to be able to check automatically if a given graph property is satisfiable. Actually, in most application scenarios it is desirable to be able to explore graphs satisfying the graph property if they exist or even to get a complete and compact overview of the graphs satisfying the graph property. We show that the tableau-based reasoning method for graph properties as introduced by Lambers and Orejas paves the way for a symbolic model generation algorithm for graph properties. Graph properties are formulated in a dedicated logic making use of graphs and graph morphisms, which is equivalent to firstorder logic on graphs as introduced by Courcelle. Our parallelizable algorithm gradually generates a finite set of so-called symbolic models, where each symbolic model describes a set of finite graphs (i.e., finite models) satisfying the graph property. The set of symbolic models jointly describes all finite models for the graph property (complete) and does not describe any finite graph violating the graph property (sound). Moreover, no symbolic model is already covered by another one (compact). Finally, the algorithm is able to generate from each symbolic model a minimal finite model immediately and allows for an exploration of further finite models. The algorithm is implemented in the new tool AutoGraph.}, language = {en} } @misc{SchneiderShigeyamaKovacsetal.2018, author = {Schneider, Oliver and Shigeyama, Jotaro and Kovacs, Robert and Roumen, Thijs Jan and Marwecki, Sebastian and B{\"o}ckhoff, Nico and Gl{\"o}ckner, Daniel Amadeus Johannes and Bounama, Jonas and Baudisch, Patrick}, title = {DualPanto}, series = {UIST '18: Proceedings of the 31st Annual ACM Symposium on User Interface Software and Technology}, journal = {UIST '18: Proceedings of the 31st Annual ACM Symposium on User Interface Software and Technology}, publisher = {Association for Computing Machinery}, address = {New York}, isbn = {978-1-4503-5948-1}, doi = {10.1145/3242587.3242604}, pages = {877 -- 887}, year = {2018}, abstract = {We present a new haptic device that enables blind users to continuously track the absolute position of moving objects in spatial virtual environments, as is the case in sports or shooter games. Users interact with DualPanto by operating the me handle with one hand and by holding on to the it handle with the other hand. Each handle is connected to a pantograph haptic input/output device. The key feature is that the two handles are spatially registered with respect to each other. When guiding their avatar through a virtual world using the me handle, spatial registration enables users to track moving objects by having the device guide the output hand. This allows blind players of a 1-on-1 soccer game to race for the ball or evade an opponent; it allows blind players of a shooter game to aim at an opponent and dodge shots. In our user study, blind participants reported very high enjoyment when using the device to play (6.5/7).}, language = {en} } @article{SchneiderWenigPapenbrock2021, author = {Schneider, Johannes and Wenig, Phillip and Papenbrock, Thorsten}, title = {Distributed detection of sequential anomalies in univariate time series}, series = {The VLDB journal : the international journal on very large data bases}, volume = {30}, journal = {The VLDB journal : the international journal on very large data bases}, number = {4}, publisher = {Springer}, address = {Berlin}, issn = {1066-8888}, doi = {10.1007/s00778-021-00657-6}, pages = {579 -- 602}, year = {2021}, abstract = {The automated detection of sequential anomalies in time series is an essential task for many applications, such as the monitoring of technical systems, fraud detection in high-frequency trading, or the early detection of disease symptoms. All these applications require the detection to find all sequential anomalies possibly fast on potentially very large time series. In other words, the detection needs to be effective, efficient and scalable w.r.t. the input size. Series2Graph is an effective solution based on graph embeddings that are robust against re-occurring anomalies and can discover sequential anomalies of arbitrary length and works without training data. Yet, Series2Graph is no t scalable due to its single-threaded approach; it cannot, in particular, process arbitrarily large sequences due to the memory constraints of a single machine. In this paper, we propose our distributed anomaly detection system, short DADS, which is an efficient and scalable adaptation of Series2Graph. Based on the actor programming model, DADS distributes the input time sequence, intermediate state and the computation to all processors of a cluster in a way that minimizes communication costs and synchronization barriers. Our evaluation shows that DADS is orders of magnitude faster than S2G, scales almost linearly with the number of processors in the cluster and can process much larger input sequences due to its scale-out property.}, language = {en} } @book{SchmiedgenRhinowKoeppenetal.2015, author = {Schmiedgen, Jan and Rhinow, Holger and K{\"o}ppen, Eva and Meinel, Christoph}, title = {Parts without a whole?}, number = {97}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-334-3}, issn = {1613-5652}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-79969}, publisher = {Universit{\"a}t Potsdam}, pages = {143}, year = {2015}, abstract = {This explorative study gives a descriptive overview of what organizations do and experience when they say they practice design thinking. It looks at how the concept has been appropriated in organizations and also describes patterns of design thinking adoption. The authors use a mixed-method research design fed by two sources: questionnaire data and semi-structured personal expert interviews. The study proceeds in six parts: (1) design thinking¹s entry points into organizations; (2) understandings of the descriptor; (3) its fields of application and organizational localization; (4) its perceived impact; (5) reasons for its discontinuation or failure; and (6) attempts to measure its success. In conclusion the report challenges managers to be more conscious of their current design thinking practice. The authors suggest a co-evolution of the concept¹s introduction with innovation capability building and the respective changes in leadership approaches. It is argued that this might help in unfolding design thinking¹s hidden potentials as well as preventing unintended side-effects such as discontented teams or the dwindling authority of managers.}, language = {en} } @article{SchmidlPapenbrock2022, author = {Schmidl, Sebastian and Papenbrock, Thorsten}, title = {Efficient distributed discovery of bidirectional order dependencies}, series = {The VLDB journal}, volume = {31}, journal = {The VLDB journal}, number = {1}, publisher = {Springer}, address = {Berlin ; Heidelberg ; New York}, issn = {1066-8888}, doi = {10.1007/s00778-021-00683-4}, pages = {49 -- 74}, year = {2022}, abstract = {Bidirectional order dependencies (bODs) capture order relationships between lists of attributes in a relational table. They can express that, for example, sorting books by publication date in ascending order also sorts them by age in descending order. The knowledge about order relationships is useful for many data management tasks, such as query optimization, data cleaning, or consistency checking. Because the bODs of a specific dataset are usually not explicitly given, they need to be discovered. The discovery of all minimal bODs (in set-based canonical form) is a task with exponential complexity in the number of attributes, though, which is why existing bOD discovery algorithms cannot process datasets of practically relevant size in a reasonable time. In this paper, we propose the distributed bOD discovery algorithm DISTOD, whose execution time scales with the available hardware. DISTOD is a scalable, robust, and elastic bOD discovery approach that combines efficient pruning techniques for bOD candidates in set-based canonical form with a novel, reactive, and distributed search strategy. Our evaluation on various datasets shows that DISTOD outperforms both single-threaded and distributed state-of-the-art bOD discovery algorithms by up to orders of magnitude; it can, in particular, process much larger datasets.}, language = {en} } @inproceedings{SchlosserBoissier2017, author = {Schlosser, Rainer and Boissier, Martin}, title = {Optimal price reaction strategies in the presence of active and passive competitors}, series = {Proceedings of the 6th International Conference on Operations Research and Enterprise Systems - ICORES}, booktitle = {Proceedings of the 6th International Conference on Operations Research and Enterprise Systems - ICORES}, editor = {Liberatore, Federico and Parlier, Greg H. and Demange, Marc}, publisher = {SCITEPRESS - Science and Technology Publications, Lda.}, address = {Set{\´u}bal}, isbn = {978-989-758-218-9}, doi = {10.5220/0006118200470056}, pages = {47 -- 56}, year = {2017}, abstract = {Many markets are characterized by pricing competition. Typically, competitors are involved that adjust their prices in response to other competitors with different frequencies. We analyze stochastic dynamic pricing models under competition for the sale of durable goods. Given a competitor's pricing strategy, we show how to derive optimal response strategies that take the anticipated competitor's price adjustments into account. We study resulting price cycles and the associated expected long-term profits. We show that reaction frequencies have a major impact on a strategy's performance. In order not to act predictable our model also allows to include randomized reaction times. Additionally, we study to which extent optimal response strategies of active competitors are affected by additional passive competitors that use constant prices. It turns out that optimized feedback strategies effectively avoid a decline in price. They help to gain profits, especially, when aggressive competitor s are involved.}, language = {en} } @article{Schlosser2020, author = {Schlosser, Rainer}, title = {Risk-sensitive control of Markov decision processes}, series = {Computers \& operations research : and their applications to problems of world concern}, volume = {123}, journal = {Computers \& operations research : and their applications to problems of world concern}, publisher = {Elsevier}, address = {Oxford}, issn = {0305-0548}, doi = {10.1016/j.cor.2020.104997}, pages = {14}, year = {2020}, abstract = {In many revenue management applications risk-averse decision-making is crucial. In dynamic settings, however, it is challenging to find the right balance between maximizing expected rewards and minimizing various kinds of risk. In existing approaches utility functions, chance constraints, or (conditional) value at risk considerations are used to influence the distribution of rewards in a preferred way. Nevertheless, common techniques are not flexible enough and typically numerically complex. In our model, we exploit the fact that a distribution is characterized by its mean and higher moments. We present a multi-valued dynamic programming heuristic to compute risk-sensitive feedback policies that are able to directly control the moments of future rewards. Our approach is based on recursive formulations of higher moments and does not require an extension of the state space. Finally, we propose a self-tuning algorithm, which allows to identify feedback policies that approximate predetermined (risk-sensitive) target distributions. We illustrate the effectiveness and the flexibility of our approach for different dynamic pricing scenarios. (C) 2020 Elsevier Ltd. All rights reserved.}, language = {en} } @article{Schlosser2020, author = {Schlosser, Rainer}, title = {Scalable relaxation techniques to solve stochastic dynamic multi-product pricing problems with substitution effects}, series = {Journal of revenue and pricing management}, volume = {20}, journal = {Journal of revenue and pricing management}, number = {1}, publisher = {Palgrave Macmillan}, address = {Basingstoke}, issn = {1476-6930}, doi = {10.1057/s41272-020-00249-z}, pages = {54 -- 65}, year = {2020}, abstract = {In many businesses, firms are selling different types of products, which share mutual substitution effects in demand. To compute effective pricing strategies is challenging as the sales probabilities of each of a firm's products can also be affected by the prices of potential substitutes. In this paper, we analyze stochastic dynamic multi-product pricing models for the sale of perishable goods. To circumvent the limitations of time-consuming optimal solutions for highly complex models, we propose different relaxation techniques, which allow to reduce the size of critical model components, such as the state space, the action space, or the set of potential sales events. Our heuristics are able to decrease the size of those components by forming corresponding clusters and using subsets of representative elements. Using numerical examples, we verify that our heuristics make it possible to dramatically reduce the computation time while still obtaining close-to-optimal expected profits. Further, we show that our heuristics are (i) flexible, (ii) scalable, and (iii) can be arbitrarily combined in a mutually supportive way.}, language = {en} } @article{Schlosser2022, author = {Schlosser, Rainer}, title = {Heuristic mean-variance optimization in Markov decision processes using state-dependent risk aversion}, series = {IMA journal of management mathematics / Institute of Mathematics and Its Applications}, volume = {33}, journal = {IMA journal of management mathematics / Institute of Mathematics and Its Applications}, number = {2}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1471-678X}, doi = {10.1093/imaman/dpab009}, pages = {181 -- 199}, year = {2022}, abstract = {In dynamic decision problems, it is challenging to find the right balance between maximizing expected rewards and minimizing risks. In this paper, we consider NP-hard mean-variance (MV) optimization problems in Markov decision processes with a finite time horizon. We present a heuristic approach to solve MV problems, which is based on state-dependent risk aversion and efficient dynamic programming techniques. Our approach can also be applied to mean-semivariance (MSV) problems, which particularly focus on the downside risk. We demonstrate the applicability and the effectiveness of our heuristic for dynamic pricing applications. Using reproducible examples, we show that our approach outperforms existing state-of-the-art benchmark models for MV and MSV problems while also providing competitive runtimes. Further, compared to models based on constant risk levels, we find that state-dependent risk aversion allows to more effectively intervene in case sales processes deviate from their planned paths. Our concepts are domain independent, easy to implement and of low computational complexity.}, language = {en} } @article{Schlosser2015, author = {Schlosser, Rainer}, title = {Dynamic pricing and advertising of perishable products with inventory holding costs}, series = {Journal of economic dynamics \& control}, volume = {57}, journal = {Journal of economic dynamics \& control}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0165-1889}, doi = {10.1016/j.jedc.2015.05.017}, pages = {163 -- 181}, year = {2015}, abstract = {We examine a special class of dynamic pricing and advertising models for the sale of perishable goods, including marginal unit costs and inventory holding costs. The time horizon is assumed to be finite and we allow several model parameters to be dependent on time. For the stochastic version of the model, we derive closed-form expressions of the value function as well as of the optimal pricing and advertising policy in feedback form. Moreover, we show that for small unit shares, the model converges to a deterministic version of the problem, whose explicit solution is characterized by an overage and an underage case. We quantify the close relationship between the open-loop solution of the deterministic model and the expected evolution of optimally controlled stochastic sales processes. For both models, we derive sensitivity results. We find that in the case of positive holding costs, on average, optimal prices increase in time and advertising rates decrease. Furthermore, we analytically verify the excellent quality of optimal feedback policies of deterministic models applied in stochastic models. (C) 2015 Elsevier B.V. All rights reserved.}, language = {en} } @article{SchirmerPapenbrockKoumarelasetal.2020, author = {Schirmer, Philipp and Papenbrock, Thorsten and Koumarelas, Ioannis and Naumann, Felix}, title = {Efficient discovery of matching dependencies}, series = {ACM transactions on database systems : TODS}, volume = {45}, journal = {ACM transactions on database systems : TODS}, number = {3}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {0362-5915}, doi = {10.1145/3392778}, pages = {33}, year = {2020}, abstract = {Matching dependencies (MDs) are data profiling results that are often used for data integration, data cleaning, and entity matching. They are a generalization of functional dependencies (FDs) matching similar rather than same elements. As their discovery is very difficult, existing profiling algorithms find either only small subsets of all MDs or their scope is limited to only small datasets. We focus on the efficient discovery of all interesting MDs in real-world datasets. For this purpose, we propose HyMD, a novel MD discovery algorithm that finds all minimal, non-trivial MDs within given similarity boundaries. The algorithm extracts the exact similarity thresholds for the individual MDs from the data instead of using predefined similarity thresholds. For this reason, it is the first approach to solve the MD discovery problem in an exact and truly complete way. If needed, the algorithm can, however, enforce certain properties on the reported MDs, such as disjointness and minimum support, to focus the discovery on such results that are actually required by downstream use cases. HyMD is technically a hybrid approach that combines the two most popular dependency discovery strategies in related work: lattice traversal and inference from record pairs. Despite the additional effort of finding exact similarity thresholds for all MD candidates, the algorithm is still able to efficiently process large datasets, e.g., datasets larger than 3 GB.}, language = {en} } @article{SapeginJaegerChengetal.2017, author = {Sapegin, Andrey and Jaeger, David and Cheng, Feng and Meinel, Christoph}, title = {Towards a system for complex analysis of security events in large-scale networks}, series = {Computers \& security : the international journal devoted to the study of the technical and managerial aspects of computer security}, volume = {67}, journal = {Computers \& security : the international journal devoted to the study of the technical and managerial aspects of computer security}, publisher = {Elsevier Science}, address = {Oxford}, issn = {0167-4048}, doi = {10.1016/j.cose.2017.02.001}, pages = {16 -- 34}, year = {2017}, abstract = {After almost two decades of development, modern Security Information and Event Management (SIEM) systems still face issues with normalisation of heterogeneous data sources, high number of false positive alerts and long analysis times, especially in large-scale networks with high volumes of security events. In this paper, we present our own prototype of SIEM system, which is capable of dealing with these issues. For efficient data processing, our system employs in-memory data storage (SAP HANA) and our own technologies from the previous work, such as the Object Log Format (OLF) and high-speed event normalisation. We analyse normalised data using a combination of three different approaches for security analysis: misuse detection, query-based analytics, and anomaly detection. Compared to the previous work, we have significantly improved our unsupervised anomaly detection algorithms. Most importantly, we have developed a novel hybrid outlier detection algorithm that returns ranked clusters of anomalies. It lets an operator of a SIEM system to concentrate on the several top-ranked anomalies, instead of digging through an unsorted bundle of suspicious events. We propose to use anomaly detection in a combination with signatures and queries, applied on the same data, rather than as a full replacement for misuse detection. In this case, the majority of attacks will be captured with misuse detection, whereas anomaly detection will highlight previously unknown behaviour or attacks. We also propose that only the most suspicious event clusters need to be checked by an operator, whereas other anomalies, including false positive alerts, do not need to be explicitly checked if they have a lower ranking. We have proved our concepts and algorithms on a dataset of 160 million events from a network segment of a big multinational company and suggest that our approach and methods are highly relevant for modern SIEM systems.}, language = {en} } @misc{RoumenShigeyamaRudolphetal.2019, author = {Roumen, Thijs and Shigeyama, Jotaro and Rudolph, Julius Cosmo Romeo and Grzelka, Felix and Baudisch, Patrick}, title = {SpringFit}, series = {User Interface Software and Technology}, journal = {User Interface Software and Technology}, publisher = {Association for Computing Machinery}, address = {New York}, isbn = {978-1-4503-6816-2}, doi = {10.1145/3332165.3347930}, pages = {727 -- 738}, year = {2019}, abstract = {Joints are crucial to laser cutting as they allow making three-dimensional objects; mounts are crucial because they allow embedding technical components, such as motors. Unfortunately, mounts and joints tend to fail when trying to fabricate a model on a different laser cutter or from a different material. The reason for this lies in the way mounts and joints hold objects in place, which is by forcing them into slightly smaller openings. Such "press fit" mechanisms unfortunately are susceptible to the small changes in diameter that occur when switching to a machine that removes more or less material ("kerf"), as well as to changes in stiffness, as they occur when switching to a different material. We present a software tool called springFit that resolves this problem by replacing the problematic press fit-based mounts and joints with what we call cantilever-based mounts and joints. A cantilever spring is simply a long thin piece of material that pushes against the object to be held. Unlike press fits, cantilever springs are robust against variations in kerf and material; they can even handle very high variations, simply by using longer springs. SpringFit converts models in the form of 2D cutting plans by replacing all contained mounts, notch joints, finger joints, and t-joints. In our technical evaluation, we used springFit to convert 14 models downloaded from the web.}, language = {en} } @article{RoseHoelzleBjoerk2020, author = {Rose, Robert and H{\"o}lzle, Katharina and Bj{\"o}rk, Jennie}, title = {More than a quarter century of creativity and innovation management}, series = {Creativity and innovation management}, volume = {29}, journal = {Creativity and innovation management}, number = {1}, publisher = {Wiley-Blackwell}, address = {Oxford}, issn = {0963-1690}, doi = {10.1111/caim.12361}, pages = {5 -- 20}, year = {2020}, abstract = {When this journal was founded in 1992 by Tudor Rickards and Susan Moger, there was no academic outlet available that addressed issues at the intersection of creativity and innovation. From zero to 1,163 records, from the new kid on the block to one of the leading journals in creativity and innovation management has been quite a journey, and we would like to reflect on the past 28 years and the intellectual and conceptual structure of Creativity and Innovation Management (CIM). Specifically, we highlight milestones and influential articles, identify how key journal characteristics evolved, outline the (co-)authorship structure, and finally, map the thematic landscape of CIM by means of a text-mining analysis. This study represents the first systematic and comprehensive assessment of the journal's published body of knowledge and helps to understand the journal's influence on the creativity and innovation management community. We conclude by discussing future topics and paths of the journal as well as limitations of our approach.}, language = {en} } @article{RoschkeChengMeinel2012, author = {Roschke, Sebastian and Cheng, Feng and Meinel, Christoph}, title = {An alert correlation platform for memory-supported techniques}, series = {Concurrency and computation : practice \& experience}, volume = {24}, journal = {Concurrency and computation : practice \& experience}, number = {10}, publisher = {Wiley-Blackwell}, address = {Hoboken}, issn = {1532-0626}, doi = {10.1002/cpe.1750}, pages = {1123 -- 1136}, year = {2012}, abstract = {Intrusion Detection Systems (IDS) have been widely deployed in practice for detecting malicious behavior on network communication and hosts. False-positive alerts are a popular problem for most IDS approaches. The solution to address this problem is to enhance the detection process by correlation and clustering of alerts. To meet the practical requirements, this process needs to be finished fast, which is a challenging task as the amount of alerts in large-scale IDS deployments is significantly high. We identifytextitdata storage and processing algorithms to be the most important factors influencing the performance of clustering and correlation. We propose and implement a highly efficient alert correlation platform. For storage, a column-based database, an In-Memory alert storage, and memory-based index tables lead to significant improvements of the performance. For processing, algorithms are designed and implemented which are optimized for In-Memory databases, e.g. an attack graph-based correlation algorithm. The platform can be distributed over multiple processing units to share memory and processing power. A standardized interface is designed to provide a unified view of result reports for end users. The efficiency of the platform is tested by practical experiments with several alert storage approaches, multiple algorithms, as well as a local and a distributed deployment.}, language = {en} } @article{RoschkeChengMeinel2013, author = {Roschke, Sebastian and Cheng, Feng and Meinel, Christoph}, title = {High-quality attack graph-based IDS correlation}, series = {Logic journal of the IGPL}, volume = {21}, journal = {Logic journal of the IGPL}, number = {4}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1367-0751}, doi = {10.1093/jigpal/jzs034}, pages = {571 -- 591}, year = {2013}, abstract = {Intrusion Detection Systems are widely deployed in computer networks. As modern attacks are getting more sophisticated and the number of sensors and network nodes grow, the problem of false positives and alert analysis becomes more difficult to solve. Alert correlation was proposed to analyse alerts and to decrease false positives. Knowledge about the target system or environment is usually necessary for efficient alert correlation. For representing the environment information as well as potential exploits, the existing vulnerabilities and their Attack Graph (AG) is used. It is useful for networks to generate an AG and to organize certain vulnerabilities in a reasonable way. In this article, a correlation algorithm based on AGs is designed that is capable of detecting multiple attack scenarios for forensic analysis. It can be parameterized to adjust the robustness and accuracy. A formal model of the algorithm is presented and an implementation is tested to analyse the different parameters on a real set of alerts from a local network. To improve the speed of the algorithm, a multi-core version is proposed and a HMM-supported version can be used to further improve the quality. The parallel implementation is tested on a multi-core correlation platform, using CPUs and GPUs.}, language = {en} } @article{RoostapourNeumannNeumannetal.2022, author = {Roostapour, Vahid and Neumann, Aneta and Neumann, Frank and Friedrich, Tobias}, title = {Pareto optimization for subset selection with dynamic cost constraints}, series = {Artificial intelligence}, volume = {302}, journal = {Artificial intelligence}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0004-3702}, doi = {10.1016/j.artint.2021.103597}, pages = {17}, year = {2022}, abstract = {We consider the subset selection problem for function f with constraint bound B that changes over time. Within the area of submodular optimization, various greedy approaches are commonly used. For dynamic environments we observe that the adaptive variants of these greedy approaches are not able to maintain their approximation quality. Investigating the recently introduced POMC Pareto optimization approach, we show that this algorithm efficiently computes a phi=(alpha(f)/2)(1 - 1/e(alpha)f)-approximation, where alpha(f) is the submodularity ratio of f, for each possible constraint bound b <= B. Furthermore, we show that POMC is able to adapt its set of solutions quickly in the case that B increases. Our experimental investigations for the influence maximization in social networks show the advantage of POMC over generalized greedy algorithms. We also consider EAMC, a new evolutionary algorithm with polynomial expected time guarantee to maintain phi approximation ratio, and NSGA-II with two different population sizes as advanced multi-objective optimization algorithm, to demonstrate their challenges in optimizing the maximum coverage problem. Our empirical analysis shows that, within the same number of evaluations, POMC is able to perform as good as NSGA-II under linear constraint, while EAMC performs significantly worse than all considered algorithms in most cases.}, language = {en} } @article{RoggeSoltiWeske2015, author = {Rogge-Solti, Andreas and Weske, Mathias}, title = {Prediction of business process durations using non-Markovian stochastic Petri nets}, series = {Information systems}, volume = {54}, journal = {Information systems}, publisher = {Elsevier}, address = {Oxford}, issn = {0306-4379}, doi = {10.1016/j.is.2015.04.004}, pages = {1 -- 14}, year = {2015}, abstract = {Companies need to efficiently manage their business processes to deliver products and services in time. Therefore, they monitor the progress of individual cases to be able to timely detect undesired deviations and to react accordingly. For example, companies can decide to speed up process execution by raising alerts or by using additional resources, which increases the chance that a certain deadline or service level agreement can be met. Central to such process control is accurate prediction of the remaining time of a case and the estimation of the risk of missing a deadline. To achieve this goal, we use a specific kind of stochastic Petri nets that can capture arbitrary duration distributions. Thereby, we are able to achieve higher prediction accuracy than related approaches. Further, we evaluate the approach in comparison to state of the art approaches and show the potential of exploiting a so far untapped source of information: the elapsed time since the last observed event. Real-world case studies in the financial and logistics domain serve to illustrate and evaluate the approach presented. (C) 2015 Elsevier Ltd. All rights reserved.}, language = {en} } @book{RoggeSoltiMansvanderAalstetal.2013, author = {Rogge-Solti, Andreas and Mans, Ronny S. and van der Aalst, Wil M. P. and Weske, Mathias}, title = {Repairing event logs using stochastic process models}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-258-2}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-66797}, publisher = {Universit{\"a}t Potsdam}, pages = {19}, year = {2013}, abstract = {Companies strive to improve their business processes in order to remain competitive. Process mining aims to infer meaningful insights from process-related data and attracted the attention of practitioners, tool-vendors, and researchers in recent years. Traditionally, event logs are assumed to describe the as-is situation. But this is not necessarily the case in environments where logging may be compromised due to manual logging. For example, hospital staff may need to manually enter information regarding the patient's treatment. As a result, events or timestamps may be missing or incorrect. In this paper, we make use of process knowledge captured in process models, and provide a method to repair missing events in the logs. This way, we facilitate analysis of incomplete logs. We realize the repair by combining stochastic Petri nets, alignments, and Bayesian networks. We evaluate the results using both synthetic data and real event data from a Dutch hospital.}, language = {en} }