@article{WiemkerBunovaNeufeldetal.2022, author = {Wiemker, Veronika and Bunova, Anna and Neufeld, Maria and Gornyi, Boris and Yurasova, Elena and Konigorski, Stefan and Kalinina, Anna and Kontsevaya, Anna and Ferreira-Borges, Carina and Probst, Charlotte}, title = {Pilot study to evaluate usability and acceptability of the 'Animated Alcohol Assessment Tool' in Russian primary healthcare}, series = {Digital health}, volume = {8}, journal = {Digital health}, publisher = {Sage Publications}, address = {London}, issn = {2055-2076}, doi = {10.1177/20552076211074491}, pages = {11}, year = {2022}, abstract = {Background and aims: Accurate and user-friendly assessment tools quantifying alcohol consumption are a prerequisite to effective prevention and treatment programmes, including Screening and Brief Intervention. Digital tools offer new potential in this field. We developed the 'Animated Alcohol Assessment Tool' (AAA-Tool), a mobile app providing an interactive version of the World Health Organization's Alcohol Use Disorders Identification Test (AUDIT) that facilitates the description of individual alcohol consumption via culturally informed animation features. This pilot study evaluated the Russia-specific version of the Animated Alcohol Assessment Tool with regard to (1) its usability and acceptability in a primary healthcare setting, (2) the plausibility of its alcohol consumption assessment results and (3) the adequacy of its Russia-specific vessel and beverage selection. Methods: Convenience samples of 55 patients (47\% female) and 15 healthcare practitioners (80\% female) in 2 Russian primary healthcare facilities self-administered the Animated Alcohol Assessment Tool and rated their experience on the Mobile Application Rating Scale - User Version. Usage data was automatically collected during app usage, and additional feedback on regional content was elicited in semi-structured interviews. Results: On average, patients completed the Animated Alcohol Assessment Tool in 6:38 min (SD = 2.49, range = 3.00-17.16). User satisfaction was good, with all subscale Mobile Application Rating Scale - User Version scores averaging >3 out of 5 points. A majority of patients (53\%) and practitioners (93\%) would recommend the tool to 'many people' or 'everyone'. Assessed alcohol consumption was plausible, with a low number (14\%) of logically impossible entries. Most patients reported the Animated Alcohol Assessment Tool to reflect all vessels (78\%) and all beverages (71\%) they typically used. Conclusion: High acceptability ratings by patients and healthcare practitioners, acceptable completion time, plausible alcohol usage assessment results and perceived adequacy of region-specific content underline the Animated Alcohol Assessment Tool's potential to provide a novel approach to alcohol assessment in primary healthcare. After its validation, the Animated Alcohol Assessment Tool might contribute to reducing alcohol-related harm by facilitating Screening and Brief Intervention implementation in Russia and beyond.}, language = {en} } @article{UlrichLutfiRutzenetal.2022, author = {Ulrich, Jens-Uwe and Lutfi, Ahmad and Rutzen, Kilian and Renard, Bernhard Y.}, title = {ReadBouncer}, series = {Bioinformatics}, volume = {38}, journal = {Bioinformatics}, number = {SUPPL 1}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1367-4803}, doi = {10.1093/bioinformatics/btac223}, pages = {153 -- 160}, year = {2022}, abstract = {Motivation: Nanopore sequencers allow targeted sequencing of interesting nucleotide sequences by rejecting other sequences from individual pores. This feature facilitates the enrichment of low-abundant sequences by depleting overrepresented ones in-silico. Existing tools for adaptive sampling either apply signal alignment, which cannot handle human-sized reference sequences, or apply read mapping in sequence space relying on fast graphical processing units (GPU) base callers for real-time read rejection. Using nanopore long-read mapping tools is also not optimal when mapping shorter reads as usually analyzed in adaptive sampling applications. Results: Here, we present a new approach for nanopore adaptive sampling that combines fast CPU and GPU base calling with read classification based on Interleaved Bloom Filters. ReadBouncer improves the potential enrichment of low abundance sequences by its high read classification sensitivity and specificity, outperforming existing tools in the field. It robustly removes even reads belonging to large reference sequences while running on commodity hardware without GPUs, making adaptive sampling accessible for in-field researchers. Readbouncer also provides a user-friendly interface and installer files for end-users without a bioinformatics background.}, language = {en} } @article{WittigMirandaHoelzeretal.2022, author = {Wittig, Alice and Miranda, Fabio Malcher and H{\"o}lzer, Martin and Altenburg, Tom and Bartoszewicz, Jakub Maciej and Beyvers, Sebastian and Dieckmann, Marius Alfred and Genske, Ulrich and Giese, Sven Hans-Joachim and Nowicka, Melania and Richard, Hugues and Schiebenhoefer, Henning and Schmachtenberg, Anna-Juliane and Sieben, Paul and Tang, Ming and Tembrockhaus, Julius and Renard, Bernhard Y. and Fuchs, Stephan}, title = {CovRadar}, series = {Bioinformatics}, volume = {38}, journal = {Bioinformatics}, number = {17}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1367-4803}, doi = {10.1093/bioinformatics/btac411}, pages = {4223 -- 4225}, year = {2022}, abstract = {The ongoing pandemic caused by SARS-CoV-2 emphasizes the importance of genomic surveillance to understand the evolution of the virus, to monitor the viral population, and plan epidemiological responses. Detailed analysis, easy visualization and intuitive filtering of the latest viral sequences are powerful for this purpose. We present CovRadar, a tool for genomic surveillance of the SARS-CoV-2 Spike protein. CovRadar consists of an analytical pipeline and a web application that enable the analysis and visualization of hundreds of thousand sequences. First, CovRadar extracts the regions of interest using local alignment, then builds a multiple sequence alignment, infers variants and consensus and finally presents the results in an interactive app, making accessing and reporting simple, flexible and fast.}, language = {en} } @misc{MontiRautenstrauchGhanbarietal.2022, author = {Monti, Remo and Rautenstrauch, Pia and Ghanbari, Mahsa and James, Alva Rani and Kirchler, Matthias and Ohler, Uwe and Konigorski, Stefan and Lippert, Christoph}, title = {Identifying interpretable gene-biomarker associations with functionally informed kernel-based tests in 190,000 exomes}, series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, journal = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, number = {16}, doi = {10.25932/publishup-58607}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-586078}, pages = {16}, year = {2022}, abstract = {Here we present an exome-wide rare genetic variant association study for 30 blood biomarkers in 191,971 individuals in the UK Biobank. We compare gene- based association tests for separate functional variant categories to increase interpretability and identify 193 significant gene-biomarker associations. Genes associated with biomarkers were ~ 4.5-fold enriched for conferring Mendelian disorders. In addition to performing weighted gene-based variant collapsing tests, we design and apply variant-category-specific kernel-based tests that integrate quantitative functional variant effect predictions for mis- sense variants, splicing and the binding of RNA-binding proteins. For these tests, we present a computationally efficient combination of the likelihood- ratio and score tests that found 36\% more associations than the score test alone while also controlling the type-1 error. Kernel-based tests identified 13\% more associations than their gene-based collapsing counterparts and had advantages in the presence of gain of function missense variants. We introduce local collapsing by amino acid position for missense variants and use it to interpret associations and identify potential novel gain of function variants in PIEZO1. Our results show the benefits of investigating different functional mechanisms when performing rare-variant association tests, and demonstrate pervasive rare-variant contribution to biomarker variability.}, language = {en} } @article{MontiRautenstrauchGhanbarietal.2022, author = {Monti, Remo and Rautenstrauch, Pia and Ghanbari, Mahsa and James, Alva Rani and Kirchler, Matthias and Ohler, Uwe and Konigorski, Stefan and Lippert, Christoph}, title = {Identifying interpretable gene-biomarker associations with functionally informed kernel-based tests in 190,000 exomes}, series = {Nature Communications}, volume = {13}, journal = {Nature Communications}, publisher = {Nature Publishing Group UK}, address = {London}, issn = {2041-1723}, doi = {10.1038/s41467-022-32864-2}, pages = {16}, year = {2022}, abstract = {Here we present an exome-wide rare genetic variant association study for 30 blood biomarkers in 191,971 individuals in the UK Biobank. We compare gene- based association tests for separate functional variant categories to increase interpretability and identify 193 significant gene-biomarker associations. Genes associated with biomarkers were ~ 4.5-fold enriched for conferring Mendelian disorders. In addition to performing weighted gene-based variant collapsing tests, we design and apply variant-category-specific kernel-based tests that integrate quantitative functional variant effect predictions for mis- sense variants, splicing and the binding of RNA-binding proteins. For these tests, we present a computationally efficient combination of the likelihood- ratio and score tests that found 36\% more associations than the score test alone while also controlling the type-1 error. Kernel-based tests identified 13\% more associations than their gene-based collapsing counterparts and had advantages in the presence of gain of function missense variants. We introduce local collapsing by amino acid position for missense variants and use it to interpret associations and identify potential novel gain of function variants in PIEZO1. Our results show the benefits of investigating different functional mechanisms when performing rare-variant association tests, and demonstrate pervasive rare-variant contribution to biomarker variability.}, language = {en} } @article{RichlySchlosserBoissier2022, author = {Richly, Keven and Schlosser, Rainer and Boissier, Martin}, title = {Budget-conscious fine-grained configuration optimization for spatio-temporal applications}, series = {Proceedings of the VLDB Endowment}, volume = {15}, journal = {Proceedings of the VLDB Endowment}, number = {13}, publisher = {Association for Computing Machinery (ACM)}, address = {[New York]}, issn = {2150-8097}, doi = {10.14778/3565838.3565858}, pages = {4079 -- 4092}, year = {2022}, abstract = {Based on the performance requirements of modern spatio-temporal data mining applications, in-memory database systems are often used to store and process the data. To efficiently utilize the scarce DRAM capacities, modern database systems support various tuning possibilities to reduce the memory footprint (e.g., data compression) or increase performance (e.g., additional indexes). However, the selection of cost and performance balancing configurations is challenging due to the vast number of possible setups consisting of mutually dependent individual decisions. In this paper, we introduce a novel approach to jointly optimize the compression, sorting, indexing, and tiering configuration for spatio-temporal workloads. Further, we consider horizontal data partitioning, which enables the independent application of different tuning options on a fine-grained level. We propose different linear programming (LP) models addressing cost dependencies at different levels of accuracy to compute optimized tuning configurations for a given workload and memory budgets. To yield maintainable and robust configurations, we extend our LP-based approach to incorporate reconfiguration costs as well as a worst-case optimization for potential workload scenarios. Further, we demonstrate on a real-world dataset that our models allow to significantly reduce the memory footprint with equal performance or increase the performance with equal memory size compared to existing tuning heuristics.}, language = {en} } @article{YadavHusainFutrell2022, author = {Yadav, Himanshu and Husain, Samar and Futrell, Richard}, title = {Assessing corpus evidence for formal and psycholinguistic constraints on nonprojectivity}, series = {Computational linguistics}, volume = {48}, journal = {Computational linguistics}, number = {2}, publisher = {MIT Press}, address = {Cambridge}, issn = {0891-2017}, doi = {10.1162/coli_a_00437}, pages = {375 -- 401}, year = {2022}, abstract = {Formal constraints on crossing dependencies have played a large role in research on the formal complexity of natural language grammars and parsing. Here we ask whether the apparent evidence for constraints on crossing dependencies in treebanks might arise because of independent constraints on trees, such as low arity and dependency length minimization. We address this question using two sets of experiments. In Experiment 1, we compare the distribution of formal properties of crossing dependencies, such as gap degree, between real trees and baseline trees matched for rate of crossing dependencies and various other properties. In Experiment 2, we model whether two dependencies cross, given certain psycholinguistic properties of the dependencies. We find surprisingly weak evidence for constraints originating from the mild context-sensitivity literature (gap degree and well-nestedness) beyond what can be explained by constraints on rate of crossing dependencies, topological properties of the trees, and dependency length. However, measures that have emerged from the parsing literature (e.g., edge degree, end-point crossings, and heads' depth difference) differ strongly between real and random trees. Modeling results show that cognitive metrics relating to information locality and working-memory limitations affect whether two dependencies cross or not, but they do not fully explain the distribution of crossing dependencies in natural languages. Together these results suggest that crossing constraints are better characterized by processing pressures than by mildly context-sensitive constraints.}, language = {en} } @article{FiggeDimitrovSchlosseretal.2022, author = {Figge, Frank and Dimitrov, Stanko and Schlosser, Rainer and Chenavaz, Regis}, title = {Does the circular economy fuel the throwaway society? The role of opportunity costs for products that lose value over time}, series = {Journal of cleaner production}, volume = {368}, journal = {Journal of cleaner production}, publisher = {Elsevier}, address = {Oxford}, issn = {0959-6526}, doi = {10.1016/j.jclepro.2022.133207}, pages = {9}, year = {2022}, abstract = {The efficient use of natural resources is considered a necessary condition for their sustainable use. Extending the lifetime of products and using resources circularly are two popular strategies to increase the efficiency of resource use. Both strategies are usually assumed to contribute to the eco-efficiency of resource use independently. We argue that a move to a circular economy creates opportunity costs for consumers holding on to their products, due to the resource embedded in the product. Assuming rational consumers, we develop a model that determines optimal replacement times for products subject to minimizing average costs over time. We find that in a perfectly circular economy, consumers are incentivized to discard their products more quickly than in a perfectly linear economy. A direct consequence of our finding is that extending product use is in direct conflict with closing resource loops in the circular economy. We identify the salvage value of discarded products and technical progress as two factors that determine the impact that closing resource loops has on the duration of product use. The article highlights the risk that closing resource loops and moving to a more circular economy incentivizes more unsustainable behavior.}, language = {en} } @misc{HollmannRegiererBechisetal.2022, author = {Hollmann, Susanne and Regierer, Babette and Bechis, Jaele and Tobin, Lesley and D'Elia, Domenica}, title = {Ten simple rules on how to develop a stakeholder engagement plan}, series = {PLoS Computational Biology}, volume = {18}, journal = {PLoS Computational Biology}, number = {10}, publisher = {Public Library of Science (PLoS)}, address = {San Fransisco}, issn = {1553-734X}, doi = {10.1371/journal.pcbi.1010520}, pages = {12}, year = {2022}, abstract = {To make research responsible and research outcomes meaningful, it is necessary to communicate our research and to involve as many relevant stakeholders as possible, especially in application-oriented-including information and communications technology (ICT)-research. Nowadays, stakeholder engagement is of fundamental importance to project success and achieving the expected impact and is often mandatory in a third-party funding context. Ultimately, research and development can only be successful if people react positively to the results and benefits generated by a project. For the wider acceptance of research outcomes, it is therefore essential that the public is made aware of and has an opportunity to discuss the results of research undertaken through two-way communication (interpersonal communication) with researchers. Responsible Research and Innovation (RRI), an approach that anticipates and assesses potential implications and societal expectations regarding research and innovation, aims to foster inclusive and sustainable research and innovation. Research and innovation processes need to become more responsive and adaptive to these grand challenges. This implies, among other things, the introduction of broader foresight and impact assessments for new technologies beyond their anticipated market benefits and risks. Therefore, this article provides a structured workflow that explains "how to develop a stakeholder engagement plan" step by step.}, language = {en} } @article{RojahnWeberGronau2023, author = {Rojahn, Marcel and Weber, Edzard and Gronau, Norbert}, title = {Towards a standardization in scheduling models}, series = {International journal of industrial and systems engineering}, volume = {17}, journal = {International journal of industrial and systems engineering}, number = {6}, publisher = {Inderscience Enterprises}, address = {Gen{\`e}ve}, issn = {1748-5037}, pages = {401 -- 408}, year = {2023}, abstract = {Terminology is a critical instrument for each researcher. Different terminologies for the same research object may arise in different research communities. By this inconsistency, many synergistic effects get lost. Theories and models will be more understandable and reusable if a common terminology is applied. This paper examines the terminological (in)consistence for the research field of job-shop scheduling by a literature review. There is an enormous variety in the choice of terms and mathematical notation for the same concept. The comparability, reusability and combinability of scheduling methods is unnecessarily hampered by the arbitrary use of homonyms and synonyms. The acceptance in the community of used variables and notation forms is shown by means of a compliance quotient. This is proven by the evaluation of 240 scientific publications on planning methods.}, language = {en} } @misc{RitterbuschTeichmann2023, author = {Ritterbusch, Georg David and Teichmann, Malte Rolf}, title = {Defining the metaverse}, series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Wirtschafts- und Sozialwissenschaftliche Reihe}, journal = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Wirtschafts- und Sozialwissenschaftliche Reihe}, number = {159}, issn = {1867-5808}, doi = {10.25932/publishup-58879}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-588799}, pages = {12368 -- 12377}, year = {2023}, abstract = {The term Metaverse is emerging as a result of the late push by multinational technology conglomerates and a recent surge of interest in Web 3.0, Blockchain, NFT, and Cryptocurrencies. From a scientific point of view, there is no definite consensus on what the Metaverse will be like. This paper collects, analyzes, and synthesizes scientific definitions and the accompanying major characteristics of the Metaverse using the methodology of a Systematic Literature Review (SLR). Two revised definitions for the Metaverse are presented, both condensing the key attributes, where the first one is rather simplistic holistic describing "a three-dimensional online environment in which users represented by avatars interact with each other in virtual spaces decoupled from the real physical world". In contrast, the second definition is specified in a more detailed manner in the paper and further discussed. These comprehensive definitions offer specialized and general scholars an application within and beyond the scientific context of the system science, information system science, computer science, and business informatics, by also introducing open research challenges. Furthermore, an outlook on the social, economic, and technical implications is given, and the preconditions that are necessary for a successful implementation are discussed.}, language = {en} } @article{RitterbuschTeichmann2023, author = {Ritterbusch, Georg David and Teichmann, Malte Rolf}, title = {Defining the metaverse}, series = {IEEE Access}, volume = {11}, journal = {IEEE Access}, publisher = {Institute of Electrical and Electronics Engineers}, address = {New York, NY}, issn = {2169-3536}, doi = {10.1109/ACCESS.2023.3241809}, pages = {12368 -- 12377}, year = {2023}, abstract = {The term Metaverse is emerging as a result of the late push by multinational technology conglomerates and a recent surge of interest in Web 3.0, Blockchain, NFT, and Cryptocurrencies. From a scientific point of view, there is no definite consensus on what the Metaverse will be like. This paper collects, analyzes, and synthesizes scientific definitions and the accompanying major characteristics of the Metaverse using the methodology of a Systematic Literature Review (SLR). Two revised definitions for the Metaverse are presented, both condensing the key attributes, where the first one is rather simplistic holistic describing "a three-dimensional online environment in which users represented by avatars interact with each other in virtual spaces decoupled from the real physical world". In contrast, the second definition is specified in a more detailed manner in the paper and further discussed. These comprehensive definitions offer specialized and general scholars an application within and beyond the scientific context of the system science, information system science, computer science, and business informatics, by also introducing open research challenges. Furthermore, an outlook on the social, economic, and technical implications is given, and the preconditions that are necessary for a successful implementation are discussed.}, language = {en} } @phdthesis{Bano2023, author = {Bano, Dorina}, title = {Discovering data models from event logs}, doi = {10.25932/publishup-58542}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-585427}, school = {Universit{\"a}t Potsdam}, pages = {xvii, 137}, year = {2023}, abstract = {In the last two decades, process mining has developed from a niche discipline to a significant research area with considerable impact on academia and industry. Process mining enables organisations to identify the running business processes from historical execution data. The first requirement of any process mining technique is an event log, an artifact that represents concrete business process executions in the form of sequence of events. These logs can be extracted from the organization's information systems and are used by process experts to retrieve deep insights from the organization's running processes. Considering the events pertaining to such logs, the process models can be automatically discovered and enhanced or annotated with performance-related information. Besides behavioral information, event logs contain domain specific data, albeit implicitly. However, such data are usually overlooked and, thus, not utilized to their full potential. Within the process mining area, we address in this thesis the research gap of discovering, from event logs, the contextual information that cannot be captured by applying existing process mining techniques. Within this research gap, we identify four key problems and tackle them by looking at an event log from different angles. First, we address the problem of deriving an event log in the absence of a proper database access and domain knowledge. The second problem is related to the under-utilization of the implicit domain knowledge present in an event log that can increase the understandability of the discovered process model. Next, there is a lack of a holistic representation of the historical data manipulation at the process model level of abstraction. Last but not least, each process model presumes to be independent of other process models when discovered from an event log, thus, ignoring possible data dependencies between processes within an organization. For each of the problems mentioned above, this thesis proposes a dedicated method. The first method provides a solution to extract an event log only from the transactions performed on the database that are stored in the form of redo logs. The second method deals with discovering the underlying data model that is implicitly embedded in the event log, thus, complementing the discovered process model with important domain knowledge information. The third method captures, on the process model level, how the data affects the running process instances. Lastly, the fourth method is about the discovery of the relations between business processes (i.e., how they exchange data) from a set of event logs and explicitly representing such complex interdependencies in a business process architecture. All the methods introduced in this thesis are implemented as a prototype and their feasibility is proven by being applied on real-life event logs.}, language = {en} } @incollection{RojahnAmbrosBiruetal.2023, author = {Rojahn, Marcel and Ambros, Maximilian and Biru, Tibebu and Krallmann, Hermann and Gronau, Norbert and Grum, Marcus}, title = {Adequate basis for the data-driven and machine-learning-based identification}, series = {Artificial intelligence and soft computing}, booktitle = {Artificial intelligence and soft computing}, editor = {Rutkowski, Leszek and Scherer, Rafał and Korytkowski, Marcin and Pedrycz, Witold and Tadeusiewicz, Ryszard and Zurada, Jacek M.}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-42504-2}, doi = {10.1007/978-3-031-42505-9_48}, pages = {570 -- 588}, year = {2023}, abstract = {Process mining (PM) has established itself in recent years as a main method for visualizing and analyzing processes. However, the identification of knowledge has not been addressed adequately because PM aims solely at data-driven discovering, monitoring, and improving real-world processes from event logs available in various information systems. The following paper, therefore, outlines a novel systematic analysis view on tools for data-driven and machine learning (ML)-based identification of knowledge-intensive target processes. To support the effectiveness of the identification process, the main contributions of this study are (1) to design a procedure for a systematic review and analysis for the selection of relevant dimensions, (2) to identify different categories of dimensions as evaluation metrics to select source systems, algorithms, and tools for PM and ML as well as include them in a multi-dimensional grid box model, (3) to select and assess the most relevant dimensions of the model, (4) to identify and assess source systems, algorithms, and tools in order to find evidence for the selected dimensions, and (5) to assess the relevance and applicability of the conceptualization and design procedure for tool selection in data-driven and ML-based process mining research.}, language = {en} } @phdthesis{Sakizloglou2023, author = {Sakizloglou, Lucas}, title = {Evaluating temporal queries over history-aware architectural runtime models}, doi = {10.25932/publishup-60439}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-604396}, school = {Universit{\"a}t Potsdam}, pages = {v, 168}, year = {2023}, abstract = {In model-driven engineering, the adaptation of large software systems with dynamic structure is enabled by architectural runtime models. Such a model represents an abstract state of the system as a graph of interacting components. Every relevant change in the system is mirrored in the model and triggers an evaluation of model queries, which search the model for structural patterns that should be adapted. This thesis focuses on a type of runtime models where the expressiveness of the model and model queries is extended to capture past changes and their timing. These history-aware models and temporal queries enable more informed decision-making during adaptation, as they support the formulation of requirements on the evolution of the pattern that should be adapted. However, evaluating temporal queries during adaptation poses significant challenges. First, it implies the capability to specify and evaluate requirements on the structure, as well as the ordering and timing in which structural changes occur. Then, query answers have to reflect that the history-aware model represents the architecture of a system whose execution may be ongoing, and thus answers may depend on future changes. Finally, query evaluation needs to be adequately fast and memory-efficient despite the increasing size of the history---especially for models that are altered by numerous, rapid changes. The thesis presents a query language and a querying approach for the specification and evaluation of temporal queries. These contributions aim to cope with the challenges of evaluating temporal queries at runtime, a prerequisite for history-aware architectural monitoring and adaptation which has not been systematically treated by prior model-based solutions. The distinguishing features of our contributions are: the specification of queries based on a temporal logic which encodes structural patterns as graphs; the provision of formally precise query answers which account for timing constraints and ongoing executions; the incremental evaluation which avoids the re-computation of query answers after each change; and the option to discard history that is no longer relevant to queries. The query evaluation searches the model for occurrences of a pattern whose evolution satisfies a temporal logic formula. Therefore, besides model-driven engineering, another related research community is runtime verification. The approach differs from prior logic-based runtime verification solutions by supporting the representation and querying of structure via graphs and graph queries, respectively, which is more efficient for queries with complex patterns. We present a prototypical implementation of the approach and measure its speed and memory consumption in monitoring and adaptation scenarios from two application domains, with executions of an increasing size. We assess scalability by a comparison to the state-of-the-art from both related research communities. The implementation yields promising results, which pave the way for sophisticated history-aware self-adaptation solutions and indicate that the approach constitutes a highly effective technique for runtime monitoring on an architectural level.}, language = {en} } @phdthesis{Lindinger2023, author = {Lindinger, Jakob}, title = {Variational inference for composite Gaussian process models}, doi = {10.25932/publishup-60444}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-604441}, school = {Universit{\"a}t Potsdam}, pages = {xi, 122}, year = {2023}, abstract = {Most machine learning methods provide only point estimates when being queried to predict on new data. This is problematic when the data is corrupted by noise, e.g. from imperfect measurements, or when the queried data point is very different to the data that the machine learning model has been trained with. Probabilistic modelling in machine learning naturally equips predictions with corresponding uncertainty estimates which allows a practitioner to incorporate information about measurement noise into the modelling process and to know when not to trust the predictions. A well-understood, flexible probabilistic framework is provided by Gaussian processes that are ideal as building blocks of probabilistic models. They lend themself naturally to the problem of regression, i.e., being given a set of inputs and corresponding observations and then predicting likely observations for new unseen inputs, and can also be adapted to many more machine learning tasks. However, exactly inferring the optimal parameters of such a Gaussian process model (in a computationally tractable manner) is only possible for regression tasks in small data regimes. Otherwise, approximate inference methods are needed, the most prominent of which is variational inference. In this dissertation we study models that are composed of Gaussian processes embedded in other models in order to make those more flexible and/or probabilistic. The first example are deep Gaussian processes which can be thought of as a small network of Gaussian processes and which can be employed for flexible regression. The second model class that we study are Gaussian process state-space models. These can be used for time-series modelling, i.e., the task of being given a stream of data ordered by time and then predicting future observations. For both model classes the state-of-the-art approaches offer a trade-off between expressive models and computational properties (e.g. speed or convergence properties) and mostly employ variational inference. Our goal is to improve inference in both models by first getting a deep understanding of the existing methods and then, based on this, to design better inference methods. We achieve this by either exploring the existing trade-offs or by providing general improvements applicable to multiple methods. We first provide an extensive background, introducing Gaussian processes and their sparse (approximate and efficient) variants. We continue with a description of the models under consideration in this thesis, deep Gaussian processes and Gaussian process state-space models, including detailed derivations and a theoretical comparison of existing methods. Then we start analysing deep Gaussian processes more closely: Trading off the properties (good optimisation versus expressivity) of state-of-the-art methods in this field, we propose a new variational inference based approach. We then demonstrate experimentally that our new algorithm leads to better calibrated uncertainty estimates than existing methods. Next, we turn our attention to Gaussian process state-space models, where we closely analyse the theoretical properties of existing methods.The understanding gained in this process leads us to propose a new inference scheme for general Gaussian process state-space models that incorporates effects on multiple time scales. This method is more efficient than previous approaches for long timeseries and outperforms its comparison partners on data sets in which effects on multiple time scales (fast and slowly varying dynamics) are present. Finally, we propose a new inference approach for Gaussian process state-space models that trades off the properties of state-of-the-art methods in this field. By combining variational inference with another approximate inference method, the Laplace approximation, we design an efficient algorithm that outperforms its comparison partners since it achieves better calibrated uncertainties.}, language = {en} } @phdthesis{Discher2023, author = {Discher, S{\"o}ren}, title = {Real-Time Rendering Techniques for Massive 3D Point Clouds}, doi = {10.25932/publishup-60164}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-601641}, school = {Universit{\"a}t Potsdam}, pages = {ix, 123}, year = {2023}, abstract = {Today, point clouds are among the most important categories of spatial data, as they constitute digital 3D models of the as-is reality that can be created at unprecedented speed and precision. However, their unique properties, i.e., lack of structure, order, or connectivity information, necessitate specialized data structures and algorithms to leverage their full precision. In particular, this holds true for the interactive visualization of point clouds, which requires to balance hardware limitations regarding GPU memory and bandwidth against a naturally high susceptibility to visual artifacts. This thesis focuses on concepts, techniques, and implementations of robust, scalable, and portable 3D visualization systems for massive point clouds. To that end, a number of rendering, visualization, and interaction techniques are introduced, that extend several basic strategies to decouple rendering efforts and data management: First, a novel visualization technique that facilitates context-aware filtering, highlighting, and interaction within point cloud depictions. Second, hardware-specific optimization techniques that improve rendering performance and image quality in an increasingly diversified hardware landscape. Third, natural and artificial locomotion techniques for nausea-free exploration in the context of state-of-the-art virtual reality devices. Fourth, a framework for web-based rendering that enables collaborative exploration of point clouds across device ecosystems and facilitates the integration into established workflows and software systems. In cooperation with partners from industry and academia, the practicability and robustness of the presented techniques are showcased via several case studies using representative application scenarios and point cloud data sets. In summary, the work shows that the interactive visualization of point clouds can be implemented by a multi-tier software architecture with a number of domain-independent, generic system components that rely on optimization strategies specific to large point clouds. It demonstrates the feasibility of interactive, scalable point cloud visualization as a key component for distributed IT solutions that operate with spatial digital twins, providing arguments in favor of using point clouds as a universal type of spatial base data usable directly for visualization purposes.}, language = {en} } @phdthesis{Kossmann2023, author = {Koßmann, Jan}, title = {Unsupervised database optimization}, doi = {10.25932/publishup-58949}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-589490}, school = {Universit{\"a}t Potsdam}, pages = {xi, 203}, year = {2023}, abstract = {The amount of data stored in databases and the complexity of database workloads are ever- increasing. Database management systems (DBMSs) offer many configuration options, such as index creation or unique constraints, which must be adapted to the specific instance to efficiently process large volumes of data. Currently, such database optimization is complicated, manual work performed by highly skilled database administrators (DBAs). In cloud scenarios, manual database optimization even becomes infeasible: it exceeds the abilities of the best DBAs due to the enormous number of deployed DBMS instances (some providers maintain millions of instances), missing domain knowledge resulting from data privacy requirements, and the complexity of the configuration tasks. Therefore, we investigate how to automate the configuration of DBMSs efficiently with the help of unsupervised database optimization. While there are numerous configuration options, in this thesis, we focus on automatic index selection and the use of data dependencies, such as functional dependencies, for query optimization. Both aspects have an extensive performance impact and complement each other by approaching unsupervised database optimization from different perspectives. Our contributions are as follows: (1) we survey automated state-of-the-art index selection algorithms regarding various criteria, e.g., their support for index interaction. We contribute an extensible platform for evaluating the performance of such algorithms with industry-standard datasets and workloads. The platform is well-received by the community and has led to follow-up research. With our platform, we derive the strengths and weaknesses of the investigated algorithms. We conclude that existing solutions often have scalability issues and cannot quickly determine (near-)optimal solutions for large problem instances. (2) To overcome these limitations, we present two new algorithms. Extend determines (near-)optimal solutions with an iterative heuristic. It identifies the best index configurations for the evaluated benchmarks. Its selection runtimes are up to 10 times lower compared with other near-optimal approaches. SWIRL is based on reinforcement learning and delivers solutions instantly. These solutions perform within 3 \% of the optimal ones. Extend and SWIRL are available as open-source implementations. (3) Our index selection efforts are complemented by a mechanism that analyzes workloads to determine data dependencies for query optimization in an unsupervised fashion. We describe and classify 58 query optimization techniques based on functional, order, and inclusion dependencies as well as on unique column combinations. The unsupervised mechanism and three optimization techniques are implemented in our open-source research DBMS Hyrise. Our approach reduces the Join Order Benchmark's runtime by 26 \% and accelerates some TPC-DS queries by up to 58 times. Additionally, we have developed a cockpit for unsupervised database optimization that allows interactive experiments to build confidence in such automated techniques. In summary, our contributions improve the performance of DBMSs, support DBAs in their work, and enable them to contribute their time to other, less arduous tasks.}, language = {en} } @masterthesis{Repp2023, type = {Bachelor Thesis}, author = {Repp, Leo}, title = {Extending the automatic theorem prover nanoCoP with arithmetic procedures}, doi = {10.25932/publishup-57619}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-576195}, school = {Universit{\"a}t Potsdam}, pages = {52}, year = {2023}, abstract = {In dieser Bachelorarbeit implementiere ich den automatischen Theorembeweiser nanoCoP-Ω. Es handelt sich bei diesem neuen System um das Ergebnis einer Portierung von Arithmetik-behandelnden Prozeduren aus dem automatischen Theorembeweiser mit Arithmetik leanCoP-Ω in das System nanoCoP 2.0. Dazu wird zuerst der mathematische Hintergrund zu automatischen Theorembeweisern und Arithmetik gegeben. Ich stelle die Vorg{\"a}ngerprojekte leanCoP, nanoCoP und leanCoP-Ω vor, auf dessen Vorlage nanoCoP-Ω entwickelt wurde. Es folgt eine ausf{\"u}hrliche Erkl{\"a}rung der Konzepte, um welche der nicht-klausale Konnektionskalk{\"u}l erweitert werden muss, um eine Behandlung von arithmetischen Ausdr{\"u}cken und Gleichheiten in den Kalk{\"u}l zu integrieren, sowie eine Beschreibung der Implementierung dieser Konzepte in nanoCoP-Ω. Als letztes folgt eine experimentelle Evaluation von nanoCoP-Ω. Es wurde ein ausf{\"u}hrlicher Vergleich von Laufzeit und Anzahl gel{\"o}ster Probleme im Vergleich zum {\"a}hnlich aufgebauten Theorembeweiser leanCoP-Ω auf Basis der TPTP-Benchmark durchgef{\"u}hrt. Ich komme zu dem Ergebnis, dass nanoCoP-Ω deutlich schneller ist als leanCoP-Ω ist, jedoch weniger gut geeignet f{\"u}r gr{\"o}ßere Probleme. Zudem konnte ich feststellen, dass nanoCoP-Ω falsche Beweise liefern kann. Ich bespreche, wie dieses Problem gel{\"o}st werden kann, sowie einige m{\"o}gliche Optimierungen und Erweiterungen des Beweissystems.}, language = {en} } @phdthesis{Molitor2023, author = {Molitor, Louise}, title = {Strategic Residential Segregation}, doi = {10.25932/publishup-60135}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-601359}, school = {Universit{\"a}t Potsdam}, pages = {xi, 210}, year = {2023}, abstract = {Residential segregation is a widespread phenomenon that can be observed in almost every major city. In these urban areas, residents with different ethnical or socioeconomic backgrounds tend to form homogeneous clusters. In Schelling's classical segregation model two types of agents are placed on a grid. An agent is content with its location if the fraction of its neighbors, which have the same type as the agent, is at least 𝜏, for some 0 < 𝜏 ≤ 1. Discontent agents simply swap their location with a randomly chosen other discontent agent or jump to a random empty location. The model gives a coherent explanation of how clusters can form even if all agents are tolerant, i.e., if they agree to live in mixed neighborhoods. For segregation to occur, all it needs is a slight bias towards agents preferring similar neighbors. Although the model is well studied, previous research focused on a random process point of view. However, it is more realistic to assume instead that the agents strategically choose where to live. We close this gap by introducing and analyzing game-theoretic models of Schelling segregation, where rational agents strategically choose their locations. As the first step, we introduce and analyze a generalized game-theoretic model that allows more than two agent types and more general underlying graphs modeling the residential area. We introduce different versions of Swap and Jump Schelling Games. Swap Schelling Games assume that every vertex of the underlying graph serving as a residential area is occupied by an agent and pairs of discontent agents can swap their locations, i.e., their occupied vertices, to increase their utility. In contrast, for the Jump Schelling Game, we assume that there exist empty vertices in the graph and agents can jump to these vacant vertices if this increases their utility. We show that the number of agent types as well as the structure of underlying graph heavily influence the dynamic properties and the tractability of finding an optimal strategy profile. As a second step, we significantly deepen these investigations for the swap version with 𝜏 = 1 by studying the influence of the underlying topology modeling the residential area on the existence of equilibria, the Price of Anarchy, and the dynamic properties. Moreover, we restrict the movement of agents locally. As a main takeaway, we find that both aspects influence the existence and the quality of stable states. Furthermore, also for the swap model, we follow sociological surveys and study, asking the same core game-theoretic questions, non-monotone singlepeaked utility functions instead of monotone ones, i.e., utility functions that are not monotone in the fraction of same-type neighbors. Our results clearly show that moving from monotone to non-monotone utilities yields novel structural properties and different results in terms of existence and quality of stable states. In the last part, we introduce an agent-based saturated open-city variant, the Flip Schelling Process, in which agents, based on the predominant type in their neighborhood, decide whether to change their types. We provide a general framework for analyzing the influence of the underlying topology on residential segregation and investigate the probability that an edge is monochrome, i.e., that both incident vertices have the same type, on random geometric and Erdős-R{\´e}nyi graphs. For random geometric graphs, we prove the existence of a constant c > 0 such that the expected fraction of monochrome edges after the Flip Schelling Process is at least 1/2 + c. For Erdős-R{\´e}nyi graphs, we show the expected fraction of monochrome edges after the Flip Schelling Process is at most 1/2 + o(1).}, language = {en} }