@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{VitaglianoHameedJiangetal.2023, author = {Vitagliano, Gerardo and Hameed, Mazhar and Jiang, Lan and Reisener, Lucas and Wu, Eugene and Naumann, Felix}, title = {Pollock: a data loading benchmark}, series = {Proceedings of the VLDB Endowment}, volume = {16}, journal = {Proceedings of the VLDB Endowment}, number = {8}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {2150-8097}, doi = {10.14778/3594512.3594518}, pages = {1870 -- 1882}, year = {2023}, abstract = {Any system at play in a data-driven project has a fundamental requirement: the ability to load data. The de-facto standard format to distribute and consume raw data is CSV. Yet, the plain text and flexible nature of this format make such files often difficult to parse and correctly load their content, requiring cumbersome data preparation steps. We propose a benchmark to assess the robustness of systems in loading data from non-standard CSV formats and with structural inconsistencies. First, we formalize a model to describe the issues that affect real-world files and use it to derive a systematic lpollutionz process to generate dialects for any given grammar. Our benchmark leverages the pollution framework for the csv format. To guide pollution, we have surveyed thousands of real-world, publicly available csv files, recording the problems we encountered. We demonstrate the applicability of our benchmark by testing and scoring 16 different systems: popular csv parsing frameworks, relational database tools, spreadsheet systems, and a data visualization tool.}, language = {en} } @inproceedings{MarxBruenkerMirbabaieetal.2024, author = {Marx, Julian and Br{\"u}nker, Felix and Mirbabaie, Milad and Stieglitz, Stefan}, title = {Digital activism on social media}, series = {Proceedings of the 57th Annual Hawaii International Conference on System Sciences}, booktitle = {Proceedings of the 57th Annual Hawaii International Conference on System Sciences}, editor = {Bui, Tung X.}, publisher = {Department of IT Management Shidler College of Business University of Hawaii}, address = {Honolulu, HI}, isbn = {978-0-99813-317-1}, pages = {7205 -- 7214}, year = {2024}, abstract = {Social media constitute an important arena for public debates and steady interchange of issues relevant to society. To boost their reputation, commercial organizations also engage in political, social, or environmental debates on social media. To engage in this type of digital activism, organizations increasingly utilize the social media profiles of executive employees and other brand ambassadors. However, the relationship between brand ambassadors' digital activism and corporate reputation is only vaguely understood. The results of a qualitative inquiry suggest that digital activism via brand ambassadors can be risky (e.g., creating additional surface for firestorms, financial loss) and rewarding (e.g., emitting authenticity, employing 'megaphones' for industry change) at the same time. The paper informs both scholarship and practitioners about strategic trade-offs that need to be considered when employing brand ambassadors for digital activism.}, language = {en} } @article{FandinoLaferriereRomeroetal.2021, author = {Fandi{\~n}o, Jorge and Laferriere, Francois and Romero, Javier and Schaub, Torsten H. and Son, Tran Cao}, title = {Planning with incomplete information in quantified answer set programming}, series = {Theory and practice of logic programming}, volume = {21}, journal = {Theory and practice of logic programming}, number = {5}, publisher = {Cambridge University Press}, address = {Cambridge}, issn = {1471-0684}, doi = {10.1017/S1471068421000259}, pages = {663 -- 679}, year = {2021}, abstract = {We present a general approach to planning with incomplete information in Answer Set Programming (ASP). More precisely, we consider the problems of conformant and conditional planning with sensing actions and assumptions. We represent planning problems using a simple formalism where logic programs describe the transition function between states, the initial states and the goal states. For solving planning problems, we use Quantified Answer Set Programming (QASP), an extension of ASP with existential and universal quantifiers over atoms that is analogous to Quantified Boolean Formulas (QBFs). We define the language of quantified logic programs and use it to represent the solutions different variants of conformant and conditional planning. On the practical side, we present a translation-based QASP solver that converts quantified logic programs into QBFs and then executes a QBF solver, and we evaluate experimentally the approach on conformant and conditional planning benchmarks.}, language = {en} } @inproceedings{MirbabaieRieskampHofeditzetal.2024, author = {Mirbabaie, Milad and Rieskamp, Jonas and Hofeditz, Lennart and Stieglitz, Stefan}, title = {Breaking down barriers}, series = {Proceedings of the 57th Annual Hawaii International Conference on System Sciences}, booktitle = {Proceedings of the 57th Annual Hawaii International Conference on System Sciences}, editor = {Bui, Tung X.}, publisher = {Department of IT Management Shidler College of Business University of Hawaii}, address = {Honolulu, HI}, isbn = {978-0-99813-317-1}, pages = {672 -- 681}, year = {2024}, abstract = {Many researchers hesitate to provide full access to their datasets due to a lack of knowledge about research data management (RDM) tools and perceived fears, such as losing the value of one's own data. Existing tools and approaches often do not take into account these fears and missing knowledge. In this study, we examined how conversational agents (CAs) can provide a natural way of guidance through RDM processes and nudge researchers towards more data sharing. This work offers an online experiment in which researchers interacted with a CA on a self-developed RDM platform and a survey on participants' data sharing behavior. Our findings indicate that the presence of a guiding and enlightening CA on an RDM platform has a constructive influence on both the intention to share data and the actual behavior of data sharing. Notably, individual factors do not appear to impede or hinder this effect.}, language = {en} } @article{NguyenGeorgieKayhanetal.2021, author = {Nguyen, Dong Hai Phuong and Georgie, Yasmin Kim and Kayhan, Ezgi and Eppe, Manfred and Hafner, Verena Vanessa and Wermter, Stefan}, title = {Sensorimotor representation learning for an "active self" in robots}, series = {K{\"u}nstliche Intelligenz : KI ; Forschung, Entwicklung, Erfahrungen ; Organ des Fachbereichs 1 K{\"u}nstliche Intelligenz der Gesellschaft f{\"u}r Informatik e.V., GI / Fachbereich 1 der Gesellschaft f{\"u}r Informatik e.V}, volume = {35}, journal = {K{\"u}nstliche Intelligenz : KI ; Forschung, Entwicklung, Erfahrungen ; Organ des Fachbereichs 1 K{\"u}nstliche Intelligenz der Gesellschaft f{\"u}r Informatik e.V., GI / Fachbereich 1 der Gesellschaft f{\"u}r Informatik e.V}, number = {1}, publisher = {Springer}, address = {Berlin}, issn = {0933-1875}, doi = {10.1007/s13218-021-00703-z}, pages = {9 -- 35}, year = {2021}, abstract = {Safe human-robot interactions require robots to be able to learn how to behave appropriately in spaces populated by people and thus to cope with the challenges posed by our dynamic and unstructured environment, rather than being provided a rigid set of rules for operations. In humans, these capabilities are thought to be related to our ability to perceive our body in space, sensing the location of our limbs during movement, being aware of other objects and agents, and controlling our body parts to interact with them intentionally. Toward the next generation of robots with bio-inspired capacities, in this paper, we first review the developmental processes of underlying mechanisms of these abilities: The sensory representations of body schema, peripersonal space, and the active self in humans. Second, we provide a survey of robotics models of these sensory representations and robotics models of the self; and we compare these models with the human counterparts. Finally, we analyze what is missing from these robotics models and propose a theoretical computational framework, which aims to allow the emergence of the sense of self in artificial agents by developing sensory representations through self-exploration.}, language = {en} } @phdthesis{Huegle2024, author = {Huegle, Johannes}, title = {Causal discovery in practice: Non-parametric conditional independence testing and tooling for causal discovery}, doi = {10.25932/publishup-63582}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-635820}, school = {Universit{\"a}t Potsdam}, pages = {xiv, 156}, year = {2024}, abstract = {Knowledge about causal structures is crucial for decision support in various domains. For example, in discrete manufacturing, identifying the root causes of failures and quality deviations that interrupt the highly automated production process requires causal structural knowledge. However, in practice, root cause analysis is usually built upon individual expert knowledge about associative relationships. But, "correlation does not imply causation", and misinterpreting associations often leads to incorrect conclusions. Recent developments in methods for causal discovery from observational data have opened the opportunity for a data-driven examination. Despite its potential for data-driven decision support, omnipresent challenges impede causal discovery in real-world scenarios. In this thesis, we make a threefold contribution to improving causal discovery in practice. (1) The growing interest in causal discovery has led to a broad spectrum of methods with specific assumptions on the data and various implementations. Hence, application in practice requires careful consideration of existing methods, which becomes laborious when dealing with various parameters, assumptions, and implementations in different programming languages. Additionally, evaluation is challenging due to the lack of ground truth in practice and limited benchmark data that reflect real-world data characteristics. To address these issues, we present a platform-independent modular pipeline for causal discovery and a ground truth framework for synthetic data generation that provides comprehensive evaluation opportunities, e.g., to examine the accuracy of causal discovery methods in case of inappropriate assumptions. (2) Applying constraint-based methods for causal discovery requires selecting a conditional independence (CI) test, which is particularly challenging in mixed discrete-continuous data omnipresent in many real-world scenarios. In this context, inappropriate assumptions on the data or the commonly applied discretization of continuous variables reduce the accuracy of CI decisions, leading to incorrect causal structures. Therefore, we contribute a non-parametric CI test leveraging k-nearest neighbors methods and prove its statistical validity and power in mixed discrete-continuous data, as well as the asymptotic consistency when used in constraint-based causal discovery. An extensive evaluation of synthetic and real-world data shows that the proposed CI test outperforms state-of-the-art approaches in the accuracy of CI testing and causal discovery, particularly in settings with low sample sizes. (3) To show the applicability and opportunities of causal discovery in practice, we examine our contributions in real-world discrete manufacturing use cases. For example, we showcase how causal structural knowledge helps to understand unforeseen production downtimes or adds decision support in case of failures and quality deviations in automotive body shop assembly lines.}, language = {en} } @book{ZhangPlauthEberhardtetal.2020, author = {Zhang, Shuhao and Plauth, Max and Eberhardt, Felix and Polze, Andreas and Lehmann, Jens and Sejdiu, Gezim and Jabeen, Hajira and Servadei, Lorenzo and M{\"o}stl, Christian and B{\"a}r, Florian and Netzeband, Andr{\´e} and Schmidt, Rainer and Knigge, Marlene and Hecht, Sonja and Prifti, Loina and Krcmar, Helmut and Sapegin, Andrey and Jaeger, David and Cheng, Feng and Meinel, Christoph and Friedrich, Tobias and Rothenberger, Ralf and Sutton, Andrew M. and Sidorova, Julia A. and Lundberg, Lars and Rosander, Oliver and Sk{\"o}ld, Lars and Di Varano, Igor and van der Walt, Est{\´e}e and Eloff, Jan H. P. and Fabian, Benjamin and Baumann, Annika and Ermakova, Tatiana and Kelkel, Stefan and Choudhary, Yash and Cooray, Thilini and Rodr{\´i}guez, Jorge and Medina-P{\´e}rez, Miguel Angel and Trejo, Luis A. and Barrera-Animas, Ari Yair and Monroy-Borja, Ra{\´u}l and L{\´o}pez-Cuevas, Armando and Ram{\´i}rez-M{\´a}rquez, Jos{\´e} Emmanuel and Grohmann, Maria and Niederleithinger, Ernst and Podapati, Sasidhar and Schmidt, Christopher and Huegle, Johannes and de Oliveira, Roberto C. L. and Soares, F{\´a}bio Mendes and van Hoorn, Andr{\´e} and Neumer, Tamas and Willnecker, Felix and Wilhelm, Mathias and Kuster, Bernhard}, title = {HPI Future SOC Lab - Proceedings 2017}, number = {130}, editor = {Meinel, Christoph and Polze, Andreas and Beins, Karsten and Strotmann, Rolf and Seibold, Ulrich and R{\"o}dszus, Kurt and M{\"u}ller, J{\"u}rgen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-475-3}, issn = {1613-5652}, doi = {10.25932/publishup-43310}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-433100}, publisher = {Universit{\"a}t Potsdam}, pages = {ix, 235}, year = {2020}, abstract = {The "HPI Future SOC Lab" is a cooperation of the Hasso Plattner Institute (HPI) and industry partners. Its mission is to enable and promote exchange and interaction between the research community and the industry partners. The HPI Future SOC Lab provides researchers with free of charge access to a complete infrastructure of state of the art hard and software. This infrastructure includes components, which might be too expensive for an ordinary research environment, such as servers with up to 64 cores and 2 TB main memory. The offerings address researchers particularly from but not limited to the areas of computer science and business information systems. Main areas of research include cloud computing, parallelization, and In-Memory technologies. This technical report presents results of research projects executed in 2017. Selected projects have presented their results on April 25th and November 15th 2017 at the Future SOC Lab Day events.}, language = {en} } @phdthesis{Taleb2024, author = {Taleb, Aiham}, title = {Self-supervised deep learning methods for medical image analysis}, doi = {10.25932/publishup-64408}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-644089}, school = {Universit{\"a}t Potsdam}, pages = {xii, 171}, year = {2024}, abstract = {Deep learning has seen widespread application in many domains, mainly for its ability to learn data representations from raw input data. Nevertheless, its success has so far been coupled with the availability of large annotated (labelled) datasets. This is a requirement that is difficult to fulfil in several domains, such as in medical imaging. Annotation costs form a barrier in extending deep learning to clinically-relevant use cases. The labels associated with medical images are scarce, since the generation of expert annotations of multimodal patient data at scale is non-trivial, expensive, and time-consuming. This substantiates the need for algorithms that learn from the increasing amounts of unlabeled data. Self-supervised representation learning algorithms offer a pertinent solution, as they allow solving real-world (downstream) deep learning tasks with fewer annotations. Self-supervised approaches leverage unlabeled samples to acquire generic features about different concepts, enabling annotation-efficient downstream task solving subsequently. Nevertheless, medical images present multiple unique and inherent challenges for existing self-supervised learning approaches, which we seek to address in this thesis: (i) medical images are multimodal, and their multiple modalities are heterogeneous in nature and imbalanced in quantities, e.g. MRI and CT; (ii) medical scans are multi-dimensional, often in 3D instead of 2D; (iii) disease patterns in medical scans are numerous and their incidence exhibits a long-tail distribution, so it is oftentimes essential to fuse knowledge from different data modalities, e.g. genomics or clinical data, to capture disease traits more comprehensively; (iv) Medical scans usually exhibit more uniform color density distributions, e.g. in dental X-Rays, than natural images. Our proposed self-supervised methods meet these challenges, besides significantly reducing the amounts of required annotations. We evaluate our self-supervised methods on a wide array of medical imaging applications and tasks. Our experimental results demonstrate the obtained gains in both annotation-efficiency and performance; our proposed methods outperform many approaches from related literature. Additionally, in case of fusion with genetic modalities, our methods also allow for cross-modal interpretability. In this thesis, not only we show that self-supervised learning is capable of mitigating manual annotation costs, but also our proposed solutions demonstrate how to better utilize it in the medical imaging domain. Progress in self-supervised learning has the potential to extend deep learning algorithms application to clinical scenarios.}, language = {en} } @phdthesis{Richly2024, author = {Richly, Keven}, title = {Memory-efficient data management for spatio-temporal applications}, doi = {10.25932/publishup-63547}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-635473}, school = {Universit{\"a}t Potsdam}, pages = {xii, 181}, year = {2024}, abstract = {The wide distribution of location-acquisition technologies means that large volumes of spatio-temporal data are continuously being accumulated. Positioning systems such as GPS enable the tracking of various moving objects' trajectories, which are usually represented by a chronologically ordered sequence of observed locations. The analysis of movement patterns based on detailed positional information creates opportunities for applications that can improve business decisions and processes in a broad spectrum of industries (e.g., transportation, traffic control, or medicine). Due to the large data volumes generated in these applications, the cost-efficient storage of spatio-temporal data is desirable, especially when in-memory database systems are used to achieve interactive performance requirements. To efficiently utilize the available 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 structures). By considering horizontal data partitioning, we can independently apply different tuning options on a fine-grained level. 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 thesis, we introduce multiple approaches to improve spatio-temporal data management by automatically optimizing diverse tuning options for the application-specific access patterns and data characteristics. Our contributions are as follows: (1) We introduce a novel approach to determine fine-grained table configurations for spatio-temporal workloads. Our linear programming (LP) approach jointly optimizes the (i) data compression, (ii) ordering, (iii) indexing, and (iv) tiering. We propose different models which address cost dependencies at different levels of accuracy to compute optimized tuning configurations for a given workload, memory budgets, and data characteristics. To yield maintainable and robust configurations, we further extend our LP-based approach to incorporate reconfiguration costs as well as optimizations for multiple potential workload scenarios. (2) To optimize the storage layout of timestamps in columnar databases, we present a heuristic approach for the workload-driven combined selection of a data layout and compression scheme. By considering attribute decomposition strategies, we are able to apply application-specific optimizations that reduce the memory footprint and improve performance. (3) We introduce an approach that leverages past trajectory data to improve the dispatch processes of transportation network companies. Based on location probabilities, we developed risk-averse dispatch strategies that reduce critical delays. (4) Finally, we used the use case of a transportation network company to evaluate our database optimizations on a real-world dataset. We demonstrate that workload-driven fine-grained optimizations allow us to reduce the memory footprint (up to 71\% by equal performance) or increase the performance (up to 90\% by equal memory size) compared to established rule-based heuristics. Individually, our contributions provide novel approaches to the current challenges in spatio-temporal data mining and database research. Combining them allows in-memory databases to store and process spatio-temporal data more cost-efficiently.}, language = {en} }