@phdthesis{Vitagliano2024,
  author    = {Vitagliano, Gerardo},
  title     = {Modeling the structure of tabular files for data preparation},
  doi       = {10.25932/publishup-62435},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-624351},
  school      = {Universit{\"a}t Potsdam},
  pages     = {ii, 114},
  year      = {2024},
  abstract  = {To manage tabular data files and leverage their content in a given downstream task, practitioners often design and execute complex transformation pipelines to prepare them. The complexity of such pipelines stems from different factors, including the nature of the preparation tasks, often exploratory or ad-hoc to specific datasets; the large repertory of tools, algorithms, and frameworks that practitioners need to master; and the volume, variety, and velocity of the files to be prepared. Metadata plays a fundamental role in reducing this complexity: characterizing a file assists end users in the design of data preprocessing pipelines, and furthermore paves the way for suggestion, automation, and optimization of data preparation tasks. Previous research in the areas of data profiling, data integration, and data cleaning, has focused on extracting and characterizing metadata regarding the content of tabular data files, i.e., about the records and attributes of tables. Content metadata are useful for the latter stages of a preprocessing pipeline, e.g., error correction, duplicate detection, or value normalization, but they require a properly formed tabular input. Therefore, these metadata are not relevant for the early stages of a preparation pipeline, i.e., to correctly parse tables out of files. In this dissertation, we turn our focus to what we call the structure of a tabular data file, i.e., the set of characters within a file that do not represent data values but are required to parse and understand the content of the file. We provide three different approaches to represent file structure, an explicit representation based on context-free grammars; an implicit representation based on file-wise similarity; and a learned representation based on machine learning. In our first contribution, we use the grammar-based representation to characterize a set of over 3000 real-world csv files and identify multiple structural issues that let files deviate from the csv standard, e.g., by having inconsistent delimiters or containing multiple tables. We leverage our learnings about real-world files and propose Pollock, a benchmark to test how well systems parse csv files that have a non-standard structure, without any previous preparation. We report on our experiments on using Pollock to evaluate the performance of 16 real-world data management systems. Following, we characterize the structure of files implicitly, by defining a measure of structural similarity for file pairs. We design a novel algorithm to compute this measure, which is based on a graph representation of the files' content. We leverage this algorithm and propose Mondrian, a graphical system to assist users in identifying layout templates in a dataset, classes of files that have the same structure, and therefore can be prepared by applying the same preparation pipeline. Finally, we introduce MaGRiTTE, a novel architecture that uses self-supervised learning to automatically learn structural representations of files in the form of vectorial embeddings at three different levels: cell level, row level, and file level. We experiment with the application of structural embeddings for several tasks, namely dialect detection, row classification, and data preparation efforts estimation. Our experimental results show that structural metadata, either identified explicitly on parsing grammars, derived implicitly as file-wise similarity, or learned with the help of machine learning architectures, is fundamental to automate several tasks, to scale up preparation to large quantities of files, and to provide repeatable preparation pipelines.},
  language  = {en}
}
@phdthesis{Halfpap2024,
  author    = {Halfpap, Stefan},
  title     = {Integer linear programming-based heuristics for partially replicated database clusters and selecting indexes},
  doi       = {10.25932/publishup-63361},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-633615},
  school      = {Universit{\"a}t Potsdam},
  pages     = {iii, 185},
  year      = {2024},
  abstract  = {Column-oriented database systems can efficiently process transactional and analytical queries on a single node. However, increasing or peak analytical loads can quickly saturate single-node database systems. Then, a common scale-out option is using a database cluster with a single primary node for transaction processing and read-only replicas. Using (the naive) full replication, queries are distributed among nodes independently of the accessed data. This approach is relatively expensive because all nodes must store all data and apply all data modifications caused by inserts, deletes, or updates. In contrast to full replication, partial replication is a more cost-efficient implementation: Instead of duplicating all data to all replica nodes, partial replicas store only a subset of the data while being able to process a large workload share. Besides lower storage costs, partial replicas enable (i) better scaling because replicas must potentially synchronize only subsets of the data modifications and thus have more capacity for read-only queries and (ii) better elasticity because replicas have to load less data and can be set up faster. However, splitting the overall workload evenly among the replica nodes while optimizing the data allocation is a challenging assignment problem. The calculation of optimized data allocations in a partially replicated database cluster can be modeled using integer linear programming (ILP). ILP is a common approach for solving assignment problems, also in the context of database systems. Because ILP is not scalable, existing approaches (also for calculating partial allocations) often fall back to simple (e.g., greedy) heuristics for larger problem instances. Simple heuristics may work well but can lose optimization potential. In this thesis, we present optimal and ILP-based heuristic programming models for calculating data fragment allocations for partially replicated database clusters. Using ILP, we are flexible to extend our models to (i) consider data modifications and reallocations and (ii) increase the robustness of allocations to compensate for node failures and workload uncertainty. We evaluate our approaches for TPC-H, TPC-DS, and a real-world accounting workload and compare the results to state-of-the-art allocation approaches. Our evaluations show significant improvements for varied allocation's properties: Compared to existing approaches, we can, for example, (i) almost halve the amount of allocated data, (ii) improve the throughput in case of node failures and workload uncertainty while using even less memory, (iii) halve the costs of data modifications, and (iv) reallocate less than 90\% of data when adding a node to the cluster. Importantly, we can calculate the corresponding ILP-based heuristic solutions within a few seconds. Finally, we demonstrate that the ideas of our ILP-based heuristics are also applicable to the index selection problem.},
  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}
}
@inproceedings{RojahnGronau2024,
  author    = {Rojahn, Marcel and Gronau, Norbert},
  title     = {Openness indicators for the evaluation of digital platforms between the launch and maturity phase},
  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     = {4516 -- 4525},
  year      = {2024},
  abstract  = {In recent years, the evaluation of digital platforms has become an important focus in the field of information systems science. The identification of influential indicators that drive changes in digital platforms, specifically those related to openness, is still an unresolved issue. This paper addresses the challenge of identifying measurable indicators and characterizing the transition from launch to maturity in digital platforms. It proposes a systematic analytical approach to identify relevant openness indicators for evaluation purposes. The main contributions of this study are the following (1) the development of a comprehensive procedure for analyzing indicators, (2) the categorization of indicators as evaluation metrics within a multidimensional grid-box model, (3) the selection and evaluation of relevant indicators, (4) the identification and assessment of digital platform architectures during the launch-to-maturity transition, and (5) the evaluation of the applicability of the conceptualization and design process for digital platform evaluation.},
  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}
}
@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{XinYingTiberiusAlnooretal.2024,
  author    = {XinYing, Chew and Tiberius, Victor and Alnoor, Alhamzah and Camilleri, Mark and Khaw, Khai Wah},
  title     = {The dark side of metaverse: a multi-perspective of deviant behaviors from PLS-SEM and fsQCA findings},
  series = {International journal of human-computer interaction},
  journal   = {International journal of human-computer interaction},
  publisher = {Taylor \& Francis},
  address   = {London},
  issn      = {1044-7318},
  doi       = {10.1080/10447318.2024.2331875},
  pages     = {21},
  year      = {2024},
  abstract  = {The metaverse has created a huge buzz of interest because such a phenomenon is emerging. The behavioral aspect of the metaverse includes user engagement and deviant behaviors in the metaverse. Such technology has brought various dangers to individuals and society. There are growing cases reported of sexual abuse, racism, harassment, hate speech, and bullying because of online disinhibition make us feel more relaxed. This study responded to the literature call by investigating the effect of technical and social features through mediating roles of security and privacy on deviant behaviors in the metaverse. The data collected from virtual network users reached 1121 respondents. Partial Least Squares based structural equation modeling (PLS-SEM) and fuzzy set Qualitative Comparative Analysis (fsQCA) were used. PLS-SEM results revealed that social features such as user-to-user interaction, homophily, social ties, and social identity, and technical design such as immersive experience and invisibility significantly affect users' deviant behavior in the metaverse. The fsQCA results provided insights into the multiple causal solutions and configurations. This study is exceptional because it provided decisive results by understanding the deviant behavior of users based on the symmetrical and asymmetrical approach to virtual networks.},
  language  = {en}
}
@article{KuehlerDrathschmidtGrossmann2024,
  author    = {K{\"u}hler, Jakob and Drathschmidt, Nicolas and Großmann, Daniela},
  title     = {'Modern talking'},
  series = {Information polity},
  volume    = {29},
  journal   = {Information polity},
  number    = {2},
  publisher = {IOS Press},
  address   = {Amsterdam},
  issn      = {1570-1255},
  doi       = {10.3233/IP-230059},
  pages     = {199 -- 216},
  year      = {2024},
  abstract  = {Despite growing interest, we lack a clear understanding of how the arguably ambiguous phenomenon of agile is perceived in government practice. This study aims to alleviate this puzzle by investigating how managers and employees in German public sector organisations make sense of agile as a spreading management fashion in the form of narratives. This is important because narratives function as innovation carriers that ultimately influence the manifestations of the concept in organisations. Based on a multi-case study of 31 interviews and 24 responses to a qualitative online survey conducted in 2021 and 2022, we provide insights into what public sector managers, employees and consultants understand (and, more importantly, do not understand) as agile and how they weave it into their existing reality of bureaucratic organisations. We uncover three meta-narratives of agile government, which we label 'renew', 'complement' and 'integrate'. In particular, the meta-narratives differ in their positioning of how agile interacts with the characteristics of bureaucratic organisations. Importantly, we also show that agile as a management fad serves as a projection surface for what actors want from a modern and digital organisation. Thus, the vocabulary of agile government within the narratives is inherently linked to other diffusing phenomena such as new work or digitalisation.},
  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}
}
@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}
}
@phdthesis{Doskoč2023,
  author    = {Doskoč, Vanja},
  title     = {Mapping restrictions in behaviourally correct learning},
  doi       = {10.25932/publishup-59311},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-593110},
  school      = {Universit{\"a}t Potsdam},
  pages     = {ix, 74},
  year      = {2023},
  abstract  = {In this thesis, we investigate language learning in the formalisation of Gold [Gol67]. Here, a learner, being successively presented all information of a target language, conjectures which language it believes to be shown. Once these hypotheses converge syntactically to a correct explanation of the target language, the learning is considered successful. Fittingly, this is termed explanatory learning. To model learning strategies, we impose restrictions on the hypotheses made, for example requiring the conjectures to follow a monotonic behaviour. This way, we can study the impact a certain restriction has on learning. Recently, the literature shifted towards map charting. Here, various seemingly unrelated restrictions are contrasted, unveiling interesting relations between them. The results are then depicted in maps. For explanatory learning, the literature already provides maps of common restrictions for various forms of data presentation. In the case of behaviourally correct learning, where the learners are required to converge semantically instead of syntactically, the same restrictions as in explanatory learning have been investigated. However, a similarly complete picture regarding their interaction has not been presented yet. In this thesis, we transfer the map charting approach to behaviourally correct learning. In particular, we complete the partial results from the literature for many well-studied restrictions and provide full maps for behaviourally correct learning with different types of data presentation. We also study properties of learners assessed important in the literature. We are interested whether learners are consistent, that is, whether their conjectures include the data they are built on. While learners cannot be assumed consistent in explanatory learning, the opposite is the case in behaviourally correct learning. Even further, it is known that learners following different restrictions may be assumed consistent. We contribute to the literature by showing that this is the case for all studied restrictions. We also investigate mathematically interesting properties of learners. In particular, we are interested in whether learning under a given restriction may be done with strongly Bc-locking learners. Such learners are of particular value as they allow to apply simulation arguments when, for example, comparing two learning paradigms to each other. The literature gives a rich ground on when learners may be assumed strongly Bc-locking, which we complete for all studied restrictions.},
  language  = {en}
}
@phdthesis{Hagedorn2023,
  author    = {Hagedorn, Christopher},
  title     = {Parallel execution of causal structure learning on graphics processing units},
  doi       = {10.25932/publishup-59758},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-597582},
  school      = {Universit{\"a}t Potsdam},
  pages     = {8, 192},
  year      = {2023},
  abstract  = {Learning the causal structures from observational data is an omnipresent challenge in data science. The amount of observational data available to Causal Structure Learning (CSL) algorithms is increasing as data is collected at high frequency from many data sources nowadays. While processing more data generally yields higher accuracy in CSL, the concomitant increase in the runtime of CSL algorithms hinders their widespread adoption in practice. CSL is a parallelizable problem. Existing parallel CSL algorithms address execution on multi-core Central Processing Units (CPUs) with dozens of compute cores. However, modern computing systems are often heterogeneous and equipped with Graphics Processing Units (GPUs) to accelerate computations. Typically, these GPUs provide several thousand compute cores for massively parallel data processing. To shorten the runtime of CSL algorithms, we design efficient execution strategies that leverage the parallel processing power of GPUs. Particularly, we derive GPU-accelerated variants of a well-known constraint-based CSL method, the PC algorithm, as it allows choosing a statistical Conditional Independence test (CI test) appropriate to the observational data characteristics. Our two main contributions are: (1) to reflect differences in the CI tests, we design three GPU-based variants of the PC algorithm tailored to CI tests that handle data with the following characteristics. We develop one variant for data assuming the Gaussian distribution model, one for discrete data, and another for mixed discrete-continuous data and data with non-linear relationships. Each variant is optimized for the appropriate CI test leveraging GPU hardware properties, such as shared or thread-local memory. Our GPU-accelerated variants outperform state-of-the-art parallel CPU-based algorithms by factors of up to 93.4× for data assuming the Gaussian distribution model, up to 54.3× for discrete data, up to 240× for continuous data with non-linear relationships and up to 655× for mixed discrete-continuous data. However, the proposed GPU-based variants are limited to datasets that fit into a single GPU's memory. (2) To overcome this shortcoming, we develop approaches to scale our GPU-based variants beyond a single GPU's memory capacity. For example, we design an out-of-core GPU variant that employs explicit memory management to process arbitrary-sized datasets. Runtime measurements on a large gene expression dataset reveal that our out-of-core GPU variant is 364 times faster than a parallel CPU-based CSL algorithm. Overall, our proposed GPU-accelerated variants speed up CSL in numerous settings to foster CSL's adoption in practice and research.},
  language  = {en}
}
@book{BarkowskyGiese2023,
  author    = {Barkowsky, Matthias and Giese, Holger},
  title     = {Modular and incremental global model management with extended generalized discrimination networks},
  number    = {154},
  isbn      = {978-3-86956-555-2},
  issn      = {1613-5652},
  doi       = {10.25932/publishup-57396},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-573965},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {63 -- 63},
  year      = {2023},
  abstract  = {Complex projects developed under the model-driven engineering paradigm nowadays often involve several interrelated models, which are automatically processed via a multitude of model operations. Modular and incremental construction and execution of such networks of models and model operations are required to accommodate efficient development with potentially large-scale models. The underlying problem is also called Global Model Management. In this report, we propose an approach to modular and incremental Global Model Management via an extension to the existing technique of Generalized Discrimination Networks (GDNs). In addition to further generalizing the notion of query operations employed in GDNs, we adapt the previously query-only mechanism to operations with side effects to integrate model transformation and model synchronization. We provide incremental algorithms for the execution of the resulting extended Generalized Discrimination Networks (eGDNs), as well as a prototypical implementation for a number of example eGDN operations. Based on this prototypical implementation, we experiment with an application scenario from the software development domain to empirically evaluate our approach with respect to scalability and conceptually demonstrate its applicability in a typical scenario. Initial results confirm that the presented approach can indeed be employed to realize efficient Global Model Management in the considered scenario.},
  language  = {en}
}
@phdthesis{Shekhar2023,
  author    = {Shekhar, Sumit},
  title     = {Image and video processing based on intrinsic attributes},
  doi       = {10.25932/publishup-62004},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-620049},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xii, 143},
  year      = {2023},
  abstract  = {Advancements in computer vision techniques driven by machine learning have facilitated robust and efficient estimation of attributes such as depth, optical flow, albedo, and shading. To encapsulate all such underlying properties associated with images and videos, we evolve the concept of intrinsic images towards intrinsic attributes. Further, rapid hardware growth in the form of high-quality smartphone cameras, readily available depth sensors, mobile GPUs, or dedicated neural processing units have made image and video processing pervasive. In this thesis, we explore the synergies between the above two advancements and propose novel image and video processing techniques and systems based on them. To begin with, we investigate intrinsic image decomposition approaches and analyze how they can be implemented on mobile devices. We propose an approach that considers not only diffuse reflection but also specular reflection; it allows us to decompose an image into specularity, albedo, and shading on a resource constrained system (e.g., smartphones or tablets) using the depth data provided by the built-in depth sensors. In addition, we explore how on-device depth data can further be used to add an immersive dimension to 2D photos, e.g., showcasing parallax effects via 3D photography. In this regard, we develop a novel system for interactive 3D photo generation and stylization on mobile devices. Further, we investigate how adaptive manipulation of baseline-albedo (i.e., chromaticity) can be used for efficient visual enhancement under low-lighting conditions. The proposed technique allows for interactive editing of enhancement settings while achieving improved quality and performance. We analyze the inherent optical flow and temporal noise as intrinsic properties of a video. We further propose two new techniques for applying the above intrinsic attributes for the purpose of consistent video filtering. To this end, we investigate how to remove temporal inconsistencies perceived as flickering artifacts. One of the techniques does not require costly optical flow estimation, while both provide interactive consistency control. Using intrinsic attributes for image and video processing enables new solutions for mobile devices - a pervasive visual computing device - and will facilitate novel applications for Augmented Reality (AR), 3D photography, and video stylization. The proposed low-light enhancement techniques can also improve the accuracy of high-level computer vision tasks (e.g., face detection) under low-light conditions. Finally, our approach for consistent video filtering can extend a wide range of image-based processing for videos.},
  language  = {en}
}
@inproceedings{DeselOpelSiegerisetal.2023,
  author    = {Desel, J{\"o}rg and Opel, Simone and Siegeris, Juliane and Draude, Claude and Weber, Gerhard and Schell, Timon and Schwill, Andreas and Thorbr{\"u}gge, Carsten and Sch{\"a}fer, Len Ole and Netzer, Cajus Marian and Gerstenberger, Dietrich and Winkelnkemper, Felix and Schulte, Carsten and B{\"o}ttcher, Axel and Thurner, Veronika and H{\"a}fner, Tanja and Ottinger, Sarah and Große-B{\"o}lting, Gregor and Scheppach, Lukas and M{\"u}hling, Andreas and Baberowski, David and Leonhardt, Thiemo and Rentsch, Susanne and Bergner, Nadine and Bonorden, Leif and Stemme, Jonas and Hoppe, Uwe and Weicker, Karsten and Bender, Esther and Barbas, Helena and Hamann, Fabian and Soll, Marcus and Sitzmann, Daniel},
  title     = {Hochschuldidaktik Informatik HDI 2021},
  series = {Commentarii informaticae didacticae},
  booktitle = {Commentarii informaticae didacticae},
  number    = {13},
  editor    = {Desel, J{\"o}rg and Opel, Simone and Siegeris, Juliane},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-548-4},
  issn      = {1868-0844},
  doi       = {10.25932/publishup-56507},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-565070},
  pages     = {299},
  year      = {2023},
  abstract  = {Die Fachtagungen HDI (Hochschuldidaktik Informatik) besch{\"a}ftigen sich mit den unterschiedlichen Aspekten informatischer Bildung im Hochschulbereich. Neben den allgemeinen Themen wie verschiedenen Lehr- und Lernformen, dem Einsatz von Informatiksystemen in der Hochschullehre oder Fragen der Gewinnung von geeigneten Studierenden, deren Kompetenzerwerb oder auch der Betreuung der Studierenden widmet sich die HDI immer auch einem Schwerpunktthema. Im Jahr 2021 war dies die Ber{\"u}cksichtigung von Diversit{\"a}t in der Lehre. Diskutiert wurden beispielsweise die Einbeziehung von besonderen fachlichen und {\"u}berfachlichen Kompetenzen Studierender, der Unterst{\"u}tzung von Durchl{\"a}ssigkeit aus nichtakademischen Berufen, aber auch die Gestaltung inklusiver Lehr- und Lernszenarios, Aspekte des Lebenslangen Lernens oder sich an die Diversit{\"a}t von Studierenden adaptierte oder adaptierende Lehrsysteme. Dieser Band enth{\"a}lt ausgew{\"a}hlte Beitr{\"a}ge der 9. Fachtagung 2021, die in besonderer Weise die Konferenz und die dort diskutierten Themen repr{\"a}sentieren.},
  language  = {de}
}
@inproceedings{RojahnGronau2023,
  author    = {Rojahn, Marcel and Gronau, Norbert},
  title     = {Digital platform concepts for manufacturing companies},
  series = {10th International Conference on Future Internet of Things and Cloud (FiCloud)},
  booktitle = {10th International Conference on Future Internet of Things and Cloud (FiCloud)},
  publisher = {IEEE},
  address   = {[Erscheinungsort nicht ermittelbar]},
  isbn      = {979-8-3503-1635-3},
  doi       = {10.1109/FiCloud58648.2023.00030},
  pages     = {149 -- 158},
  year      = {2023},
  abstract  = {Digital Platforms (DPs) has established themself in recent years as a central concept of the Information Technology Science. Due to the great diversity of digital platform concepts, clear definitions are still required. Furthermore, DPs are subject to dynamic changes from internal and external factors, which pose challenges for digital platform operators, developers and customers. Which current digital platform research directions should be taken to address these challenges remains open so far. The following paper aims to contribute to this by outlining a systematic literature review (SLR) on digital platform concepts in the context of the Industrial Internet of Things (IIoT) for manufacturing companies and provides a basis for (1) a selection of definitions of current digital platform and ecosystem concepts and (2) a selection of current digital platform research directions. These directions are diverted into (a) occurrence of digital platforms, (b) emergence of digital platforms, (c) evaluation of digital platforms, (d) development of digital platforms, and (e) selection of digital platforms.},
  language  = {en}
}
@article{MarxStieglitzBruenkeretal.2023,
  author    = {Marx, Julian and Stieglitz, Stefan and Br{\"u}nker, Felix and Mirbabaie, Milad},
  title     = {Home (office) is where your heart is},
  series = {Business \& information systems engineering},
  volume    = {65},
  journal   = {Business \& information systems engineering},
  number    = {3},
  publisher = {Springer Gabler},
  address   = {Wiesbaden},
  issn      = {2363-7005},
  doi       = {10.1007/s12599-023-00807-w},
  pages     = {293 -- 308},
  year      = {2023},
  abstract  = {Working conditions of knowledge workers have been subject to rapid change recently. Digital nomadism is no longer a phenomenon that relates only to entrepreneurs, freelancers, and gig workers. Corporate employees, too, have begun to uncouple their work from stationary (home) offices and 9-to-5 schedules. However, pursuing a permanent job in a corporate environment is still subject to fundamentally different values than postulated by the original notion of digital nomadism. Therefore, this paper explores the work identity of what is referred to as 'corporate nomads'. By drawing on identity theory and the results of semi-structured interviews, the paper proposes a conceptualization of the corporate nomad archetype and presents nine salient identity issues of corporate nomads (e.g., holding multiple contradictory identities, the flexibility paradox, or collaboration constraints). By introducing the 'corporate nomad' archetype to the Information Systems literature, this article helps to rethink established conceptions of "home office" and socio-spatial configurations of knowledge work.},
  language  = {en}
}
@article{HofeditzMirbabaieOrtmann2023,
  author    = {Hofeditz, Lennart and Mirbabaie, Milad and Ortmann, Mara},
  title     = {Ethical challenges for human-agent interaction in virtual collaboration at work},
  series = {International journal of human computer interaction},
  journal   = {International journal of human computer interaction},
  publisher = {Taylor \& Francis},
  address   = {New York, NY},
  issn      = {1044-7318},
  doi       = {10.1080/10447318.2023.2279400},
  pages     = {17},
  year      = {2023},
  abstract  = {In virtual collaboration at the workplace, a growing number of teams apply supportive conversational agents (CAs). They take on different work-related tasks for teams and single users such as scheduling meetings or stimulating creativity. Previous research merely focused on these positive aspects of introducing CAs at the workplace, omitting ethical challenges faced by teams using these often artificial intelligence (AI)-enabled technologies. Thus, on the one hand, CAs can present themselves as benevolent teammates, but on the other hand, they can collect user data, reduce worker autonomy, or foster social isolation by their service. In this work, we conducted 15 expert interviews with senior researchers from the fields of ethics, collaboration, and computer science in order to derive ethical guidelines for introducing CAs in virtual team collaboration. We derived 14 guidelines and seven research questions to pave the way for future research on the dark sides of human-agent interaction in organizations.},
  language  = {en}
}
@article{BruenkerMarxMirbabaieetal.2023,
  author    = {Br{\"u}nker, Felix and Marx, Julian and Mirbabaie, Milad and Stieglitz, Stefan},
  title     = {Proactive digital workplace transformation},
  series = {Journal of information technology},
  journal   = {Journal of information technology},
  publisher = {Sage Publishing},
  address   = {London},
  issn      = {0268-3962},
  doi       = {10.1177/02683962231219516},
  pages     = {19},
  year      = {2023},
  abstract  = {Digital transformation fundamentally changes the way individuals conduct work in organisations. In accordance with this statement, prevalent literature understands digital workplace transformation as a second-order effect of implementing new information technology to increase organisational effectiveness or reach other strategic goals. This paper, in contrast, provides empirical evidence from two remote-first organisations that undergo a proactive rather than reactive digital workplace transformation. The analysis of these cases suggests that new ways of working can be the consequence of an identity change that is a precondition for introducing new information technology rather than its outcome. The resulting process model contributes a competing argument to the existing debate in digital transformation literature. Instead of issuing digital workplace transformation as a deliverable of technological progress and strategic goals, this paper supports a notion of digital workplace transformation that serves a desired identity based on work preferences.},
  language  = {en}
}
@article{Draude2023,
  author    = {Draude, Claude},
  title     = {Working with Diversity in Informatics},
  series = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  journal   = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  number    = {13},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-548-4},
  issn      = {1868-0844},
  doi       = {10.25932/publishup-61378},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-613787},
  pages     = {13 -- 33},
  year      = {2023},
  abstract  = {Diversity is a term that is broadly used and challenging for informatics research, development and education. Diversity concerns may relate to unequal participation, knowledge and methodology, curricula, institutional planning etc. For a lot of these areas, measures, guidelines and best practices on diversity awareness exist. A systemic, sustainable impact of diversity measures on informatics is still largely missing. In this paper I explore what working with diversity and gender concepts in informatics entails, what the main challenges are and provide thoughts for improvement. The paper includes definitions of diversity and intersectionality, reflections on the disciplinary basis of informatics and practical implications of integrating diversity in informatics research and development. In the final part, two concepts from the social sciences and the humanities, the notion of "third space"/hybridity and the notion of "feminist ethics of care", serve as a lens to foster more sustainable ways of working with diversity in informatics.},
  language  = {en}
}
@article{GerstenbergerWinkelnkemperSchulte2023,
  author    = {Gerstenberger, Dietrich and Winkelnkemper, Felix and Schulte, Carsten},
  title     = {Nutzung der Personas-Methode zum Umgang mit der Heterogenit{\"a}t von Informatikstudierenden},
  series = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  journal   = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  number    = {13},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-548-4},
  issn      = {1868-0844},
  doi       = {10.25932/publishup-61568},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-615682},
  pages     = {117 -- 135},
  year      = {2023},
  abstract  = {Informatikstudieng{\"a}nge verzeichnen hohe Abbruchquoten innerhalb der ersten beiden Semester, die h{\"a}ufig mit Leistungsdefiziten oder Motivationsproblemen begr{\"u}ndet werden. Eine Ursache daf{\"u}r, dass trotz intensiver Bem{\"u}hungen um bessere Lehre und motivationsf{\"o}rdernde Maßnahmen diese Situation imWesentlichen unver{\"a}ndert bleibt, k{\"o}nnte darin liegen, dass nicht die eine Maßnahme oder der eine Ansatz das Problem im Ganzen l{\"o}sen kann, sondern dass eine heterogene Studierendenschaft vielmehr nach unterschiedlichen Maßnahmen verlangt. Bisher findet sich wenig Forschung zu differenzierten Studierendentypen in der Informatik. Wir stellen in dieser Arbeit einen Ansatz daf{\"u}r vor, die Heterogenit{\"a}t der Informatikstudierenden zu ergr{\"u}nden, und beschreiben die Ergebnisse erster Versuche mit diesem Ansatz. Um die große Anzahl von Studierenden auf eine {\"u}berschaubare Anzahl von Typen mit jeweils {\"a}hnlichen Bed{\"u}rfnissen und Erwartungen zu reduzieren, wird dazu die im Produktmanagement bew{\"a}hrte Personas-Methode adaptiert. Im Rahmen einer Befragung von 170 Informatikstudierenden konnten hierzu bereits einige Personas mit unterschiedlichen Merkmalsh{\"a}ufungen ausgearbeitet werden, die eine gute Grundlage darstellen, um auf dieser Basis differenzierte Interventionen zur F{\"o}rderung und Motivation der Informatikstudierenden zu entwickeln.},
  language  = {de}
}
@article{Bonorden2023,
  author    = {Bonorden, Leif},
  title     = {Forschendes Lernen im Bachelorseminar „Software Engineering"},
  series = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  journal   = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  number    = {13},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-548-4},
  issn      = {1868-0844},
  doi       = {10.25932/publishup-61600},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-616009},
  pages     = {213 -- 230},
  year      = {2023},
  abstract  = {Forschendes Lernen ist eine Lehr-Lernform, in der Studierende einen eigenen Forschungsprozess vollst{\"a}ndig durchlaufen. In Informatikstudieng{\"a}ngen und insbesondere in Informatikbachelorstudieng{\"a}ngen ist die Forschungsorientierung allerdings nur gering ausgepr{\"a}gt: Forschendes Lernen wird kaum eingesetzt, obwohl dies m{\"o}glich und sinnvoll ist. Dieser Artikel stellt ein Konzept f{\"u}r ein Seminar Software Engineering im Bachelorstudium vor und beschreibt dessen Durchf{\"u}hrung. Abschließend wird das Konzept diskutiert und sowohl aus Studierenden- als auch aus Lehrendensicht positiv evaluiert.},
  language  = {de}
}
@article{GrosseBoeltingScheppachMuehling2023,
  author    = {Große-B{\"o}lting, Gregor and Scheppach, Lukas and M{\"u}hling, Andreas},
  title     = {The Place of Ethics in Computer Science Education},
  series = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  journal   = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  number    = {13},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-548-4},
  issn      = {1868-0844},
  doi       = {10.25932/publishup-61598},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-615982},
  pages     = {173 -- 187},
  year      = {2023},
  abstract  = {Ethical issues surrounding modern computing technologies play an increasingly important role in the public debate. Yet, ethics still either doesn't appear at all or only to a very small extent in computer science degree programs. This paper provides an argument for the value of ethics beyond a pure responsibility perspective and describes the positive value of ethical debate for future computer scientists. It also provides a systematic analysis of the module handbooks of 67 German universities and shows that there is indeed a lack of ethics in computer science education. Finally, we present a principled design of a compulsory course for undergraduate students.},
  language  = {en}
}
@article{BenderBarbasHamannetal.2023,
  author    = {Bender, Esther and Barbas, Helena and Hamann, Fabian and Soll, Marcus and Sitzmann, Daniel},
  title     = {F{\"a}higkeiten und Kenntnisse bei Studienanf{\"a}nger*innen in der Informatik: Was erwarten die Dozent*innen?},
  series = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  journal   = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  number    = {13},
  isbn      = {978-3-86956-548-4},
  issn      = {1868-0844},
  doi       = {10.25932/publishup-61603},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-616039},
  pages     = {279 -- 299},
  year      = {2023},
  abstract  = {Viele Studieneingangs- und Eignungstests haben zum Ziel, f{\"u}r den entsprechenden Studiengang geeignete Studierende zu finden, die das Studium erfolgreich beenden k{\"o}nnen. Gerade in der Informatik ist aber h{\"a}ufig unklar, welche Eigenschaften geeignete Studierende haben sollten - auch stimmen mutmaßlich nicht alle Dozierenden in ihren Erwartungen an Studienanf{\"a}nger*innen {\"u}berein; Untersuchungen hierzu fehlen jedoch bislang. Um die Erwartungen von Dozent*innen an Studienanf{\"a}nger*innen im Fach Informatik an deutschen Hochschulen zu analysieren, hat das Projekt MINTFIT im Sommer 2019 eine deutschlandweite Online-Befragung durchgef{\"u}hrt, an der 588 Hochschuldozent* innen aus allen Bundesl{\"a}ndern teilnahmen. Die Umfrage hat gezeigt, dass {\"u}berwiegend allgemeine F{\"a}higkeiten, wie Motivation und logisches Denkverm{\"o}gen, und nur wenig fachliches Vorwissen, wie Programmieren oder Formale Sprache, erwartet wird. Nach Einsch{\"a}tzung der Dozent*innen sind die problembehafteten Bereiche {\"u}berwiegend in der theoretischen Informatik und in formellen Aspekten (z. B. Formale Sprache) zu finden. Obwohl Tendenzen erkennbar sind, zeigt die Umfrage, dass bei Anwendung strenger Akzeptanzkriterien keine F{\"a}higkeiten und Kenntnisse explizit vorausgesetzt werden, was darauf hindeutet, dass noch kein deutschlandweiter Konsens unter den Lehrenden vorhanden ist.},
  language  = {de}
}
@book{SchwarzerWeissSaoumiKitteletal.2023,
  author    = {Schwarzer, Ingo and Weiß-Saoumi, Said and Kittel, Roland and Friedrich, Tobias and Kaynak, Koraltan and Durak, Cemil and Isbarn, Andreas and Diestel, J{\"o}rg and Knittel, Jens and Franz, Marquart and Morra, Carlos and Stahnke, Susanne and Braband, Jens and Dittmann, Johannes and Griebel, Stephan and Krampf, Andreas and Link, Martin and M{\"u}ller, Matthias and Radestock, Jens and Strub, Leo and Bleeke, Kai and Jehl, Leander and Kapitza, R{\"u}diger and Messadi, Ines and Schmidt, Stefan and Schwarz-R{\"u}sch, Signe and Pirl, Lukas and Schmid, Robert and Friedenberger, Dirk and Beilharz, Jossekin Jakob and Boockmeyer, Arne and Polze, Andreas and R{\"o}hrig, Ralf and Sch{\"a}be, Hendrik and Thiermann, Ricky},
  title     = {RailChain},
  number    = {152},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-550-7},
  issn      = {1613-5652},
  doi       = {10.25932/publishup-57740},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-577409},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {140},
  year      = {2023},
  abstract  = {The RailChain project designed, implemented, and experimentally evaluated a juridical recorder that is based on a distributed consensus protocol. That juridical blockchain recorder has been realized as distributed ledger on board the advanced TrainLab (ICE-TD 605 017) of Deutsche Bahn. For the project, a consortium consisting of DB Systel, Siemens, Siemens Mobility, the Hasso Plattner Institute for Digital Engineering, Technische Universit{\"a}t Braunschweig, T{\"U}V Rheinland InterTraffic, and Spherity has been formed. These partners not only concentrated competencies in railway operation, computer science, regulation, and approval, but also combined experiences from industry, research from academia, and enthusiasm from startups. Distributed ledger technologies (DLTs) define distributed databases and express a digital protocol for transactions between business partners without the need for a trusted intermediary. The implementation of a blockchain with real-time requirements for the local network of a railway system (e.g., interlocking or train) allows to log data in the distributed system verifiably in real-time. For this, railway-specific assumptions can be leveraged to make modifications to standard blockchains protocols. EULYNX and OCORA (Open CCS On-board Reference Architecture) are parts of a future European reference architecture for control command and signalling (CCS, Reference CCS Architecture - RCA). Both architectural concepts outline heterogeneous IT systems with components from multiple manufacturers. Such systems introduce novel challenges for the approved and safety-relevant CCS of railways which were considered neither for road-side nor for on-board systems so far. Logging implementations, such as the common juridical recorder on vehicles, can no longer be realized as a central component of a single manufacturer. All centralized approaches are in question. The research project RailChain is funded by the mFUND program and gives practical evidence that distributed consensus protocols are a proper means to immutably (for legal purposes) store state information of many system components from multiple manufacturers. The results of RailChain have been published, prototypically implemented, and experimentally evaluated in large-scale field tests on the advanced TrainLab. At the same time, the project showed how RailChain can be integrated into the road-side and on-board architecture given by OCORA and EULYNX. Logged data can now be analysed sooner and also their trustworthiness is being increased. This enables, e.g., auditable predictive maintenance, because it is ensured that data is authentic and unmodified at any point in time.},
  language  = {en}
}
@book{GarusSawahnWankeetal.2023,
  author    = {Garus, Marcel and Sawahn, Rohan and Wanke, Jonas and Tiedt, Clemens and Granzow, Clara and Kuffner, Tim and Rosenbaum, Jannis and Hagemann, Linus and Wollnik, Tom and Woth, Lorenz and Auringer, Felix and Kantusch, Tobias and Roth, Felix and Hanff, Konrad and Schilli, Niklas and Seibold, Leonard and Lindner, Marc Fabian and Raschack, Selina},
  title     = {Operating systems II - student projects},
  number    = {142},
  editor    = {Grapentin, Andreas and Tiedt, Clemens and Polze, Andreas},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-524-8},
  issn      = {1613-5652},
  doi       = {10.25932/publishup-52636},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-526363},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {ix, 114},
  year      = {2023},
  abstract  = {This technical report presents the results of student projects which were prepared during the lecture "Operating Systems II" offered by the "Operating Systems and Middleware" group at HPI in the Summer term of 2020. The lecture covered ad- vanced aspects of operating system implementation and architecture on topics such as Virtualization, File Systems and Input/Output Systems. In addition to attending the lecture, the participating students were encouraged to gather practical experience by completing a project on a closely related topic over the course of the semester. The results of 10 selected exceptional projects are covered in this report. The students have completed hands-on projects on the topics of Operating System Design Concepts and Implementation, Hardware/Software Co-Design, Reverse Engineering, Quantum Computing, Static Source-Code Analysis, Operating Systems History, Application Binary Formats and more. It should be recognized that over the course of the semester all of these projects have achieved outstanding results which went far beyond the scope and the expec- tations of the lecture, and we would like to thank all participating students for their commitment and their effort in completing their respective projects, as well as their work on compiling this report.},
  language  = {en}
}
@article{BoettcherThurnerHaefneretal.2023,
  author    = {B{\"o}ttcher, Axel and Thurner, Veronika and H{\"a}fner, Tanja and Ottinger, Sarah},
  title     = {Erkenntnisse aus der Analyse von Studienverlaufsdaten als Grundlage f{\"u}r die Gestaltung von Beratungsangeboten},
  series = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  journal   = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  number    = {13},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-548-4},
  issn      = {1868-0844},
  doi       = {10.25932/publishup-61569},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-615693},
  pages     = {137 -- 156},
  year      = {2023},
  abstract  = {Viele Studierende stoßen im Rahmen ihres Informatikstudiums auf Probleme und ben{\"o}tigen individuell bedarfsgerechte Unterst{\"u}tzung, um beispielsweise trotz gewisser Startschwierigkeiten ihr Studium erfolgreich zu Ende zu f{\"u}hren. In die damit verbundene Lern- bzw. Studienberatung fließen Empfehlungen zur weiteren Studienverlaufsplanung ein. Anhand einer Datenanalyse {\"u}ber den Pr{\"u}fungsleistungsdaten der Studierenden {\"u}berpr{\"u}fen wir die hinter diesen Empfehlungen liegenden Hypothesen und leiten aus den dabei gewonnenen Erkenntnissen Konsequenzen f{\"u}r die Beratung ab. Insgesamt zeigt sich, dass sich nach den ersten Semestern ein mittlerer Bereich von Studierenden identifizieren l{\"a}sst, bei denen Studienabbruch und Studienerfolg etwa gleich wahrscheinlich sind. F{\"u}r diese Personengruppe ist Beratungsbedarf dringend gegeben. Gleichzeitig st{\"o}ßt die Datenanalyse auch an gewisse Grenzen, denn es zeigen sich insgesamt keine echt trennscharfen Muster, die fr{\"u}hzeitig im Studium eindeutig Erfolg oder Misserfolg prognostizieren. Dieses Ergebnis ist jedoch insofern erfreulich, als es bedeutet, dass jede:r Studierende:r auch nach einem suboptimalen Start ins Studium noch eine Chance auf einen Abschluss hat.},
  language  = {de}
}
@article{StemmeHoppe2023,
  author    = {Stemme, Jonas and Hoppe, Uwe},
  title     = {Evolution{\"a}re Entwicklung eines Inverted Classroom Formats unter Ber{\"u}cksichtigung des Student Engagement},
  series = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  journal   = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  number    = {13},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-548-4},
  issn      = {1868-0844},
  doi       = {10.25932/publishup-61601},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-616016},
  pages     = {231 -- 253},
  year      = {2023},
  abstract  = {1,7 Milliarden Studierende waren von der ad hoc Umstellung der Lehre an Hochschulen durch den Ausbruch der COVID-19-Pandemie im Jahr 2020 betroffen. Innerhalb k{\"u}rzester Zeit mussten Lehr- und Lernformate digital transformiert werden, um ein Distanzlernen f{\"u}r Studierende {\"u}berall auf der Welt zu erm{\"o}glichen. Etwa zwei Jahre sp{\"a}ter k{\"o}nnen die Erfahrungen aus der Entwicklung von digitalen Lehr- und Lernformaten dazu genutzt werden, um Blended Learning Formate zielgerecht weiterzuentwickeln. Die nachfolgende Untersuchung zeigt einerseits einen Prozess der evolution{\"a}ren Entwicklung am Beispiel eines Inverted Classrooms auf. Andererseits wird das Modell des Student Engagement genutzt, um die Einflussfaktoren, im Speziellen die des Verhaltens, zielgerecht anzupassen und so die Outcomes in Form von besseren Noten und einer erh{\"o}hten Zufriedenheit bei den Studierenden zu erzielen. Grundlage f{\"u}r die Untersuchung bildet die Lehrveranstaltung Projektmanagement, die an einer deutschen Hochschule durchgef{\"u}hrt wird.},
  language  = {de}
}
@article{Siegeris2023,
  author    = {Siegeris, Juliane},
  title     = {Attracting a new clientele for computer science with a women-only IT degree course},
  series = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  journal   = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  number    = {13},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-548-4},
  issn      = {1868-0844},
  doi       = {10.25932/publishup-61571},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-615712},
  pages     = {157 -- 170},
  year      = {2023},
  abstract  = {A degree course in IT and business administration solely for women (FIW) has been offered since 2009 at the HTW Berlin - University of Applied Sciences. This contribution discusses student motivations for enrolling in such a women only degree course and gives details of our experience over recent years. In particular, the approach to attracting new female students is described and the composition of the intake is discussed. It is shown that the women-only setting together with other factors can attract a new clientele for computer science.},
  language  = {en}
}
@article{vonSteinauSteinrueckSura2023,
  author    = {von Steinau-Steinr{\"u}ck, Robert and Sura, Stephan},
  title     = {Die (Rest-)Zul{\"a}ssigkeit von Verboten religi{\"o}ser Zeichen am Arbeitsplatz},
  series = {NJW spezial},
  volume    = {20},
  journal   = {NJW spezial},
  number    = {8},
  publisher = {C.H. Beck},
  address   = {M{\"u}nchen},
  issn      = {1613-4621},
  pages     = {242 -- 243},
  year      = {2023},
  abstract  = {In einer Reihe von Urteilen hat der EuGH seit 2017 die Zul{\"a}ssigkeit von Verboten religi{\"o}ser Zeichen und Kleidung am Arbeitsplatz bewertet. Obwohl die Einordnungen des Gerichtshofs der deutschen Rechtslage zun{\"a}chst diametral entgegenstanden, hat sich diese letztlich nicht ver{\"a}ndert.},
  language  = {de}
}
@book{Weber2023,
  author    = {Weber, Benedikt},
  title     = {Human pose estimation for decubitus prophylaxis},
  number    = {153},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-551-4},
  issn      = {1613-5652},
  doi       = {10.25932/publishup-56719},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-567196},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {73},
  year      = {2023},
  abstract  = {Decubitus is one of the most relevant diseases in nursing and the most expensive to treat. It is caused by sustained pressure on tissue, so it particularly affects bed-bound patients. This work lays a foundation for pressure mattress-based decubitus prophylaxis by implementing a solution to the single-frame 2D Human Pose Estimation problem. For this, methods of Deep Learning are employed. Two approaches are examined, a coarse-to-fine Convolutional Neural Network for direct regression of joint coordinates and a U-Net for the derivation of probability distribution heatmaps. We conclude that training our models on a combined dataset of the publicly available Bodies at Rest and SLP data yields the best results. Furthermore, various preprocessing techniques are investigated, and a hyperparameter optimization is performed to discover an improved model architecture. Another finding indicates that the heatmap-based approach outperforms direct regression. This model achieves a mean per-joint position error of 9.11 cm for the Bodies at Rest data and 7.43 cm for the SLP data. We find that it generalizes well on data from mattresses other than those seen during training but has difficulties detecting the arms correctly. Additionally, we give a brief overview of the medical data annotation tool annoto we developed in the bachelor project and furthermore conclude that the Scrum framework and agile practices enhanced our development workflow.},
  language  = {en}
}
@book{MeinelGalbasHageboelling2023,
  author    = {Meinel, Christoph and Galbas, Michael and Hageb{\"o}lling, David},
  title     = {Digitale Souver{\"a}nit{\"a}t: Erkenntnisse aus dem deutschen Bildungssektor},
  number    = {156},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-560-6},
  issn      = {1613-5652},
  doi       = {10.25932/publishup-59513},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-595138},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {1 -- 29},
  year      = {2023},
  abstract  = {Digitale Technologien bieten erhebliche politische, wirtschaftliche und gesellschaftliche Chancen. Zugleich ist der Begriff digitale Souver{\"a}nit{\"a}t zu einem Leitmotiv im deutschen Diskurs {\"u}ber digitale Technologien geworden: das heißt, die F{\"a}higkeit des Staates, seine Verantwortung wahrzunehmen und die Bef{\"a}higung der Gesellschaft - und des Einzelnen - sicherzustellen, die digitale Transformation selbstbestimmt zu gestalten. Exemplarisch f{\"u}r die Herausforderung in Deutschland und Europa, die Vorteile digitaler Technologien zu nutzen und gleichzeitig Souver{\"a}nit{\"a}tsbedenken zu ber{\"u}cksichtigen, steht der Bildungssektor. Er umfasst Bildung als zentrales {\"o}ffentliches Gut, ein schnell aufkommendes Gesch{\"a}ftsfeld und wachsende Best{\"a}nde an hochsensiblen personenbezogenen Daten. Davon ausgehend beschreibt der Bericht Wege zur Entsch{\"a}rfung des Spannungsverh{\"a}ltnisses zwischen Digitalisierung und Souver{\"a}nit{\"a}t auf drei verschiedenen Ebenen - Staat, Wirtschaft und Individuum - anhand konkreter technischer Projekte im Bildungsbereich: die HPI Schul-Cloud (staatliche Souver{\"a}nit{\"a}t), die MERLOT-Datenr{\"a}ume (wirtschaftliche Souver{\"a}nit{\"a}t) und die openHPI-Plattform (individuelle Souver{\"a}nit{\"a}t).},
  language  = {de}
}
@book{MeinelGalbasHageboelling2023,
  author    = {Meinel, Christoph and Galbas, Michael and Hageb{\"o}lling, David},
  title     = {Digital sovereignty: insights from Germany's education sector},
  number    = {157},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-561-3},
  issn      = {1613-5652},
  doi       = {10.25932/publishup-59772},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-597723},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {1 -- 27},
  year      = {2023},
  abstract  = {Digital technology offers significant political, economic, and societal opportunities. At the same time, the notion of digital sovereignty has become a leitmotif in German discourse: the state's capacity to assume its responsibilities and safeguard society's - and individuals' - ability to shape the digital transformation in a self-determined way. The education sector is exemplary for the challenge faced by Germany, and indeed Europe, of harnessing the benefits of digital technology while navigating concerns around sovereignty. It encompasses education as a core public good, a rapidly growing field of business, and growing pools of highly sensitive personal data. The report describes pathways to mitigating the tension between digitalization and sovereignty at three different levels - state, economy, and individual - through the lens of concrete technical projects in the education sector: the HPI Schul-Cloud (state sovereignty), the MERLOT data spaces (economic sovereignty), and the openHPI platform (individual sovereignty).},
  language  = {en}
}
@incollection{CorazzaThienen2023,
  author    = {Corazza, Giovanni Emanuele and Thienen, Julia von},
  title     = {Invention},
  series = {The Palgrave encyclopedia of the possible},
  booktitle = {The Palgrave encyclopedia of the possible},
  editor    = {Glăveanu, Vlad Petre},
  publisher = {Springer International Publishing},
  address   = {Cham},
  isbn      = {978-3-030-90912-3},
  doi       = {10.1007/978-3-030-90913-0_14},
  pages     = {806 -- 814},
  year      = {2023},
  abstract  = {This entry addresses invention from five different perspectives: (i) definition of the term, (ii) mechanisms underlying invention processes, (iii) (pre-)history of human inventions, (iv) intellectual property protection vs open innovation, and (v) case studies of great inventors. Regarding the definition, an invention is the outcome of a creative process taking place within a technological milieu, which is recognized as successful in terms of its effectiveness as an original technology. In the process of invention, a technological possibility becomes realized. Inventions are distinct from either discovery or innovation. In human creative processes, seven mechanisms of invention can be observed, yielding characteristic outcomes: (1) basic inventions, (2) invention branches, (3) invention combinations, (4) invention toolkits, (5) invention exaptations, (6) invention values, and (7) game-changing inventions. The development of humanity has been strongly shaped by inventions ever since early stone tools and the conception of agriculture. An "explosion of creativity" has been associated with Homo sapiens, and inventions in all fields of human endeavor have followed suit, engendering an exponential growth of cumulative culture. This culture development emerges essentially through a reuse of previous inventions, their revision, amendment and rededication. In sociocultural terms, humans have increasingly regulated processes of invention and invention-reuse through concepts such as intellectual property, patents, open innovation and licensing methods. Finally, three case studies of great inventors are considered: Edison, Marconi, and Montessori, next to a discussion of human invention processes as collaborative endeavors.},
  language  = {en}
}
@phdthesis{Najafi2023,
  author    = {Najafi, Pejman},
  title     = {Leveraging data science \& engineering for advanced security operations},
  doi       = {10.25932/publishup-61225},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-612257},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xix, 180},
  year      = {2023},
  abstract  = {The Security Operations Center (SOC) represents a specialized unit responsible for managing security within enterprises. To aid in its responsibilities, the SOC relies heavily on a Security Information and Event Management (SIEM) system that functions as a centralized repository for all security-related data, providing a comprehensive view of the organization's security posture. Due to the ability to offer such insights, SIEMS are considered indispensable tools facilitating SOC functions, such as monitoring, threat detection, and incident response. Despite advancements in big data architectures and analytics, most SIEMs fall short of keeping pace. Architecturally, they function merely as log search engines, lacking the support for distributed large-scale analytics. Analytically, they rely on rule-based correlation, neglecting the adoption of more advanced data science and machine learning techniques. This thesis first proposes a blueprint for next-generation SIEM systems that emphasize distributed processing and multi-layered storage to enable data mining at a big data scale. Next, with the architectural support, it introduces two data mining approaches for advanced threat detection as part of SOC operations. First, a novel graph mining technique that formulates threat detection within the SIEM system as a large-scale graph mining and inference problem, built on the principles of guilt-by-association and exempt-by-reputation. The approach entails the construction of a Heterogeneous Information Network (HIN) that models shared characteristics and associations among entities extracted from SIEM-related events/logs. Thereon, a novel graph-based inference algorithm is used to infer a node's maliciousness score based on its associations with other entities in the HIN. Second, an innovative outlier detection technique that imitates a SOC analyst's reasoning process to find anomalies/outliers. The approach emphasizes explainability and simplicity, achieved by combining the output of simple context-aware univariate submodels that calculate an outlier score for each entry. Both approaches were tested in academic and real-world settings, demonstrating high performance when compared to other algorithms as well as practicality alongside a large enterprise's SIEM system. This thesis establishes the foundation for next-generation SIEM systems that can enhance today's SOCs and facilitate the transition from human-centric to data-driven security operations.},
  language  = {en}
}
@inproceedings{GonnermannTeichmann2023,
  author    = {Gonnermann, Jana and Teichmann, Malte},
  title     = {Influence of pre-experience on learning, usability and cognitive load in a virtual learning environment},
  series = {Americas conference on information systems},
  booktitle = {Americas conference on information systems},
  number    = {1871},
  publisher = {AIS},
  address   = {Atlanta},
  year      = {2023},
  abstract  = {Virtual reality can have advantages for education and learning. However, it must be adequately designed so that the learner benefits from the technological possibilities. Understanding the underlying effects of the virtual learning environment and the learner's prior experience with virtual reality or prior knowledge of the content is necessary to design a proper virtual learning environment. This article presents a pre-study testing the design of a virtual learning environment for engineering vocational training courses. In the pre-study, 12 employees of two companies joined the training course in one of the two degrees of immersion (desktop VR and VR HMD). Quantitative results on learning success, cognitive load, usability, and motivation and qualitative learning process data were presented. The qualitative data assessment shows that overall, the employees were satisfied with the learning environment regardless of the level of immersion and that the participants asked for more guidance and structure accompanying the learning process. Further research is needed to test for solid group differences.},
  language  = {en}
}
@book{BarkowskyGiese2023,
  author    = {Barkowsky, Matthias and Giese, Holger},
  title     = {Triple graph grammars for multi-version models},
  number    = {155},
  isbn      = {978-3-86956-556-9},
  issn      = {1613-5652},
  doi       = {10.25932/publishup-57399},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-573994},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {28 -- 28},
  year      = {2023},
  abstract  = {Like conventional software projects, projects in model-driven software engineering require adequate management of multiple versions of development artifacts, importantly allowing living with temporary inconsistencies. In the case of model-driven software engineering, employed versioning approaches also have to handle situations where different artifacts, that is, different models, are linked via automatic model transformations. In this report, we propose a technique for jointly handling the transformation of multiple versions of a source model into corresponding versions of a target model, which enables the use of a more compact representation that may afford improved execution time of both the transformation and further analysis operations. Our approach is based on the well-known formalism of triple graph grammars and a previously introduced encoding of model version histories called multi-version models. In addition to showing the correctness of our approach with respect to the standard semantics of triple graph grammars, we conduct an empirical evaluation that demonstrates the potential benefit regarding execution time performance.},
  language  = {en}
}
@article{BaberowskiLeonhardtRentschetal.2023,
  author    = {Baberowski, David and Leonhardt, Thiemo and Rentsch, Susanne and Bergner, Nadine},
  title     = {Aufbau informatischer Kompetenzen im Kontext KI bei Lehramtsstudierenden des Faches Politik},
  series = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  journal   = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  number    = {13},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-548-4},
  issn      = {1868-0844},
  doi       = {10.25932/publishup-61599},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-615995},
  pages     = {189 -- 209},
  year      = {2023},
  abstract  = {Lehrkr{\"a}fte aller F{\"a}cher ben{\"o}tigen informatische Kompetenzen, um der wachsenden Alltagsrelevanz von Informatik und aktuell g{\"u}ltigen Lehrpl{\"a}nen gerecht zu werden. Beispielsweise verweist in Sachsen der Lehrplan f{\"u}r das Fach Gemeinschaftskunde, Rechtserziehung und Wirtschaft am Gymnasium mit dem f{\"u}r die Jahrgangsstufe 11 vorgesehenem Thema „Digitalisierung und sozialer Wandel" auf K{\"u}nstliche Intelligenz (KI) und explizit auf die Bedeutung der informatischen Bildung. Um die n{\"o}tigen informatischen Grundlagen zu vermitteln, wurde f{\"u}r Lehramtsstudierende des Faches Politik ein Workshop erarbeitet, der die Grundlagen der Funktionsweise von KI anhand von {\"u}berwachtem maschinellen Lernen in neuronalen Netzen vermittelt. Inhalt des Workshops ist es, mit Bezug auf gesellschaftliche Implikationen wie Datenschutz bei Trainingsdaten und algorithmic bias einen informierten Diskurs zu politischen Themen zu erm{\"o}glichen. Ziele des Workshops f{\"u}r Lehramtsstudierende mit dem Fach Politik sind: (1) Aufbau informatischer Kompetenzen in Bezug zum Thema KI, (2) St{\"a}rkung der Diskussionsf{\"a}higkeiten der Studierenden durch passende informatische Kompetenzen und (3) Anregung der Studierenden zum Transfer auf passende Themenstellungen im Politikunterricht. Das Evaluationskonzept umfasst eine Pre-Post-Befragung zur Zuversicht zur Vermittlungskompetenz unter Bezug auf maschinelles Lernen in neuronalen Netzen im Unterricht, sowie die Analyse einer abschließenden Diskussion. F{\"u}r die Pre-Post-Befragung konnte eine Steigerung der Zuversicht zur Vermittlungskompetenz beobachtet werden. Die Analyse der Diskussion zeigte das Bewusstsein der Alltagsrelevanz des Themas KI bei den Teilnehmenden, aber noch keine Anwendung der informatischen Inhalte des Workshops zur St{\"u}tzung der Argumente in der Diskussion.},
  language  = {de}
}
@article{ThorbrueggeDeselSchaefer2023,
  author    = {Thorbr{\"u}gge, Carsten and Desel, J{\"o}rg and Sch{\"a}fer, Len Ole},
  title     = {Vorqualifikationen und Anerkennungsoptionen im Informatikstudium},
  series = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  journal   = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  number    = {13},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-548-4},
  issn      = {1868-0844},
  doi       = {10.25932/publishup-61394},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-613942},
  pages     = {73 -- 89},
  year      = {2023},
  abstract  = {Viele Informatikstudierende sammeln bereits vor ihrem Studium berufliche Erfahrungen im Informatikbereich, ohne dass diese inhaltlich und didaktisch im Studium ber{\"u}cksichtigt werden. Dieser Beitrag geht der Frage nach, welche Kompetenzen aus beruflichen Vorqualifikationen bei Informatikstudierenden existieren und wie diese in Bezug zu Anerkennungsoptionen gesetzt werden k{\"o}nnen. Betrachtet werden: die pauschale Anerkennung, die auf erworbenen Zertifikaten beruht; die individuelle Anerkennung, bei der individuell erworbene Kompetenzen nachgewiesen werden; die Adaption von individuellen Lernwegen, die Teilkompetenzen der Studierenden ber{\"u}cksichtigt. Es wird eine Interviewstudie vorgestellt, in der Kompetenzen f{\"u}r ein Sample von Informatikstudierenden mit Vorqualifikation als Fachinformatiker/in erhoben und eine Zuordnung zu den Anerkennungsoptionen vorgenommen wurde. F{\"u}r die pr{\"a}zisere Gestaltung von Anerkennungsprozessen und zur kritischen Reflexion der eingesetzten hochschuldidaktischen Konzepte wurde eine empirische Basis geschaffen. Die vorhandenen Konzepte richten sich traditionell an Abiturienten/ innen mit sehr geringem Informatikhintergrund und ber{\"u}cksichtigen die tats{\"a}chlich existierende Heterogenit{\"a}t der Studienanf{\"a}nger/innen nicht angemessen. Die Ergebnisse zeigen, dass die Befragten aus ihrer Vorqualifikation relevante fachliche Kompetenzen mitbringen, die mit den Anerkennungsoptionen korrespondieren und deren Weiterentwicklung dienen k{\"o}nnen. Dar{\"u}ber hinaus werden aus {\"u}berfachlichen Kompetenzen wie Selbststeuerungskompetenzen weitere Erkenntnisse zur Studiengestaltung gewonnen.},
  language  = {de}
}
@article{Weicker2023,
  author    = {Weicker, Karsten},
  title     = {Peer-Review als Katalysator im Lernprozess},
  series = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  journal   = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  number    = {13},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-548-4},
  issn      = {1868-0844},
  doi       = {10.25932/publishup-61602},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-616025},
  pages     = {257 -- 277},
  year      = {2023},
  abstract  = {Peer-Reviews werden seit geraumer Zeit in unterschiedlichen Lehrszenarien eingesetzt. In diesem Paper wird untersucht, inwieweit das Peer- Review die Auseinandersetzung mit den Inhalten eines Grundlagenmoduls in einem pr{\"a}senzfreien Lehrszenario bef{\"o}rdern kann. Dabei scheint in den Ergebnissen die Qualit{\"a}t der selbst erstellten Reviews einer der wichtigsten Einflussfaktoren f{\"u}r den Lernerfolg zu sein, w{\"a}hrend Experten-Feedback und weitere Faktoren deutlich untergeordnet erscheinen. Die F{\"a}higkeit ausf{\"u}hrliche Peer-Reviews zu verfassen geht einher mit dem Erwerb von fachlicher Kompetenz bzw. entsprechenden fachlichen Vorkenntnissen.},
  language  = {de}
}
@article{OpelNetzerDesel2023,
  author    = {Opel, Simone and Netzer, Cajus Marian and Desel, J{\"o}rg},
  title     = {Adaption von Lernwegen in adaptierten Lehrmaterialien f{\"u}r Studierende mit Berufsausbildungsabschluss},
  series = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  journal   = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  number    = {13},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-548-4},
  issn      = {1868-0844},
  doi       = {10.25932/publishup-61418},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-614188},
  pages     = {91 -- 114},
  year      = {2023},
  abstract  = {Obwohl immer mehr Menschen nicht direkt ein Studium aufnehmen, sondern zuvor eine berufliche Ausbildung absolvieren, werden die in der Ausbildung erworbenen Kompetenzen von den Hochschulen inhaltlich und didaktisch meist ignoriert. Ein Ansatz, diese Kompetenzen zu w{\"u}rdigen, ist die formale Anrechnung von mitgebrachten Kompetenzen als (f{\"u}r den Studienabschluss erforderliche) Leistungspunkte. Eine andere Variante ist der Einsatz von speziell f{\"u}r die Zielgruppe der Studierenden mit Vorkenntnissen adaptiertem Lehr-Lernmaterial. Um dar{\"u}ber hinaus individuelle Unterschiede zu ber{\"u}cksichtigen, erlaubt eine weitere Adaption individueller Lernpfade den Lernenden, genau die jeweils fehlenden Kompetenzen zu erwerben. In diesem Beitrag stellen wir die exemplarische Entwicklung derartigen Materials anhand des Kurses „Datenbanken" f{\"u}r die Zielgruppe der Studierenden mit einer abgeschlossenen Ausbildung zum Fachinformatiker bzw. zur Fachinformatikerin vor.},
  language  = {de}
}
@article{Weber2023,
  author    = {Weber, Gerhard},
  title     = {Informatik und Barrierefreiheit},
  series = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  journal   = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  number    = {13},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-548-4},
  issn      = {1868-0844},
  doi       = {10.25932/publishup-61387},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-613874},
  pages     = {35 -- 50},
  year      = {2023},
  abstract  = {Barrierefreiheit kann durch Methoden der Informatik hergestellt und ausgebaut werden. Dieser eingeladene Beitrag stellt die Anforderungen von Menschen mit den umfangreichsten Benutzererfordernissen an Software vor, die z. B. eigene Schriftsysteme wie Braille und entsprechende taktile Ausgabeger{\"a}te verwenden. Assistive Technologien umfassen dabei auch Software verschiedenster Art. Es werden die wichtigsten Kompetenzen daf{\"u}r vorgestellt. Im Curriculum der Informatik k{\"o}nnen diese Kompetenzen im Rahmen von speziellen Vorlesungen und {\"U}bungen vermittelt werden oder sie werden in die jeweiligen Fachgebiete integriert. Um den Studienbetrieb ebenfalls barrierefrei zu gestalten, sind weitere Anstrengungen notwendig, die Lehrende, Verwaltung und die Hochschulleitung einbeziehen.},
  language  = {de}
}
@article{SchellSchwill2023,
  author    = {Schell, Timon and Schwill, Andreas},
  title     = {„Es ist kompliziert, alles inklusive Privatleben unter einen Hut zu bekommen"},
  series = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  journal   = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  number    = {13},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-548-4},
  issn      = {1868-0844},
  doi       = {10.25932/publishup-61388},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-613882},
  pages     = {53 -- 71},
  year      = {2023},
  abstract  = {Eine {\"u}bliche Erz{\"a}hlung verkn{\"u}pft lange Studienzeiten und hohe Abbrecherquoten im Informatikstudium zum einen mit der sehr gut bezahlten Nebent{\"a}tigkeit von Studierenden in der Informatikbranche, die deutlich studienzeitverl{\"a}ngernd sei; zum anderen werde wegen des hohen Bedarfs an Informatikern ein formeller Studienabschluss von den Studierenden h{\"a}ufig als entbehrlich betrachtet und eine Karriere in der Informatikbranche ohne abgeschlossenes Studium begonnen. In dieser Studie, durchgef{\"u}hrt an der Universit{\"a}t Potsdam, untersuchen wir, wie viele Informatikstudierende neben dem Studium innerhalb und außerhalb der Informatikbranche arbeiten, welche Erwartungen sie neben der Bezahlung damit verbinden und wie sich die T{\"a}tigkeit auf ihr Studium und ihre sp{\"a}tere berufliche Perspektive auswirkt. Aus aktuellem Anlass interessieren uns auch die Auswirkungen der Covid-19-Pandemie auf die Arbeitst{\"a}tigkeiten der Informatikstudierenden.},
  language  = {de}
}
@phdthesis{SchulzHanke2023,
  author    = {Schulz-Hanke, Christian},
  title     = {BCH Codes mit kombinierter Korrektur und Erkennung},
  doi       = {10.25932/publishup-61794},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-617943},
  school      = {Universit{\"a}t Potsdam},
  pages     = {ii, 191},
  year      = {2023},
  abstract  = {BCH Codes mit kombinierter Korrektur und Erkennung In dieser Arbeit wird auf Grundlage des BCH Codes untersucht, wie eine Fehlerkorrektur mit einer Erkennung h{\"o}herer Fehleranzahlen kombiniert werden kann. Mit dem Verfahren der 1-Bit Korrektur mit zus{\"a}tzlicher Erkennung h{\"o}herer Fehler wurde ein Ansatz entwickelt, welcher die Erkennung zus{\"a}tzlicher Fehler durch das parallele L{\"o}sen einfacher Gleichungen der Form s_x = s_1^x durchf{\"u}hrt. Die Anzahl dieser Gleichungen ist linear zu der Anzahl der zu {\"u}berpr{\"u}fenden h{\"o}heren Fehler. In dieser Arbeit wurde zus{\"a}tzlich f{\"u}r bis zu 4-Bit Korrekturen mit zus{\"a}tzlicher Erkennung h{\"o}herer Fehler ein weiterer allgemeiner Ansatz vorgestellt. Dabei werden parallel f{\"u}r alle korrigierbaren Fehleranzahlen spekulative Fehlerkorrekturen durchgef{\"u}hrt. Aus den bestimmten Fehlerstellen werden spekulative Syndromkomponenten erzeugt, durch welche die Fehlerstellen best{\"a}tigt und h{\"o}here erkennbare Fehleranzahlen ausgeschlossen werden k{\"o}nnen. Die vorgestellten Ans{\"a}tze unterscheiden sich von dem in entwickelten Ansatz, bei welchem die Anzahl der Fehlerstellen durch die Berechnung von Determinanten in absteigender Reihenfolge berechnet wird, bis die erste Determinante 0 bildet. Bei dem bekannten Verfahren ist durch die Berechnung der Determinanten eine faktorielle Anzahl an Berechnungen in Relation zu der Anzahl zu {\"u}berpr{\"u}fender Fehler durchzuf{\"u}hren. Im Vergleich zu dem bekannten sequentiellen Verfahrens nach Berlekamp Massey besitzen die Berechnungen im vorgestellten Ansatz simple Gleichungen und k{\"o}nnen parallel durchgef{\"u}hrt werden.Bei dem bekannten Verfahren zur parallelen Korrektur von 4-Bit Fehlern ist eine Gleichung vierten Grades im GF(2^m) zu l{\"o}sen. Dies erfolgt, indem eine Hilfsgleichung dritten Grades und vier Gleichungen zweiten Grades parallel gel{\"o}st werden. In der vorliegenden Arbeit wurde gezeigt, dass sich eine Gleichung zweiten Grades einsparen l{\"a}sst, wodurch sich eine Vereinfachung der Hardware bei einer parallelen Realisierung der 4-Bit Korrektur ergibt. Die erzielten Ergebnisse wurden durch umfangreiche Simulationen in Software und Hardwareimplementierungen {\"u}berpr{\"u}ft.},
  language  = {de}
}
@inproceedings{VladovaUllrichSultanowetal.2023,
  author    = {Vladova, Gergana and Ullrich, Andr{\´e} and Sultanow, Eldar and Tobolla, Marinho and Sebrak, Sebastian and Czarnecki, Christian and Brockmann, Carsten},
  title     = {Visual analytics for knowledge management},
  series = {Informatik 2023},
  booktitle = {Informatik 2023},
  editor    = {Klein, Maike and Krupka, Daniel and Winter, Cornelia and Wohlgemuth, Volker},
  publisher = {Gesellschaft f{\"u}r Informatik e.V. (GI)},
  address   = {Bonn},
  isbn      = {978-3-88579-731-9},
  issn      = {1617-5468},
  doi       = {10.18420/inf2023_187},
  pages     = {1851 -- 1870},
  year      = {2023},
  abstract  = {The management of knowledge in organizations considers both established long-term processes and cooperation in agile project teams. Since knowledge can be both tacit and explicit, its transfer from the individual to the organizational knowledge base poses a challenge in organizations. This challenge increases when the fluctuation of knowledge carriers is exceptionally high. Especially in large projects in which external consultants are involved, there is a risk that critical, company-relevant knowledge generated in the project will leave the company with the external knowledge carrier and thus be lost. In this paper, we show the advantages of an early warning system for knowledge management to avoid this loss. In particular, the potential of visual analytics in the context of knowledge management systems is presented and discussed. We present a project for the development of a business-critical software system and discuss the first implementations and results.},
  language  = {en}
}
@article{HagemannAbramova2023,
  author    = {Hagemann, Linus and Abramova, Olga},
  title     = {Emotions and information diffusion on social media},
  series = {AIS transactions on replication research},
  volume    = {9},
  journal   = {AIS transactions on replication research},
  number    = {1},
  publisher = {AIS},
  address   = {Atlanta},
  issn      = {2473-3458},
  doi       = {10.17705/1atrr.00079},
  pages     = {1 -- 19},
  year      = {2023},
  abstract  = {This paper presents a methodological and conceptual replication of Stieglitz and Dang-Xuan's (2013) investigation of the role of sentiment in information-sharing behavior on social media. Whereas Stieglitz and Dang-Xuan (2013) focused on Twitter communication prior to the state parliament elections in the German states Baden-Wurttemberg, Rheinland-Pfalz, and Berlin in 2011, we test their theoretical propositions in the context of the state parliament elections in Saxony-Anhalt (Germany) 2021. We confirm the positive link between sentiment in a political Twitter message and its number of retweets in a methodological replication. In a conceptual replication, where sentiment was assessed with the alternative dictionary-based tool LIWC, the sentiment was negatively associated with the retweet volume. In line with the original study, the strength of association between sentiment and retweet time lag insignificantly differs between tweets with negative sentiment and tweets with positive sentiment. We also found that the number of an author's followers was an essential determinant of sharing behavior. However, two hypotheses supported in the original study did not hold for our sample. Precisely, the total amount of sentiments was insignificantly linked to the time lag to the first retweet. Finally, in our data, we do not observe that the association between the overall sentiment and retweet quantity is stronger for tweets with negative sentiment than for those with positive sentiment.},
  language  = {en}
}
@article{PuriVardeMelo2023,
  author    = {Puri, Manish and Varde, Aparna S. and Melo, Gerard de},
  title     = {Commonsense based text mining on urban policy},
  series = {Language resources and evaluation},
  volume    = {57},
  journal   = {Language resources and evaluation},
  publisher = {Springer},
  address   = {Dordrecht [u.a.]},
  issn      = {1574-020X},
  doi       = {10.1007/s10579-022-09584-6},
  pages     = {733 -- 763},
  year      = {2023},
  abstract  = {Local laws on urban policy, i.e., ordinances directly affect our daily life in various ways (health, business etc.), yet in practice, for many citizens they remain impervious and complex. This article focuses on an approach to make urban policy more accessible and comprehensible to the general public and to government officials, while also addressing pertinent social media postings. Due to the intricacies of the natural language, ranging from complex legalese in ordinances to informal lingo in tweets, it is practical to harness human judgment here. To this end, we mine ordinances and tweets via reasoning based on commonsense knowledge so as to better account for pragmatics and semantics in the text. Ours is pioneering work in ordinance mining, and thus there is no prior labeled training data available for learning. This gap is filled by commonsense knowledge, a prudent choice in situations involving a lack of adequate training data. The ordinance mining can be beneficial to the public in fathoming policies and to officials in assessing policy effectiveness based on public reactions. This work contributes to smart governance, leveraging transparency in governing processes via public involvement. We focus significantly on ordinances contributing to smart cities, hence an important goal is to assess how well an urban region heads towards a smart city as per its policies mapping with smart city characteristics, and the corresponding public satisfaction.},
  language  = {en}
}
@article{GarrelsKhodabakhshRenardetal.2023,
  author    = {Garrels, Tim and Khodabakhsh, Athar and Renard, Bernhard Y. and Baum, Katharina},
  title     = {LazyFox: fast and parallelized overlapping community detection in large graphs},
  series = {PEERJ Computer Science},
  volume    = {9},
  journal   = {PEERJ Computer Science},
  publisher = {PeerJ Inc.},
  address   = {London},
  issn      = {2376-5992},
  doi       = {10.7717/peerj-cs.1291},
  pages     = {30},
  year      = {2023},
  abstract  = {The detection of communities in graph datasets provides insight about a graph's underlying structure and is an important tool for various domains such as social sciences, marketing, traffic forecast, and drug discovery. While most existing algorithms provide fast approaches for community detection, their results usually contain strictly separated communities. However, most datasets would semantically allow for or even require overlapping communities that can only be determined at much higher computational cost. We build on an efficient algorithm, FOX, that detects such overlapping communities. FOX measures the closeness of a node to a community by approximating the count of triangles which that node forms with that community. We propose LAZYFOX, a multi-threaded adaptation of the FOX algorithm, which provides even faster detection without an impact on community quality. This allows for the analyses of significantly larger and more complex datasets. LAZYFOX enables overlapping community detection on complex graph datasets with millions of nodes and billions of edges in days instead of weeks. As part of this work, LAZYFOX's implementation was published and is available as a tool under an MIT licence at https://github.com/TimGarrels/LazyFox.},
  language  = {en}
}
@book{KubanRottaNolteetal.2023,
  author    = {Kuban, Robert and Rotta, Randolf and Nolte, J{\"o}rg and Chromik, Jonas and Beilharz, Jossekin Jakob and Pirl, Lukas and Friedrich, Tobias and Lenzner, Pascal and Weyand, Christopher and Juiz, Carlos and Bermejo, Belen and Sauer, Joao and Coelh, Leandro dos Santos and Najafi, Pejman and P{\"u}nter, Wenzel and Cheng, Feng and Meinel, Christoph and Sidorova, Julia and Lundberg, Lars and Vogel, Thomas and Tran, Chinh and Moser, Irene and Grunske, Lars and Elsaid, Mohamed Esameldin Mohamed and Abbas, Hazem M. and Rula, Anisa and Sejdiu, Gezim and Maurino, Andrea and Schmidt, Christopher and H{\"u}gle, Johannes and Uflacker, Matthias and Nozza, Debora and Messina, Enza and Hoorn, Andr{\´e} van and Frank, Markus and Schulz, Henning and Alhosseini Almodarresi Yasin, Seyed Ali and Nowicki, Marek and Muite, Benson K. and Boysan, Mehmet Can and Bianchi, Federico and Cremaschi, Marco and Moussa, Rim and Abdel-Karim, Benjamin M. and Pfeuffer, Nicolas and Hinz, Oliver and Plauth, Max and Polze, Andreas and Huo, Da and Melo, Gerard de and Mendes Soares, F{\´a}bio and Oliveira, Roberto C{\´e}lio Lim{\~a}o de and Benson, Lawrence and Paul, Fabian and Werling, Christian and Windheuser, Fabian and Stojanovic, Dragan and Djordjevic, Igor and Stojanovic, Natalija and Stojnev Ilic, Aleksandra and Weidmann, Vera and Lowitzki, Leon and Wagner, Markus and Ifa, Abdessatar Ben and Arlos, Patrik and Megia, Ana and Vendrell, Joan and Pfitzner, Bjarne and Redondo, Alberto and R{\´i}os Insua, David and Albert, Justin Amadeus and Zhou, Lin and Arnrich, Bert and Szab{\´o}, Ildik{\´o} and Fodor, Szabina and Ternai, Katalin and Bhowmik, Rajarshi and Campero Durand, Gabriel and Shevchenko, Pavlo and Malysheva, Milena and Prymak, Ivan and Saake, Gunter},
  title     = {HPI Future SOC Lab - Proceedings 2019},
  number    = {158},
  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      = {978-3-86956-564-4},
  issn      = {1613-5652},
  doi       = {10.25932/publishup-59791},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-597915},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {xi, 301},
  year      = {2023},
  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 2019. Selected projects have presented their results on April 9th and November 12th 2019 at the Future SOC Lab Day events.},
  language  = {en}
}
@misc{KonigorskiWernickeSlosareketal.2023,
  author    = {Konigorski, Stefan and Wernicke, Sarah and Slosarek, Tamara and Zenner, Alexander Maximilian and Strelow, Nils and Ruether, Darius Ferenc and Henschel, Florian and Manaswini, Manisha and Pottb{\"a}cker, Fabian and Edelman, Jonathan Antonio and Owoyele, Babajide and Danieletto, Matteo and Golden, Eddye and Zweig, Micol and Nadkarni, Girish N. and B{\"o}ttinger, Erwin},
  title     = {StudyU: A Platform for Designing and Conducting Innovative Digital N-of-1 Trials},
  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    = {12},
  doi       = {10.25932/publishup-58037},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-580370},
  pages     = {12},
  year      = {2023},
  abstract  = {N-of-1 trials are the gold standard study design to evaluate individual treatment effects and derive personalized treatment strategies. Digital tools have the potential to initiate a new era of N-of-1 trials in terms of scale and scope, but fully functional platforms are not yet available. Here, we present the open source StudyU platform, which includes the StudyU Designer and StudyU app. With the StudyU Designer, scientists are given a collaborative web application to digitally specify, publish, and conduct N-of-1 trials. The StudyU app is a smartphone app with innovative user-centric elements for participants to partake in trials published through the StudyU Designer to assess the effects of different interventions on their health. Thereby, the StudyU platform allows clinicians and researchers worldwide to easily design and conduct digital N-of-1 trials in a safe manner. We envision that StudyU can change the landscape of personalized treatments both for patients and healthy individuals, democratize and personalize evidence generation for self-optimization and medicine, and can be integrated in clinical practice.},
  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}
}
@article{KayaFreitag2022,
  author    = {Kaya, Adem and Freitag, Melina A.},
  title     = {Conditioning analysis for discrete Helmholtz problems},
  series = {Computers and mathematics with applications : an international journal},
  volume    = {118},
  journal   = {Computers and mathematics with applications : an international journal},
  publisher = {Elsevier Science},
  address   = {Amsterdam},
  issn      = {0898-1221},
  doi       = {10.1016/j.camwa.2022.05.016},
  pages     = {171 -- 182},
  year      = {2022},
  abstract  = {In this paper, we examine conditioning of the discretization of the Helmholtz problem. Although the discrete Helmholtz problem has been studied from different perspectives, to the best of our knowledge, there is no conditioning analysis for it. We aim to fill this gap in the literature. We propose a novel method in 1D to observe the near-zero eigenvalues of a symmetric indefinite matrix. Standard classification of ill-conditioning based on the matrix condition number is not true for the discrete Helmholtz problem. We relate the ill-conditioning of the discretization of the Helmholtz problem with the condition number of the matrix. We carry out analytical conditioning analysis in 1D and extend our observations to 2D with numerical observations. We examine several discretizations. We find different regions in which the condition number of the problem shows different characteristics. We also explain the general behavior of the solutions in these regions.},
  language  = {en}
}
@article{MattisBeckmannReinetal.2022,
  author    = {Mattis, Toni and Beckmann, Tom and Rein, Patrick and Hirschfeld, Robert},
  title     = {First-class concepts},
  series = {Journal of object technology : JOT / ETH Z{\"u}rich, Department of Computer Science},
  volume    = {21},
  journal   = {Journal of object technology : JOT / ETH Z{\"u}rich, Department of Computer Science},
  number    = {2},
  publisher = {ETH Z{\"u}rich, Department of Computer Science},
  address   = {Z{\"u}rich},
  issn      = {1660-1769},
  doi       = {10.5381/jot.2022.21.2.a6},
  pages     = {1 -- 15},
  year      = {2022},
  abstract  = {Ideally, programs are partitioned into independently maintainable and understandable modules. As a system grows, its architecture gradually loses the capability to accommodate new concepts in a modular way. While refactoring is expensive and not always possible, and the programming language might lack dedicated primary language constructs to express certain cross-cutting concerns, programmers are still able to explain and delineate convoluted concepts through secondary means: code comments, use of whitespace and arrangement of code, documentation, or communicating tacit knowledge. <br /> Secondary constructs are easy to change and provide high flexibility in communicating cross-cutting concerns and other concepts among programmers. However, such secondary constructs usually have no reified representation that can be explored and manipulated as first-class entities through the programming environment. <br /> In this exploratory work, we discuss novel ways to express a wide range of concepts, including cross-cutting concerns, patterns, and lifecycle artifacts independently of the dominant decomposition imposed by an existing architecture. We propose the representation of concepts as first-class objects inside the programming environment that retain the capability to change as easily as code comments. We explore new tools that allow programmers to view, navigate, and change programs based on conceptual perspectives. In a small case study, we demonstrate how such views can be created and how the programming experience changes from draining programmers' attention by stretching it across multiple modules toward focusing it on cohesively presented concepts. Our designs are geared toward facilitating multiple secondary perspectives on a system to co-exist in symbiosis with the original architecture, hence making it easier to explore, understand, and explain complex contexts and narratives that are hard or impossible to express using primary modularity constructs.},
  language  = {en}
}
@article{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}
}
@phdthesis{Dreseler2022,
  author    = {Dreseler, Markus},
  title     = {Automatic tiering for in-memory database systems},
  doi       = {10.25932/publishup-55825},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-558253},
  school      = {Universit{\"a}t Potsdam},
  pages     = {vii, 143},
  year      = {2022},
  abstract  = {A decade ago, it became feasible to store multi-terabyte databases in main memory. These in-memory databases (IMDBs) profit from DRAM's low latency and high throughput as well as from the removal of costly abstractions used in disk-based systems, such as the buffer cache. However, as the DRAM technology approaches physical limits, scaling these databases becomes difficult. Non-volatile memory (NVM) addresses this challenge. This new type of memory is persistent, has more capacity than DRAM (4x), and does not suffer from its density-inhibiting limitations. Yet, as NVM has a higher latency (5-15x) and a lower throughput (0.35x), it cannot fully replace DRAM. IMDBs thus need to navigate the trade-off between the two memory tiers. We present a solution to this optimization problem. Leveraging information about access frequencies and patterns, our solution utilizes NVM's additional capacity while minimizing the associated access costs. Unlike buffer cache-based implementations, our tiering abstraction does not add any costs when reading data from DRAM. As such, it can act as a drop-in replacement for existing IMDBs. Our contributions are as follows: (1) As the foundation for our research, we present Hyrise, an open-source, columnar IMDB that we re-engineered and re-wrote from scratch. Hyrise enables realistic end-to-end benchmarks of SQL workloads and offers query performance which is competitive with other research and commercial systems. At the same time, Hyrise is easy to understand and modify as repeatedly demonstrated by its uses in research and teaching. (2) We present a novel memory management framework for different memory and storage tiers. By encapsulating the allocation and access methods of these tiers, we enable existing data structures to be stored on different tiers with no modifications to their implementation. Besides DRAM and NVM, we also support and evaluate SSDs and have made provisions for upcoming technologies such as disaggregated memory. (3) To identify the parts of the data that can be moved to (s)lower tiers with little performance impact, we present a tracking method that identifies access skew both in the row and column dimensions and that detects patterns within consecutive accesses. Unlike existing methods that have substantial associated costs, our access counters exhibit no identifiable overhead in standard benchmarks despite their increased accuracy. (4) Finally, we introduce a tiering algorithm that optimizes the data placement for a given memory budget. In the TPC-H benchmark, this allows us to move 90\% of the data to NVM while the throughput is reduced by only 10.8\% and the query latency is increased by 11.6\%. With this, we outperform approaches that ignore the workload's access skew and access patterns and increase the query latency by 20\% or more. Individually, our contributions provide novel approaches to current challenges in systems engineering and database research. Combining them allows IMDBs to scale past the limits of DRAM while continuing to profit from the benefits of in-memory computing.},
  language  = {en}
}
@phdthesis{Boeken2022,
  author    = {B{\"o}ken, Bj{\"o}rn},
  title     = {Improving prediction accuracy using dynamic information},
  doi       = {10.25932/publishup-58512},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-585125},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xii, 160},
  year      = {2022},
  abstract  = {Accurately solving classification problems nowadays is likely to be the most relevant machine learning task. Binary classification separating two classes only is algorithmically simpler but has fewer potential applications as many real-world problems are multi-class. On the reverse, separating only a subset of classes simplifies the classification task. Even though existing multi-class machine learning algorithms are very flexible regarding the number of classes, they assume that the target set Y is fixed and cannot be restricted once the training is finished. On the other hand, existing state-of-the-art production environments are becoming increasingly interconnected with the advance of Industry 4.0 and related technologies such that additional information can simplify the respective classification problems. In light of this, the main aim of this thesis is to introduce dynamic classification that generalizes multi-class classification such that the target class set can be restricted arbitrarily to a non-empty class subset M of Y at any time between two consecutive predictions. This task is solved by a combination of two algorithmic approaches. First, classifier calibration, which transforms predictions into posterior probability estimates that are intended to be well calibrated. The analysis provided focuses on monotonic calibration and in particular corrects wrong statements that appeared in the literature. It also reveals that bin-based evaluation metrics, which became popular in recent years, are unjustified and should not be used at all. Next, the validity of Platt scaling, which is the most relevant parametric calibration approach, is analyzed in depth. In particular, its optimality for classifier predictions distributed according to four different families of probability distributions as well its equivalence with Beta calibration up to a sigmoidal preprocessing are proven. For non-monotonic calibration, extended variants on kernel density estimation and the ensemble method EKDE are introduced. Finally, the calibration techniques are evaluated using a simulation study with complete information as well as on a selection of 46 real-world data sets. Building on this, classifier calibration is applied as part of decomposition-based classification that aims to reduce multi-class problems to simpler (usually binary) prediction tasks. For the involved fusing step performed at prediction time, a new approach based on evidence theory is presented that uses classifier calibration to model mass functions. This allows the analysis of decomposition-based classification against a strictly formal background and to prove closed-form equations for the overall combinations. Furthermore, the same formalism leads to a consistent integration of dynamic class information, yielding a theoretically justified and computationally tractable dynamic classification model. The insights gained from this modeling are combined with pairwise coupling, which is one of the most relevant reduction-based classification approaches, such that all individual predictions are combined with a weight. This not only generalizes existing works on pairwise coupling but also enables the integration of dynamic class information. Lastly, a thorough empirical study is performed that compares all newly introduced approaches to existing state-of-the-art techniques. For this, evaluation metrics for dynamic classification are introduced that depend on corresponding sampling strategies. Thereafter, these are applied during a three-part evaluation. First, support vector machines and random forests are applied on 26 data sets from the UCI Machine Learning Repository. Second, two state-of-the-art deep neural networks are evaluated on five benchmark data sets from a relatively recent reference work. Here, computationally feasible strategies to apply the presented algorithms in combination with large-scale models are particularly relevant because a naive application is computationally intractable. Finally, reference data from a real-world process allowing the inclusion of dynamic class information are collected and evaluated. The results show that in combination with support vector machines and random forests, pairwise coupling approaches yield the best results, while in combination with deep neural networks, differences between the different approaches are mostly small to negligible. Most importantly, all results empirically confirm that dynamic classification succeeds in improving the respective prediction accuracies. Therefore, it is crucial to pass dynamic class information in respective applications, which requires an appropriate digital infrastructure.},
  language  = {en}
}
@article{KrauseGrosseDetersBaumannetal.2022,
  author    = {Krause, Hannes-Vincent and Große Deters, Fenne and Baumann, Annika and Krasnova, Hanna},
  title     = {Active social media use and its impact on well-being},
  series = {Journal of computer-mediated communication : a journal of the International Communication Association},
  volume    = {28},
  journal   = {Journal of computer-mediated communication : a journal of the International Communication Association},
  number    = {1},
  publisher = {Oxford Univ. Press},
  address   = {Oxford},
  issn      = {1083-6101},
  doi       = {10.1093/jcmc/zmac037},
  pages     = {12},
  year      = {2022},
  abstract  = {Active use of social networking sites (SNSs) has long been assumed to benefit users' well-being. However, this established hypothesis is increasingly being challenged, with scholars criticizing its lack of empirical support and the imprecise conceptualization of active use. Nevertheless, with considerable heterogeneity among existing studies on the hypothesis and causal evidence still limited, a final verdict on its robustness is still pending. To contribute to this ongoing debate, we conducted a week-long randomized control trial with N = 381 adult Instagram users recruited via Prolific. Specifically, we tested how active SNS use, operationalized as picture postings on Instagram, affects different dimensions of well-being. The results depicted a positive effect on users' positive affect but null findings for other well-being outcomes. The findings broadly align with the recent criticism against the active use hypothesis and support the call for a more nuanced view on the impact of SNSs. <br /> Lay Summary Active use of social networking sites (SNSs) has long been assumed to benefit users' well-being. However, this established assumption is increasingly being challenged, with scholars criticizing its lack of empirical support and the imprecise conceptualization of active use. Nevertheless, with great diversity among conducted studies on the hypothesis and a lack of causal evidence, a final verdict on its viability is still pending. To contribute to this ongoing debate, we conducted a week-long experimental investigation with 381 adult Instagram users. Specifically, we tested how posting pictures on Instagram affects different aspects of well-being. The results of this study depicted a positive effect of posting Instagram pictures on users' experienced positive emotions but no effects on other aspects of well-being. The findings broadly align with the recent criticism against the active use hypothesis and support the call for a more nuanced view on the impact of SNSs on users.},
  language  = {en}
}
@phdthesis{Plauth2022,
  author    = {Plauth, Max Frederik},
  title     = {Improving the Accessibility of Heterogeneous System Resources for Application Developers using Programming Abstractions},
  doi       = {10.25932/publishup-55811},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-558118},
  school      = {Universit{\"a}t Potsdam},
  pages     = {ix, 133},
  year      = {2022},
  abstract  = {The heterogeneity of today's state-of-the-art computer architectures is confronting application developers with an immense degree of complexity which results from two major challenges. First, developers need to acquire profound knowledge about the programming models or the interaction models associated with each type of heterogeneous system resource to make efficient use thereof. Second, developers must take into account that heterogeneous system resources always need to exchange data with each other in order to work on a problem together. However, this data exchange is always associated with a certain amount of overhead, which is why the amounts of data exchanged should be kept as low as possible. This thesis proposes three programming abstractions to lessen the burdens imposed by these major challenges with the goal of making heterogeneous system resources accessible to a wider range of application developers. The lib842 compression library provides the first method for accessing the compression and decompression facilities of the NX-842 on-chip compression accelerator available in IBM Power CPUs from user space applications running on Linux. Addressing application development of scale-out GPU workloads, the CloudCL framework makes the resources of GPU clusters more accessible by hiding many aspects of distributed computing while enabling application developers to focus on the aspects of the data parallel programming model associated with GPUs. Furthermore, CloudCL is augmented with transparent data compression facilities based on the lib842 library in order to improve the efficiency of data transfers among cluster nodes. The improved data transfer efficiency provided by the integration of transparent data compression yields performance improvements ranging between 1.11x and 2.07x across four data-intensive scale-out GPU workloads. To investigate the impact of programming abstractions for data placement in NUMA systems, a comprehensive evaluation of the PGASUS framework for NUMA-aware C++ application development is conducted. On a wide range of test systems, the evaluation demonstrates that PGASUS does not only improve the developer experience across all workloads, but that it is also capable of outperforming NUMA-agnostic implementations with average performance improvements of 1.56x. Based on these programming abstractions, this thesis demonstrates that by providing a sufficient degree of abstraction, the accessibility of heterogeneous system resources can be improved for application developers without occluding performance-critical properties of the underlying hardware.},
  language  = {en}
}
@misc{UllrichVladovaEigelshovenetal.2022,
  author    = {Ullrich, Andr{\´e} and Vladova, Gergana and Eigelshoven, Felix and Renz, Andr{\´e}},
  title     = {Data mining of scientific research on artificial intelligence in teaching and administration in higher education institutions},
  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    = {160},
  issn      = {1867-5808},
  doi       = {10.25932/publishup-58907},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-589077},
  pages     = {18},
  year      = {2022},
  abstract  = {Teaching and learning as well as administrative processes are still experiencing intensive changes with the rise of artificial intelligence (AI) technologies and its diverse application opportunities in the context of higher education. Therewith, the scientific interest in the topic in general, but also specific focal points rose as well. However, there is no structured overview on AI in teaching and administration processes in higher education institutions that allows to identify major research topics and trends, and concretizing peculiarities and develops recommendations for further action. To overcome this gap, this study seeks to systematize the current scientific discourse on AI in teaching and administration in higher education institutions. This study identified an (1) imbalance in research on AI in educational and administrative contexts, (2) an imbalance in disciplines and lack of interdisciplinary research, (3) inequalities in cross-national research activities, as well as (4) neglected research topics and paths. In this way, a comparative analysis between AI usage in administration and teaching and learning processes, a systematization of the state of research, an identification of research gaps as well as further research path on AI in higher education institutions are contributed to research.},
  language  = {en}
}
@phdthesis{Draisbach2022,
  author    = {Draisbach, Uwe},
  title     = {Efficient duplicate detection and the impact of transitivity},
  doi       = {10.25932/publishup-57214},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-572140},
  school      = {Universit{\"a}t Potsdam},
  pages     = {x, 150},
  year      = {2022},
  abstract  = {Duplicate detection describes the process of finding multiple representations of the same real-world entity in the absence of a unique identifier, and has many application areas, such as customer relationship management, genealogy and social sciences, or online shopping. Due to the increasing amount of data in recent years, the problem has become even more challenging on the one hand, but has led to a renaissance in duplicate detection research on the other hand. This thesis examines the effects and opportunities of transitive relationships on the duplicate detection process. Transitivity implies that if record pairs ⟨ri,rj⟩ and ⟨rj,rk⟩ are classified as duplicates, then also record pair ⟨ri,rk⟩ has to be a duplicate. However, this reasoning might contradict with the pairwise classification, which is usually based on the similarity of objects. An essential property of similarity, in contrast to equivalence, is that similarity is not necessarily transitive. First, we experimentally evaluate the effect of an increasing data volume on the threshold selection to classify whether a record pair is a duplicate or non-duplicate. Our experiments show that independently of the pair selection algorithm and the used similarity measure, selecting a suitable threshold becomes more difficult with an increasing number of records due to an increased probability of adding a false duplicate to an existing cluster. Thus, the best threshold changes with the dataset size, and a good threshold for a small (possibly sampled) dataset is not necessarily a good threshold for a larger (possibly complete) dataset. As data grows over time, earlier selected thresholds are no longer a suitable choice, and the problem becomes worse for datasets with larger clusters. Second, we present with the Duplicate Count Strategy (DCS) and its enhancement DCS++ two alternatives to the standard Sorted Neighborhood Method (SNM) for the selection of candidate record pairs. DCS adapts SNMs window size based on the number of detected duplicates and DCS++ uses transitive dependencies to save complex comparisons for finding duplicates in larger clusters. We prove that with a proper (domain- and data-independent!) threshold, DCS++ is more efficient than SNM without loss of effectiveness. Third, we tackle the problem of contradicting pairwise classifications. Usually, the transitive closure is used for pairwise classifications to obtain a transitively closed result set. However, the transitive closure disregards negative classifications. We present three new and several existing clustering algorithms and experimentally evaluate them on various datasets and under various algorithm configurations. The results show that the commonly used transitive closure is inferior to most other clustering algorithms, especially for the precision of results. In scenarios with larger clusters, our proposed EMCC algorithm is, together with Markov Clustering, the best performing clustering approach for duplicate detection, although its runtime is longer than Markov Clustering due to the subexponential time complexity. EMCC especially outperforms Markov Clustering regarding the precision of the results and additionally has the advantage that it can also be used in scenarios where edge weights are not available.},
  language  = {en}
}
@phdthesis{Niephaus2022,
  author    = {Niephaus, Fabio},
  title     = {Exploratory tool-building platforms for polyglot virtual machines},
  doi       = {10.25932/publishup-57177},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-571776},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xxi, 249},
  year      = {2022},
  abstract  = {Polyglot programming allows developers to use multiple programming languages within the same software project. While it is common to use more than one language in certain programming domains, developers also apply polyglot programming for other purposes such as to re-use software written in other languages. Although established approaches to polyglot programming come with significant limitations, for example, in terms of performance and tool support, developers still use them to be able to combine languages. Polyglot virtual machines (VMs) such as GraalVM provide a new level of polyglot programming, allowing languages to directly interact with each other. This reduces the amount of glue code needed to combine languages, results in better performance, and enables tools such as debuggers to work across languages. However, only a little research has focused on novel tools that are designed to support developers in building software with polyglot VMs. One reason is that tool-building is often an expensive activity, another one is that polyglot VMs are still a moving target as their use cases and requirements are not yet well understood. In this thesis, we present an approach that builds on existing self-sustaining programming systems such as Squeak/Smalltalk to enable exploratory programming, a practice for exploring and gathering software requirements, and re-use their extensive tool-building capabilities in the context of polyglot VMs. Based on TruffleSqueak, our implementation for the GraalVM, we further present five case studies that demonstrate how our approach helps tool developers to design and build tools for polyglot programming. We further show that TruffleSqueak can also be used by application developers to build and evolve polyglot applications at run-time and by language and runtime developers to understand the dynamic behavior of GraalVM languages and internals. Since our platform allows all these developers to apply polyglot programming, it can further help to better understand the advantages, use cases, requirements, and challenges of polyglot VMs. Moreover, we demonstrate that our approach can also be applied to other polyglot VMs and that insights gained through it are transferable to other programming systems. We conclude that our research on tools for polyglot programming is an important step toward making polyglot VMs more approachable for developers in practice. With good tool support, we believe polyglot VMs can make it much more common for developers to take advantage of multiple languages and their ecosystems when building software.},
  language  = {en}
}
@misc{AlLabanRegerLucke2022,
  author    = {Al Laban, Firas and Reger, Martin and Lucke, Ulrike},
  title     = {Closing the Policy Gap in the Academic Bridge},
  series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  journal   = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  number    = {1310},
  issn      = {1866-8372},
  doi       = {10.25932/publishup-58357},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-583572},
  pages     = {22},
  year      = {2022},
  abstract  = {The highly structured nature of the educational sector demands effective policy mechanisms close to the needs of the field. That is why evidence-based policy making, endorsed by the European Commission under Erasmus+ Key Action 3, aims to make an alignment between the domains of policy and practice. Against this background, this article addresses two issues: First, that there is a vertical gap in the translation of higher-level policies to local strategies and regulations. Second, that there is a horizontal gap between educational domains regarding the policy awareness of individual players. This was analyzed in quantitative and qualitative studies with domain experts from the fields of virtual mobility and teacher training. From our findings, we argue that the combination of both gaps puts the academic bridge from secondary to tertiary education at risk, including the associated knowledge proficiency levels. We discuss the role of digitalization in the academic bridge by asking the question: which value does the involved stakeholders expect from educational policies? As a theoretical basis, we rely on the model of value co-creation for and by stakeholders. We describe the used instruments along with the obtained results and proposed benefits. Moreover, we reflect on the methodology applied, and we finally derive recommendations for future academic bridge policies.},
  language  = {en}
}
@phdthesis{Melnichenko2022,
  author    = {Melnichenko, Anna},
  title     = {Selfish Creation of Realistic Networks},
  doi       = {10.25932/publishup-54814},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-548141},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xi, 175},
  year      = {2022},
  abstract  = {Complex networks like the Internet or social networks are fundamental parts of our everyday lives. It is essential to understand their structural properties and how these networks are formed. A game-theoretic approach to network design problems has become of high interest in the last decades. The reason is that many real-world networks are the outcomes of decentralized strategic behavior of independent agents without central coordination. Fabrikant, Luthra, Maneva, Papadimitriou, and Schenker proposed a game-theoretic model aiming to explain the formation of the Internet-like networks. In this model, called the Network Creation Game, agents are associated with nodes of a network. Each agent seeks to maximize her centrality by establishing costly connections to other agents. The model is relatively simple but shows a high potential in modeling complex real-world networks. In this thesis, we contribute to the line of research on variants of the Network Creation Games. Inspired by real-world networks, we propose and analyze several novel network creation models. We aim to understand the impact of certain realistic modeling assumptions on the structure of the created networks and the involved agents' behavior. The first natural additional objective that we consider is the network's robustness. We consider a game where the agents seek to maximize their centrality and, at the same time, the stability of the created network against random edge failure. Our second point of interest is a model that incorporates an underlying geometry. We consider a network creation model where the agents correspond to points in some underlying space and where edge lengths are equal to the distances between the endpoints in that space. The geometric setting captures many physical real-world networks like transport networks and fiber-optic communication networks. We focus on the formation of social networks and consider two models that incorporate particular realistic behavior observed in real-world networks. In the first model, we embed the anti-preferential attachment link formation. Namely, we assume that the cost of the connection is proportional to the popularity of the targeted agent. Our second model is based on the observation that the probability of two persons to connect is inversely proportional to the length of their shortest chain of mutual acquaintances. For each of the four models above, we provide a complete game-theoretical analysis. In particular, we focus on distinctive structural properties of the equilibria, the hardness of computing a best response, the quality of equilibria in comparison to the centrally designed socially optimal networks. We also analyze the game dynamics, i.e., the process of sequential strategic improvements by the agents, and analyze the convergence to an equilibrium state and its properties.},
  language  = {en}
}
@phdthesis{Haarmann2022,
  author    = {Haarmann, Stephan},
  title     = {WICKR: A Joint Semantics for Flexible Processes and Data},
  doi       = {10.25932/publishup-54613},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-546137},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xvii, 191},
  year      = {2022},
  abstract  = {Knowledge-intensive business processes are flexible and data-driven. Therefore, traditional process modeling languages do not meet their requirements: These languages focus on highly structured processes in which data plays a minor role. As a result, process-oriented information systems fail to assist knowledge workers on executing their processes. We propose a novel case management approach that combines flexible activity-centric processes with data models, and we provide a joint semantics using colored Petri nets. The approach is suited to model, verify, and enact knowledge-intensive processes and can aid the development of information systems that support knowledge work. Knowledge-intensive processes are human-centered, multi-variant, and data-driven. Typical domains include healthcare, insurances, and law. The processes cannot be fully modeled, since the underlying knowledge is too vast and changes too quickly. Thus, models for knowledge-intensive processes are necessarily underspecified. In fact, a case emerges gradually as knowledge workers make informed decisions. Knowledge work imposes special requirements on modeling and managing respective processes. They include flexibility during design and execution, ad-hoc adaption to unforeseen situations, and the integration of behavior and data. However, the predominantly used process modeling languages (e.g., BPMN) are unsuited for this task. Therefore, novel modeling languages have been proposed. Many of them focus on activities' data requirements and declarative constraints rather than imperative control flow. Fragment-Based Case Management, for example, combines activity-centric imperative process fragments with declarative data requirements. At runtime, fragments can be combined dynamically, and new ones can be added. Yet, no integrated semantics for flexible activity-centric process models and data models exists. In this thesis, Wickr, a novel case modeling approach extending fragment-based Case Management, is presented. It supports batch processing of data, sharing data among cases, and a full-fledged data model with associations and multiplicity constraints. We develop a translational semantics for Wickr targeting (colored) Petri nets. The semantics assert that a case adheres to the constraints in both the process fragments and the data models. Among other things, multiplicity constraints must not be violated. Furthermore, the semantics are extended to multiple cases that operate on shared data. Wickr shows that the data structure may reflect process behavior and vice versa. Based on its semantics, prototypes for executing and verifying case models showcase the feasibility of Wickr. Its applicability to knowledge-intensive and to data-centric processes is evaluated using well-known requirements from related work.},
  language  = {en}
}
@article{UllrichVladovaEigelshovenetal.2022,
  author    = {Ullrich, Andr{\´e} and Vladova, Gergana and Eigelshoven, Felix and Renz, Andr{\´e}},
  title     = {Data mining of scientific research on artificial intelligence in teaching and administration in higher education institutions},
  series = {Discover artificial intelligence},
  volume    = {2},
  journal   = {Discover artificial intelligence},
  publisher = {Springer},
  address   = {Cham},
  issn      = {2731-0809},
  doi       = {10.1007/s44163-022-00031-7},
  pages     = {18},
  year      = {2022},
  abstract  = {Teaching and learning as well as administrative processes are still experiencing intensive changes with the rise of artificial intelligence (AI) technologies and its diverse application opportunities in the context of higher education. Therewith, the scientific interest in the topic in general, but also specific focal points rose as well. However, there is no structured overview on AI in teaching and administration processes in higher education institutions that allows to identify major research topics and trends, and concretizing peculiarities and develops recommendations for further action. To overcome this gap, this study seeks to systematize the current scientific discourse on AI in teaching and administration in higher education institutions. This study identified an (1) imbalance in research on AI in educational and administrative contexts, (2) an imbalance in disciplines and lack of interdisciplinary research, (3) inequalities in cross-national research activities, as well as (4) neglected research topics and paths. In this way, a comparative analysis between AI usage in administration and teaching and learning processes, a systematization of the state of research, an identification of research gaps as well as further research path on AI in higher education institutions are contributed to research.},
  language  = {en}
}
@article{BenderKoerppen2022,
  author    = {Bender, Benedict and K{\"o}rppen, Tim},
  title     = {Integriert statt isoliert},
  series = {Digital business : cloud},
  volume    = {26},
  journal   = {Digital business : cloud},
  number    = {1},
  publisher = {WIN-Verlag GmbH \& Co. KG},
  address   = {Vaterstetten},
  issn      = {2510-344X},
  pages     = {26 -- 27},
  year      = {2022},
  abstract  = {Dass Daten und Analysen Innovationstreiber sind und nicht mehr nur einen Hygienefaktor darstellen, haben viele Unternehmen erkannt. Um Potenziale zu heben, m{\"u}ssen Daten zielf{\"u}hrend integriert werden. Komplexe Systemlandschaften und isolierte Datenbest{\"a}nde erschweren dies. Technologien f{\"u}r die erfolgreiche Umsetzung von datengetriebenem Management m{\"u}ssen richtig eingesetzt werden.},
  language  = {de}
}
@phdthesis{Dehnert2022,
  author    = {Dehnert, Maik},
  title     = {Studies on the Digital Transformation of Incumbent Organizations},
  doi       = {10.25932/publishup-54832},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-548324},
  school      = {Universit{\"a}t Potsdam},
  pages     = {339},
  year      = {2022},
  abstract  = {Traditional organizations are strongly encouraged by emerging digital customer behavior and digital competition to transform their businesses for the digital age. Incumbents are particularly exposed to the field of tension between maintaining and renewing their business model. Banking is one of the industries most affected by digitalization, with a large stream of digital innovations around Fintech. Most research contributions focus on digital innovations, such as Fintech, but there are only a few studies on the related challenges and perspectives of incumbent organizations, such as traditional banks. Against this background, this dissertation examines the specific causes, effects and solutions for traditional banks in digital transformation - an underrepresented research area so far. The first part of the thesis examines how digitalization has changed the latent customer expectations in banking and studies the underlying technological drivers of evolving business-to-consumer (B2C) business models. Online consumer reviews are systematized to identify latent concepts of customer behavior and future decision paths as strategic digitalization effects. Furthermore, the service attribute preferences, the impact of influencing factors and the underlying customer segments are uncovered for checking accounts in a discrete choice experiment. The dissertation contributes here to customer behavior research in digital transformation, moving beyond the technology acceptance model. In addition, the dissertation systematizes value proposition types in the evolving discourse around smart products and services as key drivers of business models and market power in the platform economy. The second part of the thesis focuses on the effects of digital transformation on the strategy development of financial service providers, which are classified along with their firm performance levels. Standard types are derived based on fuzzy-set qualitative comparative analysis (fsQCA), with facade digitalization as one typical standard type for low performing incumbent banks that lack a holistic strategic response to digital transformation. Based on this, the contradictory impact of digitalization measures on key business figures is examined for German savings banks, confirming that the shift towards digital customer interaction was not accompanied by new revenue models diminishing bank profitability. The dissertation further contributes to the discourse on digitalized work designs and the consequences for job perceptions in banking customer advisory. The threefold impact of the IT support perceived in customer interaction on the job satisfaction of customer advisors is disentangled. In the third part of the dissertation, solutions are developed design-oriented for core action areas of digitalized business models, i.e., data and platforms. A consolidated taxonomy for data-driven business models and a future reference model for digital banking have been developed. The impact of the platform economy is demonstrated here using the example of the market entry by Bigtech. The role-based e3-value modeling is extended by meta-roles and role segments and linked to value co-creation mapping in VDML. In this way, the dissertation extends enterprise modeling research on platform ecosystems and value co-creation using the example of banking.},
  language  = {en}
}
@article{SteinertStabernack2022,
  author    = {Steinert, Fritjof and Stabernack, Benno},
  title     = {Architecture of a low latency H.264/AVC video codec for robust ML based image classification how region of interests can minimize the impact of coding artifacts},
  series = {Journal of Signal Processing Systems for Signal, Image, and Video Technology},
  volume    = {94},
  journal   = {Journal of Signal Processing Systems for Signal, Image, and Video Technology},
  number    = {7},
  publisher = {Springer},
  address   = {New York},
  issn      = {1939-8018},
  doi       = {10.1007/s11265-021-01727-2},
  pages     = {693 -- 708},
  year      = {2022},
  abstract  = {The use of neural networks is considered as the state of the art in the field of image classification. A large number of different networks are available for this purpose, which, appropriately trained, permit a high level of classification accuracy. Typically, these networks are applied to uncompressed image data, since a corresponding training was also carried out using image data of similar high quality. However, if image data contains image errors, the classification accuracy deteriorates drastically. This applies in particular to coding artifacts which occur due to image and video compression. Typical application scenarios for video compression are narrowband transmission channels for which video coding is required but a subsequent classification is to be carried out on the receiver side. In this paper we present a special H.264/Advanced Video Codec (AVC) based video codec that allows certain regions of a picture to be coded with near constant picture quality in order to allow a reliable classification using neural networks, whereas the remaining image will be coded using constant bit rate. We have combined this feature with the ability to run with lowest latency properties, which is usually also required in remote control applications scenarios. The codec has been implemented as a fully hardwired High Definition video capable hardware architecture which is suitable for Field Programmable Gate Arrays.},
  language  = {en}
}
@article{BonifatiMiorNaumannetal.2022,
  author    = {Bonifati, Angela and Mior, Michael J. and Naumann, Felix and Noack, Nele Sina},
  title     = {How inclusive are we?},
  series = {SIGMOD record / Association for Computing Machinery, Special Interest Group on Management of Data},
  volume    = {50},
  journal   = {SIGMOD record / Association for Computing Machinery, Special Interest Group on Management of Data},
  number    = {4},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {0163-5808},
  doi       = {10.1145/3516431.3516438},
  pages     = {30 -- 35},
  year      = {2022},
  abstract  = {ACM SIGMOD, VLDB and other database organizations have committed to fostering an inclusive and diverse community, as do many other scientific organizations. Recently, different measures have been taken to advance these goals, especially for underrepresented groups. One possible measure is double-blind reviewing, which aims to hide gender, ethnicity, and other properties of the authors. <br /> We report the preliminary results of a gender diversity analysis of publications of the database community across several peer-reviewed venues, and also compare women's authorship percentages in both single-blind and double-blind venues along the years. We also obtained a cross comparison of the obtained results in data management with other relevant areas in Computer Science.},
  language  = {en}
}
@article{AlnoorTiberiusAtiyahetal.2022,
  author    = {Alnoor, Alhamzah and Tiberius, Victor and Atiyah, Abbas Gatea and Khaw, Khai Wah and Yin, Teh Sin and Chew, XinYing and Abbas, Sammar},
  title     = {How positive and negative electronic word of mouth (eWOM) affects customers' intention to use social commerce?},
  series = {International journal of human computer interaction},
  journal   = {International journal of human computer interaction},
  publisher = {Taylor \& Francis},
  address   = {New York},
  issn      = {1044-7318},
  doi       = {10.1080/10447318.2022.2125610},
  pages     = {1 -- 30},
  year      = {2022},
  abstract  = {Advances in Web 2.0 technologies have led to the widespread assimilation of electronic commerce platforms as an innovative shopping method and an alternative to traditional shopping. However, due to pro-technology bias, scholars focus more on adopting technology, and slightly less attention has been given to the impact of electronic word of mouth (eWOM) on customers' intention to use social commerce. This study addresses the gap by examining the intention through exploring the effect of eWOM on males' and females' intentions and identifying the mediation of perceived crowding. To this end, we adopted a dual-stage multi-group structural equation modeling and artificial neural network (SEM-ANN) approach. We successfully extended the eWOM concept by integrating negative and positive factors and perceived crowding. The results reveal the causal and non-compensatory relationships between the constructs. The variables supported by the SEM analysis are adopted as the ANN model's input neurons. According to the natural significance obtained from the ANN approach, males' intentions to accept social commerce are related mainly to helping the company, followed by core functionalities. In contrast, females are highly influenced by technical aspects and mishandling. The ANN model predicts customers' intentions to use social commerce with an accuracy of 97\%. We discuss the theoretical and practical implications of increasing customers' intention toward social commerce channels among consumers based on our findings.},
  language  = {en}
}
@book{EichenrothReinHirschfeld2022,
  author    = {Eichenroth, Friedrich and Rein, Patrick and Hirschfeld, Robert},
  title     = {Fast packrat parsing in a live programming environment},
  series = {Technische Berichte des Hasso-Plattner-Instituts f{\"u}r Digital Engineering an der Universit{\"a}t Potsdam},
  journal   = {Technische Berichte des Hasso-Plattner-Instituts f{\"u}r Digital Engineering an der Universit{\"a}t Potsdam},
  number    = {135},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-503-3},
  issn      = {1613-5652},
  doi       = {10.25932/publishup-49124},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-491242},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {79},
  year      = {2022},
  abstract  = {Language developers who design domain-specific languages or new language features need a way to make fast changes to language definitions. Those fast changes require immediate feedback. Also, it should be possible to parse the developed languages quickly to handle extensive sets of code. Parsing expression grammars provides an easy to understand method for language definitions. Packrat parsing is a method to parse grammars of this kind, but this method is unable to handle left-recursion properly. Existing solutions either partially rewrite left-recursive rules and partly forbid them, or use complex extensions to packrat parsing that are hard to understand and cost-intensive. We investigated methods to make parsing as fast as possible, using easy to follow algorithms while not losing the ability to make fast changes to grammars. We focused our efforts on two approaches. One is to start from an existing technique for limited left-recursion rewriting and enhance it to work for general left-recursive grammars. The second approach is to design a grammar compilation process to find left-recursion before parsing, and in this way, reduce computational costs wherever possible and generate ready to use parser classes. Rewriting parsing expression grammars is a task that, if done in a general way, unveils a large number of cases such that any rewriting algorithm surpasses the complexity of other left-recursive parsing algorithms. Lookahead operators introduce this complexity. However, most languages have only little portions that are left-recursive and in virtually all cases, have no indirect or hidden left-recursion. This means that the distinction of left-recursive parts of grammars from components that are non-left-recursive holds great improvement potential for existing parsers. In this report, we list all the required steps for grammar rewriting to handle left-recursion, including grammar analysis, grammar rewriting itself, and syntax tree restructuring. Also, we describe the implementation of a parsing expression grammar framework in Squeak/Smalltalk and the possible interactions with the already existing parser Ohm/S. We quantitatively benchmarked this framework directing our focus on parsing time and the ability to use it in a live programming context. Compared with Ohm, we achieved massive parsing time improvements while preserving the ability to use our parser it as a live programming tool. The work is essential because, for one, we outlined the difficulties and complexity that come with grammar rewriting. Also, we removed the existing limitations that came with left-recursion by eliminating them before parsing.},
  language  = {en}
}
@book{FreundRaetschHradilaketal.2022,
  author    = {Freund, Rieke and R{\"a}tsch, Jan Philip and Hradilak, Franziska and Vidic, Benedikt and Heß, Oliver and Lißner, Nils and W{\"o}lert, Hendrik and Lincke, Jens and Beckmann, Tom and Hirschfeld, Robert},
  title     = {Implementing a crowd-sourced picture archive for Bad Harzburg},
  number    = {149},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-545-3},
  issn      = {1613-5652},
  doi       = {10.25932/publishup-56029},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-560291},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {x, 191},
  year      = {2022},
  abstract  = {Pictures are a medium that helps make the past tangible and preserve memories. Without context, they are not able to do so. Pictures are brought to life by their associated stories. However, the older pictures become, the fewer contemporary witnesses can tell these stories. Especially for large, analog picture archives, knowledge and memories are spread over many people. This creates several challenges: First, the pictures must be digitized to save them from decaying and make them available to the public. Since a simple listing of all the pictures is confusing, the pictures should be structured accessibly. Second, known information that makes the stories vivid needs to be added to the pictures. Users should get the opportunity to contribute their knowledge and memories. To make this usable for all interested parties, even for older, less technophile generations, the interface should be intuitive and error-tolerant. The resulting requirements are not covered in their entirety by any existing software solution without losing the intuitive interface or the scalability of the system. Therefore, we have developed our digital picture archive within the scope of a bachelor project in cooperation with the Bad Harzburg-Stiftung. For the implementation of this web application, we use the UI framework React in the frontend, which communicates via a GraphQL interface with the Content Management System Strapi in the backend. The use of this system enables our project partner to create an efficient process from scanning analog pictures to presenting them to visitors in an organized and annotated way. To customize the solution for both picture delivery and information contribution for our target group, we designed prototypes and evaluated them with people from Bad Harzburg. This helped us gain valuable insights into our system's usability and future challenges as well as requirements. Our web application is already being used daily by our project partner. During the project, we still came up with numerous ideas for additional features to further support the exchange of knowledge.},
  language  = {en}
}
@book{SchneiderMaximovaGiese2022,
  author    = {Schneider, Sven and Maximova, Maria and Giese, Holger},
  title     = {Invariant Analysis for Multi-Agent Graph Transformation Systems using k-Induction},
  number    = {143},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-531-6},
  issn      = {1613-5652},
  doi       = {10.25932/publishup-54585},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-545851},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {37},
  year      = {2022},
  abstract  = {The analysis of behavioral models such as Graph Transformation Systems (GTSs) is of central importance in model-driven engineering. However, GTSs often result in intractably large or even infinite state spaces and may be equipped with multiple or even infinitely many start graphs. To mitigate these problems, static analysis techniques based on finite symbolic representations of sets of states or paths thereof have been devised. We focus on the technique of k-induction for establishing invariants specified using graph conditions. To this end, k-induction generates symbolic paths backwards from a symbolic state representing a violation of a candidate invariant to gather information on how that violation could have been reached possibly obtaining contradictions to assumed invariants. However, GTSs where multiple agents regularly perform actions independently from each other cannot be analyzed using this technique as of now as the independence among backward steps may prevent the gathering of relevant knowledge altogether. In this paper, we extend k-induction to GTSs with multiple agents thereby supporting a wide range of additional GTSs. As a running example, we consider an unbounded number of shuttles driving on a large-scale track topology, which adjust their velocity to speed limits to avoid derailing. As central contribution, we develop pruning techniques based on causality and independence among backward steps and verify that k-induction remains sound under this adaptation as well as terminates in cases where it did not terminate before.},
  language  = {en}
}
@book{SchneiderMaximovaGiese2022,
  author    = {Schneider, Sven and Maximova, Maria and Giese, Holger},
  title     = {Probabilistic metric temporal graph logic},
  number    = {146},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-532-3},
  issn      = {1613-5652},
  doi       = {10.25932/publishup-54586},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-545867},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {34},
  year      = {2022},
  abstract  = {Cyber-physical systems often encompass complex concurrent behavior with timing constraints and probabilistic failures on demand. The analysis whether such systems with probabilistic timed behavior adhere to a given specification is essential. When the states of the system can be represented by graphs, the rule-based formalism of Probabilistic Timed Graph Transformation Systems (PTGTSs) can be used to suitably capture structure dynamics as well as probabilistic and timed behavior of the system. The model checking support for PTGTSs w.r.t. properties specified using Probabilistic Timed Computation Tree Logic (PTCTL) has been already presented. Moreover, for timed graph-based runtime monitoring, Metric Temporal Graph Logic (MTGL) has been developed for stating metric temporal properties on identified subgraphs and their structural changes over time. In this paper, we (a) extend MTGL to the Probabilistic Metric Temporal Graph Logic (PMTGL) by allowing for the specification of probabilistic properties, (b) adapt our MTGL satisfaction checking approach to PTGTSs, and (c) combine the approaches for PTCTL model checking and MTGL satisfaction checking to obtain a Bounded Model Checking (BMC) approach for PMTGL. In our evaluation, we apply an implementation of our BMC approach in AutoGraph to a running example.},
  language  = {en}
}
@book{KlinkeVerhoevenRothetal.2022,
  author    = {Klinke, Paula and Verhoeven, Silvan and Roth, Felix and Hagemann, Linus and Alnawa, Tarik and Lincke, Jens and Rein, Patrick and Hirschfeld, Robert},
  title     = {Tool support for collaborative creation of interactive storytelling media},
  number    = {141},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-521-7},
  issn      = {1613-5652},
  doi       = {10.25932/publishup-51857},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-518570},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {x, 167},
  year      = {2022},
  abstract  = {Scrollytellings are an innovative form of web content. Combining the benefits of books, images, movies, and video games, they are a tool to tell compelling stories and provide excellent learning opportunities. Due to their multi-modality, creating high-quality scrollytellings is not an easy task. Different professions, such as content designers, graphics designers, and developers, need to collaborate to get the best out of the possibilities the scrollytelling format provides. Collaboration unlocks great potential. However, content designers cannot create scrollytellings directly and always need to consult with developers to implement their vision. This can result in misunderstandings. Often, the resulting scrollytelling will not match the designer's vision sufficiently, causing unnecessary iterations. Our project partner Typeshift specializes in the creation of individualized scrollytellings for their clients. Examined existing solutions for authoring interactive content are not optimally suited for creating highly customized scrollytellings while still being able to manipulate all their elements programmatically. Based on their experience and expertise, we developed an editor to author scrollytellings in the lively.next live-programming environment. In this environment, a graphical user interface for content design is combined with powerful possibilities for programming behavior with the morphic system. The editor allows content designers to take on large parts of the creation process of scrollytellings on their own, such as creating the visible elements, animating content, and fine-tuning the scrollytelling. Hence, developers can focus on interactive elements such as simulations and games. Together with Typeshift, we evaluated the tool by recreating an existing scrollytelling and identified possible future enhancements. Our editor streamlines the creation process of scrollytellings. Content designers and developers can now both work on the same scrollytelling. Due to the editor inside of the lively.next environment, they can both work with a set of tools familiar to them and their traits. Thus, we mitigate unnecessary iterations and misunderstandings by enabling content designers to realize large parts of their vision of a scrollytelling on their own. Developers can add advanced and individual behavior. Thus, developers and content designers benefit from a clearer distribution of tasks while keeping the benefits of collaboration.},
  language  = {en}
}
@book{DuerschReinMattisetal.2022,
  author    = {D{\"u}rsch, Falco and Rein, Patrick and Mattis, Toni and Hirschfeld, Robert},
  title     = {Learning from failure},
  number    = {145},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-528-6},
  issn      = {1613-5652},
  doi       = {10.25932/publishup-53755},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-537554},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {87},
  year      = {2022},
  abstract  = {Regression testing is a widespread practice in today's software industry to ensure software product quality. Developers derive a set of test cases, and execute them frequently to ensure that their change did not adversely affect existing functionality. As the software product and its test suite grow, the time to feedback during regression test sessions increases, and impedes programmer productivity: developers wait longer for tests to complete, and delays in fault detection render fault removal increasingly difficult. Test case prioritization addresses the problem of long feedback loops by reordering test cases, such that test cases of high failure probability run first, and test case failures become actionable early in the testing process. We ask, given test execution schedules reconstructed from publicly available data, to which extent can their fault detection efficiency improved, and which technique yields the most efficient test schedules with respect to APFD? To this end, we recover regression 6200 test sessions from the build log files of Travis CI, a popular continuous integration service, and gather 62000 accompanying changelists. We evaluate the efficiency of current test schedules, and examine the prioritization results of state-of-the-art lightweight, history-based heuristics. We propose and evaluate a novel set of prioritization algorithms, which connect software changes and test failures in a matrix-like data structure. Our studies indicate that the optimization potential is substantial, because the existing test plans score only 30\% APFD. The predictive power of past test failures proves to be outstanding: simple heuristics, such as repeating tests with failures in recent sessions, result in efficiency scores of 95\% APFD. The best-performing matrix-based heuristic achieves a similar score of 92.5\% APFD. In contrast to prior approaches, we argue that matrix-based techniques are useful beyond the scope of effective prioritization, and enable a number of use cases involving software maintenance. We validate our findings from continuous integration processes by extending a continuous testing tool within development environments with means of test prioritization, and pose further research questions. We think that our findings are suited to propel adoption of (continuous) testing practices, and that programmers' toolboxes should contain test prioritization as an existential productivity tool.},
  language  = {en}
}
@article{BlaesiusFriedrichLischeidetal.2022,
  author    = {Bl{\"a}sius, Thomas and Friedrich, Tobias and Lischeid, Julius and Meeks, Kitty and Schirneck, Friedrich Martin},
  title     = {Efficiently enumerating hitting sets of hypergraphs arising in data profiling},
  series = {Journal of computer and system sciences : JCSS},
  volume    = {124},
  journal   = {Journal of computer and system sciences : JCSS},
  publisher = {Elsevier},
  address   = {San Diego},
  issn      = {0022-0000},
  doi       = {10.1016/j.jcss.2021.10.002},
  pages     = {192 -- 213},
  year      = {2022},
  abstract  = {The transversal hypergraph problem asks to enumerate the minimal hitting sets of a hypergraph. If the solutions have bounded size, Eiter and Gottlob [SICOMP'95] gave an algorithm running in output-polynomial time, but whose space requirement also scales with the output. We improve this to polynomial delay and space. Central to our approach is the extension problem, deciding for a set X of vertices whether it is contained in any minimal hitting set. We show that this is one of the first natural problems to be W[3]-complete. We give an algorithm for the extension problem running in time O(m(vertical bar X vertical bar+1) n) and prove a SETH-lower bound showing that this is close to optimal. We apply our enumeration method to the discovery problem of minimal unique column combinations from data profiling. Our empirical evaluation suggests that the algorithm outperforms its worst-case guarantees on hypergraphs stemming from real-world databases.},
  language  = {en}
}
@article{vonSteinauSteinrueckKurth2022,
  author    = {von Steinau-Steinr{\"u}ck, Robert and Kurth, Paula Sophie},
  title     = {Das reformierte Statusfeststellungsverfahren in der Praxis},
  series = {NJW spezial},
  volume    = {19},
  journal   = {NJW spezial},
  number    = {24},
  publisher = {C.H. Beck},
  address   = {M{\"u}nchen},
  issn      = {1613-4621},
  pages     = {754 -- 755},
  year      = {2022},
  abstract  = {Das Statusfeststellungsverfahren erm{\"o}glicht auf Antrag bei der alleinzust{\"a}ndigen Deutschen Rentenversicherung Bund den Erhalt einer verbindlichen Einsch{\"a}tzung der h{\"a}ufig komplizierten und folgenschweren Abgrenzung einer selbstst{\"a}ndigen T{\"a}tigkeit von einer abh{\"a}ngigen Besch{\"a}ftigung. Zum 1.4.2022 wurde das Statusfeststellungsverfahren umfassend reformiert. In der Praxis haben sich die eingef{\"u}hrten Novellierungen bislang unterschiedlich bew{\"a}hrt.},
  language  = {de}
}
@article{vonSteinauSteinrueckMiller2022,
  author    = {von Steinau-Steinr{\"u}ck, Robert and Miller, Denis},
  title     = {R{\"u}ckzahlungsklauseln f{\"u}r Fortbildungen},
  series = {Neue juristische Wochenschrift : NJW Spezial},
  volume    = {19},
  journal   = {Neue juristische Wochenschrift : NJW Spezial},
  number    = {12},
  publisher = {C.H. Beck},
  address   = {M{\"u}nchen},
  issn      = {1613-4621},
  pages     = {370 -- 371},
  year      = {2022},
  abstract  = {Mit Urteil vom 1.3.2022 (NZA2022, NZA Jahr 2022 Seite 780) hat das BAG erneut {\"u}ber die Wirksamkeit einer R{\"u}ckzahlungsklausel in einer Fortbildungsvereinbarung entschieden. Die Entscheidung reiht sich in eine nicht leicht zu durchschauende Anzahl von Urteilen hierzu ein. Sie dient uns zum Anlass, einen {\"U}berblick {\"u}ber die Rechtsprechung zu geben.},
  language  = {de}
}
@article{vonSteinauSteinrueckHoeltge2022,
  author    = {von Steinau-Steinr{\"u}ck, Robert and H{\"o}ltge, Clara},
  title     = {Krieg in Europa},
  series = {NJW spezial},
  volume    = {19},
  journal   = {NJW spezial},
  number    = {8},
  publisher = {C.H. Beck},
  address   = {M{\"u}nchen},
  issn      = {1613-4621},
  pages     = {242 -- 243},
  year      = {2022},
  abstract  = {Am 24.2.2022 begann der russische Angriffskrieg in der Ukraine. Seitdem fliehen t{\"a}glich zahlreiche ukrainische Staatsb{\"u}rger in die Europ{\"a}ische Union, viele davon nach Deutschland. Vorrangig ist jetzt die Sicherung der Grundbed{\"u}rfnisse, wie Verpflegung, Unterkunft und medizinischer Versorgung. Daneben fragen sich Arbeitgeber, wie sie ukrainische Staatsb{\"u}rger m{\"o}glichst schnell besch{\"a}ftigen k{\"o}nnen. Wir geben einen {\"U}berblick {\"u}ber die M{\"o}glichkeiten, ukrainische Gefl{\"u}chtete m{\"o}glichst schnell in den deutschen Arbeitsmarkt zu integrieren.},
  language  = {de}
}
@phdthesis{Elsaid2022,
  author    = {Elsaid, Mohamed Esameldin Mohamed},
  title     = {Virtual machines live migration cost modeling and prediction},
  doi       = {10.25932/publishup-54001},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-540013},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xiv, 107},
  year      = {2022},
  abstract  = {Dynamic resource management is an essential requirement for private and public cloud computing environments. With dynamic resource management, the physical resources assignment to the cloud virtual resources depends on the actual need of the applications or the running services, which enhances the cloud physical resources utilization and reduces the offered services cost. In addition, the virtual resources can be moved across different physical resources in the cloud environment without an obvious impact on the running applications or services production. This means that the availability of the running services and applications in the cloud is independent on the hardware resources including the servers, switches and storage failures. This increases the reliability of using cloud services compared to the classical data-centers environments. In this thesis we briefly discuss the dynamic resource management topic and then deeply focus on live migration as the definition of the compute resource dynamic management. Live migration is a commonly used and an essential feature in cloud and virtual data-centers environments. Cloud computing load balance, power saving and fault tolerance features are all dependent on live migration to optimize the virtual and physical resources usage. As we will discuss in this thesis, live migration shows many benefits to cloud and virtual data-centers environments, however the cost of live migration can not be ignored. Live migration cost includes the migration time, downtime, network overhead, power consumption increases and CPU overhead. IT admins run virtual machines live migrations without an idea about the migration cost. So, resources bottlenecks, higher migration cost and migration failures might happen. The first problem that we discuss in this thesis is how to model the cost of the virtual machines live migration. Secondly, we investigate how to make use of machine learning techniques to help the cloud admins getting an estimation of this cost before initiating the migration for one of multiple virtual machines. Also, we discuss the optimal timing for a specific virtual machine before live migration to another server. Finally, we propose practical solutions that can be used by the cloud admins to be integrated with the cloud administration portals to answer the raised research questions above. Our research methodology to achieve the project objectives is to propose empirical models based on using VMware test-beds with different benchmarks tools. Then we make use of the machine learning techniques to propose a prediction approach for virtual machines live migration cost. Timing optimization for live migration is also proposed in this thesis based on using the cost prediction and data-centers network utilization prediction. Live migration with persistent memory clusters is also discussed at the end of the thesis. The cost prediction and timing optimization techniques proposed in this thesis could be practically integrated with VMware vSphere cluster portal such that the IT admins can now use the cost prediction feature and timing optimization option before proceeding with a virtual machine live migration. Testing results show that our proposed approach for VMs live migration cost prediction shows acceptable results with less than 20\% prediction error and can be easily implemented and integrated with VMware vSphere as an example of a commonly used resource management portal for virtual data-centers and private cloud environments. The results show that using our proposed VMs migration timing optimization technique also could save up to 51\% of migration time of the VMs migration time for memory intensive workloads and up to 27\% of the migration time for network intensive workloads. This timing optimization technique can be useful for network admins to save migration time with utilizing higher network rate and higher probability of success. At the end of this thesis, we discuss the persistent memory technology as a new trend in servers memory technology. Persistent memory modes of operation and configurations are discussed in detail to explain how live migration works between servers with different memory configuration set up. Then, we build a VMware cluster with persistent memory inside server and also with DRAM only servers to show the live migration cost difference between the VMs with DRAM only versus the VMs with persistent memory inside.},
  language  = {en}
}
@book{MeinelJohnWollowski2022,
  author    = {Meinel, Christoph and John, Catrina and Wollowski, Tobias},
  title     = {Die HPI Schul-Cloud - Von der Vision zur digitale Infrastruktur f{\"u}r deutsche Schulen},
  number    = {144},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-526-2},
  issn      = {1613-5652},
  doi       = {10.25932/publishup-53586},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-535860},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {v, 77},
  year      = {2022},
  abstract  = {Digitale Medien sind aus unserem Alltag kaum noch wegzudenken. Einer der zentralsten Bereiche f{\"u}r unsere Gesellschaft, die schulische Bildung, darf hier nicht hintanstehen. Wann immer der Einsatz digital unterst{\"u}tzter Tools p{\"a}dagogisch sinnvoll ist, muss dieser in einem sicheren Rahmen erm{\"o}glicht werden k{\"o}nnen. Die HPI Schul-Cloud ist dieser Vision gefolgt, die vom Nationalen IT-Gipfel 2016 angestoßen wurde und dem Bericht vorangestellt ist - gefolgt. Sie hat sich in den vergangenen f{\"u}nf Jahren vom Pilotprojekt zur unverzichtbaren IT-Infrastruktur f{\"u}r zahlreiche Schulen entwickelt. W{\"a}hrend der Corona-Pandemie hat sie f{\"u}r viele Tausend Schulen wichtige Unterst{\"u}tzung bei der Umsetzung ihres Bildungsauftrags geboten. Das Ziel, eine zukunftssichere und datenschutzkonforme Infrastruktur zur digitalen Unterst{\"u}tzung des Unterrichts zur Verf{\"u}gung zu stellen, hat sie damit mehr als erreicht. Aktuell greifen rund 1,4 Millionen Lehrkr{\"a}fte und Sch{\"u}lerinnen und Sch{\"u}ler bundesweit und an den deutschen Auslandsschulen auf die HPI Schul-Cloud zu.},
  language  = {de}
}
@phdthesis{Bartz2022,
  author    = {Bartz, Christian},
  title     = {Reducing the annotation burden: deep learning for optical character recognition using less manual annotations},
  doi       = {10.25932/publishup-55540},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-555407},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xxiv, 183},
  year      = {2022},
  abstract  = {Text is a ubiquitous entity in our world and daily life. We encounter it nearly everywhere in shops, on the street, or in our flats. Nowadays, more and more text is contained in digital images. These images are either taken using cameras, e.g., smartphone cameras, or taken using scanning devices such as document scanners. The sheer amount of available data, e.g., millions of images taken by Google Streetview, prohibits manual analysis and metadata extraction. Although much progress was made in the area of optical character recognition (OCR) for printed text in documents, broad areas of OCR are still not fully explored and hold many research challenges. With the mainstream usage of machine learning and especially deep learning, one of the most pressing problems is the availability and acquisition of annotated ground truth for the training of machine learning models because obtaining annotated training data using manual annotation mechanisms is time-consuming and costly. In this thesis, we address of how we can reduce the costs of acquiring ground truth annotations for the application of state-of-the-art machine learning methods to optical character recognition pipelines. To this end, we investigate how we can reduce the annotation cost by using only a fraction of the typically required ground truth annotations, e.g., for scene text recognition systems. We also investigate how we can use synthetic data to reduce the need of manual annotation work, e.g., in the area of document analysis for archival material. In the area of scene text recognition, we have developed a novel end-to-end scene text recognition system that can be trained using inexact supervision and shows competitive/state-of-the-art performance on standard benchmark datasets for scene text recognition. Our method consists of two independent neural networks, combined using spatial transformer networks. Both networks learn together to perform text localization and text recognition at the same time while only using annotations for the recognition task. We apply our model to end-to-end scene text recognition (meaning localization and recognition of words) and pure scene text recognition without any changes in the network architecture. In the second part of this thesis, we introduce novel approaches for using and generating synthetic data to analyze handwriting in archival data. First, we propose a novel preprocessing method to determine whether a given document page contains any handwriting. We propose a novel data synthesis strategy to train a classification model and show that our data synthesis strategy is viable by evaluating the trained model on real images from an archive. Second, we introduce the new analysis task of handwriting classification. Handwriting classification entails classifying a given handwritten word image into classes such as date, word, or number. Such an analysis step allows us to select the best fitting recognition model for subsequent text recognition; it also allows us to reason about the semantic content of a given document page without the need for fine-grained text recognition and further analysis steps, such as Named Entity Recognition. We show that our proposed approaches work well when trained on synthetic data. Further, we propose a flexible metric learning approach to allow zero-shot classification of classes unseen during the network's training. Last, we propose a novel data synthesis algorithm to train off-the-shelf pixel-wise semantic segmentation networks for documents. Our data synthesis pipeline is based on the famous Style-GAN architecture and can synthesize realistic document images with their corresponding segmentation annotation without the need for any annotated data!},
  language  = {en}
}
@book{MeinelWillemsStaubitzetal.2022,
  author    = {Meinel, Christoph and Willems, Christian and Staubitz, Thomas and Sauer, Dominic and Hagedorn, Christiane},
  title     = {openHPI},
  number    = {148},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-544-6},
  issn      = {1613-5652},
  doi       = {10.25932/publishup-56020},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-560208},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {125},
  year      = {2022},
  abstract  = {On the occasion of the 10th openHPI anniversary, this technical report provides information about the HPI MOOC platform, including its core features, technology, and architecture. In an introduction, the platform family with all partner platforms is presented; these now amount to nine platforms, including openHPI. This section introduces openHPI as an advisor and research partner in various projects. In the second chapter, the functionalities and common course formats of the platform are presented. The functionalities are divided into learner and admin features. The learner features section provides detailed information about performance records, courses, and the learning materials of which a course is composed: videos, texts, and quizzes. In addition, the learning materials can be enriched by adding external exercise tools that communicate with the HPI MOOC platform via the Learning Tools Interoperability (LTI) standard. Furthermore, the concept of peer assessments completed the possible learning materials. The section then proceeds with further information on the discussion forum, a fundamental concept of MOOCs compared to traditional e-learning offers. The section is concluded with a description of the quiz recap, learning objectives, mobile applications, gameful learning, and the help desk. The next part of this chapter deals with the admin features. The described functionality is restricted to describing the news and announcements, dashboards and statistics, reporting capabilities, research options with A/B testing, the course feed, and the TransPipe tool to support the process of creating automated or manual subtitles. The platform supports a large variety of additional features, but a detailed description of these features goes beyond the scope of this report. The chapter then elaborates on common course formats and openHPI teaching activities at the HPI. The chapter concludes with some best practices for course design and delivery. The third chapter provides insights into the technology and architecture behind openHPI. A special characteristic of the openHPI project is the conscious decision to operate the complete application from bare metal to platform development. Hence, the chapter starts with a section about the openHPI Cloud, including detailed information about the data center and devices, the used cloud software OpenStack and Ceph, as well as the openHPI Cloud Service provided for the HPI. Afterward, a section on the application technology stack and development tooling describes the application infrastructure components, the used automation, the deployment pipeline, and the tools used for monitoring and alerting. The chapter is concluded with detailed information about the technology stack and concrete platform implementation details. The section describes the service-oriented Ruby on Rails application, inter-service communication, and public APIs. It also provides more information on the design system and components used in the application. The section concludes with a discussion of the original microservice architecture, where we share our insights and reasoning for migrating back to a monolithic application. The last chapter provides a summary and an outlook on the future of digital education.},
  language  = {en}
}
@book{MeinelWillemsStaubitzetal.2022,
  author    = {Meinel, Christoph and Willems, Christian and Staubitz, Thomas and Sauer, Dominic and Hagedorn, Christiane},
  title     = {openHPI},
  number    = {150},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-546-0},
  issn      = {1613-5652},
  doi       = {10.25932/publishup-56179},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-561792},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {86},
  year      = {2022},
  abstract  = {Anl{\"a}sslich des 10-j{\"a}hrigen Jubil{\"a}ums von openHPI informiert dieser technische Bericht {\"u}ber die HPI-MOOC-Plattform einschließlich ihrer Kernfunktionen, Technologie und Architektur. In einer Einleitung wird die Plattformfamilie mit allen Partnerplattformen vorgestellt; diese belaufen sich inklusive openHPI aktuell auf neun Plattformen. In diesem Abschnitt wird außerdem gezeigt, wie openHPI als Berater und Forschungspartner in verschiedenen Projekten fungiert. Im zweiten Kapitel werden die Funktionalit{\"a}ten und g{\"a}ngigen Kursformate der Plattform pr{\"a}sentiert. Die Funktionalit{\"a}ten sind in Lerner- und Admin-Funktionen unterteilt. Der Bereich Lernerfunktionen bietet detaillierte Informationen zu Leistungsnachweisen, Kursen und den Lernmaterialien, aus denen sich ein Kurs zusammensetzt: Videos, Texte und Quiz. Dar{\"u}ber hinaus k{\"o}nnen die Lernmaterialien durch externe {\"U}bungstools angereichert werden, die {\"u}ber den Standard Learning Tools Interoperability (LTI) mit der HPI MOOC-Plattform kommunizieren. Das Konzept der Peer-Assessments rundet die m{\"o}glichen Lernmaterialien ab. Der Abschnitt geht dann weiter auf das Diskussionsforum ein, das einen grundlegenden Unterschied von MOOCs im Vergleich zu traditionellen E-Learning-Angeboten darstellt. Zum Abschluss des Abschnitts folgen eine Beschreibung von Quiz-Recap, Lernzielen, mobilen Anwendungen, spielerischen Lernens und dem Helpdesk. Der n{\"a}chste Teil dieses Kapitels besch{\"a}ftigt sich mit den Admin-Funktionen. Die Funktionalit{\"a}tsbeschreibung beschr{\"a}nkt sich Neuigkeiten und Ank{\"u}ndigungen, Dashboards und Statistiken, Berichtsfunktionen, Forschungsoptionen mit A/B-Tests, den Kurs-Feed und das TransPipe-Tool zur Unterst{\"u}tzung beim Erstellen von automatischen oder manuellen Untertiteln. Die Plattform unterst{\"u}tzt außerdem eine Vielzahl zus{\"a}tzlicher Funktionen, doch eine detaillierte Beschreibung dieser Funktionen w{\"u}rde den Rahmen des Berichts sprengen. Das Kapitel geht dann auf g{\"a}ngige Kursformate und openHPI-Lehrveranstaltungen am HPI ein, bevor es mit einigen Best Practices f{\"u}r die Gestaltung und Durchf{\"u}hrung von Kursen schließt. Zum Abschluss des technischen Berichts gibt das letzte Kapitel eine Zusammenfassung und einen Ausblick auf die Zukunft der digitalen Bildung. Ein besonderes Merkmal des openHPI-Projekts ist die bewusste Entscheidung, die komplette Anwendung von den physischen Netzwerkkomponenten bis zur Plattformentwicklung eigenst{\"a}ndig zu betreiben. Bei der vorliegenden deutschen Variante handelt es sich um eine gek{\"u}rzte {\"U}bersetzung des technischen Berichts 148, bei der kein Einblick in die Technologien und Architektur von openHPI gegeben wird. Interessierte Leser:innen k{\"o}nnen im technischen Bericht 148 (vollst{\"a}ndige englische Version) detaillierte Informationen zum Rechenzentrum und den Ger{\"a}ten, der Cloud-Software und dem openHPI Cloud Service aber auch zu Infrastruktur-Anwendungskomponenten wie Entwicklungstools, Automatisierung, Deployment-Pipeline und Monitoring erhalten. Außerdem finden sich dort weitere Informationen {\"u}ber den Technologiestack und konkrete Implementierungsdetails der Plattform inklusive der serviceorientierten Ruby on Rails-Anwendung, die Kommunikation zwischen den Diensten, {\"o}ffentliche APIs, sowie Designsystem und -komponenten. Der Abschnitt schließt mit einer Diskussion {\"u}ber die urspr{\"u}ngliche Microservice-Architektur und die Migration zu einer monolithischen Anwendung.},
  language  = {de}
}
@article{IhdePufahlVoelkeretal.2022,
  author    = {Ihde, Sven and Pufahl, Luise and V{\"o}lker, Maximilian and Goel, Asvin and Weske, Mathias},
  title     = {A framework for modeling and executing task},
  series = {Computing : archives for informatics and numerical computation},
  volume    = {104},
  journal   = {Computing : archives for informatics and numerical computation},
  publisher = {Springer},
  address   = {Wien},
  issn      = {0010-485X},
  doi       = {10.1007/s00607-022-01093-2},
  pages     = {2405 -- 2429},
  year      = {2022},
  abstract  = {As resources are valuable assets, organizations have to decide which resources to allocate to business process tasks in a way that the process is executed not only effectively but also efficiently. Traditional role-based resource allocation leads to effective process executions, since each task is performed by a resource that has the required skills and competencies to do so. However, the resulting allocations are typically not as efficient as they could be, since optimization techniques have yet to find their way in traditional business process management scenarios. On the other hand, operations research provides a rich set of analytical methods for supporting problem-specific decisions on resource allocation. This paper provides a novel framework for creating transparency on existing tasks and resources, supporting individualized allocations for each activity in a process, and the possibility to integrate problem-specific analytical methods of the operations research domain. To validate the framework, the paper reports on the design and prototypical implementation of a software architecture, which extends a traditional process engine with a dedicated resource management component. This component allows us to define specific resource allocation problems at design time, and it also facilitates optimized resource allocation at run time. The framework is evaluated using a real-world parcel delivery process. The evaluation shows that the quality of the allocation results increase significantly with a technique from operations research in contrast to the traditional applied rule-based approach.},
  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}
}
@inproceedings{KrasnovaGundlachBaumann2022,
  author    = {Krasnova, Hanna and Gundlach, Jana and Baumann, Annika},
  title     = {Coming back for more},
  series = {PACIS 2022 proceedings},
  booktitle = {PACIS 2022 proceedings},
  publisher = {AIS Electronic Library (AISeL)},
  address   = {[Erscheinungsort nicht ermittelbar]},
  isbn      = {9781958200018},
  year      = {2022},
  abstract  = {Recent spikes in social networking site (SNS) usage times have launched investigations into reasons for excessive SNS usage. Extending research on social factors (i.e., fear of missing out), this study considers the News Feed setup. More specifically, we suggest that the order of the News Feed (chronological vs. algorithmically assembled posts) affects usage behaviors. Against the background of the variable reward schedule, this study hypothesizes that the different orders exert serendipity differently. Serendipity, termed as unexpected lucky encounters with information, resembles variable rewards. Studies have evidenced a relation between variable rewards and excessive behaviors. Similarly, we hypothesize that order-induced serendipitous encounters affect SNS usage times and explore this link in a two-wave survey with an experimental setup (users using either chronological or algorithmic News Feeds). While theoretically extending explanations for increased SNS usage times by considering the News Feed order, practically the study will offer recommendations for relevant stakeholders.},
  language  = {en}
}
@article{NdashimyeHebieTjaden2022,
  author    = {Ndashimye, Felix and Hebie, Oumarou and Tjaden, Jasper},
  title     = {Effectiveness of WhatsApp for measuring migration in follow-up phone surveys},
  series = {Social science computer review},
  journal   = {Social science computer review},
  publisher = {Sage},
  address   = {Thousand Oaks},
  issn      = {0894-4393},
  doi       = {10.1177/08944393221111340},
  pages     = {20},
  year      = {2022},
  abstract  = {Phone surveys have increasingly become important data collection tools in developing countries, particularly in the context of sudden contact restrictions due to the COVID-19 pandemic. So far, there is limited evidence regarding the potential of the messenger service WhatsApp for remote data collection despite its large global coverage and expanding membership. WhatsApp may offer advantages in terms of reducing panel attrition and cutting survey costs. WhatsApp may offer additional benefits to migration scholars interested in cross-border migration behavior which is notoriously difficult to measure using conventional face-to-face surveys. In this field experiment, we compared the response rates between WhatsApp and interactive voice response (IVR) modes using a sample of 8446 contacts in Senegal and Guinea. At 12\%, WhatsApp survey response rates were nearly eight percentage points lower than IVR survey response rates. However, WhatsApp offers higher survey completion rates, substantially lower costs and does not introduce more sample selection bias compared to IVR. We discuss the potential of WhatsApp surveys in low-income contexts and provide practical recommendations for field implementation.},
  language  = {en}
}