@inproceedings{52816, abstract = {{Manufacturing companies face the challenge of reaching required quality standards. Using optical sensors and deep learning might help. However, training deep learning algorithms require large amounts of visual training data. Using domain randomization to generate synthetic image data can alleviate this bottleneck. This paper presents the application of synthetic image training data for optical quality inspections using visual sensor technology. The results show synthetically generated training data are appropriate for visual quality inspections.}}, author = {{Gräßler, Iris and Hieb, Michael}}, booktitle = {{Lectures}}, keywords = {{synthetic training data, machine vision quality gates, deep learning, automated inspection and quality control, production control}}, location = {{Nuremberg}}, pages = {{253--524}}, publisher = {{AMA Service GmbH, Von-Münchhausen-Str. 49, 31515 Wunstorf, Germany}}, title = {{{Creating Synthetic Training Datasets for Inspection in Machine Vision Quality Gates in Manufacturing}}}, doi = {{10.5162/smsi2023/d7.4}}, year = {{2023}}, } @misc{55850, abstract = {{This release covers the state of this prototype app at the end of the funding phase for the Paderborn University part of the Beethoven in the House project. It uses https://api.domestic-beethoven.eu/ld/BithCollection.jsonld as starting point for traversing the LOD graph, and reads data from the project pod available from https://bith.solidcommunity.net/public/bith.ttl (which has no content at the time of the release).}}, author = {{Kepper, Johannes}}, keywords = {{MEI, Edirom, Music Encoding Initiative, Linked Open Data, MELD}}, publisher = {{Zenodo}}, title = {{{DomesticBeethoven/bith-annotator: Release 2023-04}}}, doi = {{10.5281/ZENODO.7877741}}, year = {{2023}}, } @inproceedings{55833, abstract = {{We present a new multi-layered, conceptual model for associating musical source materials to musicological arguments. We describe our proposal for operationalizing these concepts through a framework for musical annotation which we have implemented using RDF. Briefly stated, this model shows how portions of digitized data in various files and formats can be identified, selected, labelled, and compared.}}, author = {{Shibata, Elisabete and Lewis, David and Saccomano, Mark and Kepper, Johannes and Page, Kevin}}, booktitle = {{Proceedings of the Music Encoding Conference 2022}}, editor = {{Weigl, David and Bain, Jennifer and Ang, Ailynn}}, keywords = {{BitH, Linked Data}}, pages = {{145–150}}, title = {{{A New Conceptual Model for Musical Sources and Musicological Studies}}}, doi = {{https://doi.org/10.17613/8p2c-1q77}}, year = {{2023}}, } @inproceedings{55832, abstract = {{Digital musicology research often proceeds by extending and enriching its evidence base as it progresses, rather than starting with a complete corpus of data and metadata, as a consequence of an emergent research need. In this paper, we consider a research workflow which assumes an incremental approach to data gathering and annotation. We describe tooling which implements parts of this workflow, developed to support the study of nineteenth-century music arrangements, and evaluate the applicability of our approach through interviews with musicologists and music editors who have used the tools. We conclude by considering extensions of this approach and the wider implications for digital musicology and music information retrieval.}}, author = {{Lewis, David and Shibata, Elisabete and Hankinson, Andrew and Kepper, Johannes and Page, Kevin R. and Rosendahl, Lisa and Saccomano, Mark and Siegert, Christine}}, keywords = {{BitH, Linked Data}}, title = {{{Supporting Musicological Investigations With Information Retrieval Tools: An Iterative Approach to Data Collection}}}, doi = {{10.5281/ZENODO.10265407}}, year = {{2023}}, } @inproceedings{37497, abstract = {{Since historical times, cartographic maps have revealed spatial relations and enabled decisions and processes. Geographic Information Systems (GIS) allow for acquisition, management, analysis, and presentation of geospatial objects. With free geospatial data becoming available through open data policies and an increasing amount of digitally connected objects in the Internet of Things (IoT), GIS are becoming indispensable to Information Systems (IS) research. However, the consideration and relevance of GIS has only been investigated rarely. We examine, how and in which fields of application GIS have been studied in the IS literature and elicit the importance of GIS regarding their design and usage. A systematic literature review leads us to develop four research propositions. Our results indicate that GIS are still an undeservedly underrepresented discipline in IS and should be more theorized, put center-stage in design-oriented research, and considered for creating superior value co-creation in service systems.}}, author = {{Priefer, Jennifer}}, booktitle = {{Proceedings of the 56th Hawaii International Conference on System Sciences}}, editor = {{Bui, T.X. and Sprague, R.H.}}, keywords = {{GIS, Industry 4.0, and Sustainability, geographic information systems, geospatial data, gis, information systems research, literature review}}, title = {{{Geographic Information Systems in Information Systems Research - Review and Research Prospects}}}, year = {{2023}}, } @inproceedings{45793, abstract = {{The global megatrends of digitization and sustainability lead to new challenges for the design and management of technical products in industrial companies. Product management - as the bridge between market and company - has the task to absorb and combine the manifold requirements and make the right product-related decisions. In the process, product management is confronted with heterogeneous information, rapidly changing portfolio components, as well as increasing product, and organizational complexity. Combining and utilizing data from different sources, e.g., product usage data and social media data leads to promising potentials to improve the quality of product-related decisions. In this paper, we reinforce the need for data-driven product management as an interdisciplinary field of action. The state of data-driven product management in practice was analyzed by conducting workshops with six manufacturing companies and hosting a focus group meeting with experts from different industries. We investigate the expectations and derive requirements leading us to open research questions, a vision for data-driven product management, and a research agenda to shape future research efforts.}}, author = {{Grigoryan, Khoren and Fichtler, Timm and Schreiner, Nick and Rabe, Martin and Panzner, Melina and Kühn, Arno and Dumitrescu, Roman and Koldewey, Christian}}, booktitle = {{Procedia CIRP 33}}, keywords = {{Product Management, Data Analytics, Data-Driven Design, Product-related data, Lifecycle Data, Tool-support}}, location = {{Sydney}}, title = {{{Data-Driven Product Management: A Practitioner-Driven Research Agenda}}}, year = {{2023}}, } @inproceedings{44146, abstract = {{Many Android applications collect data from users. When they do, they must protect this collected data according to the current legal frameworks. Such data protection has become even more important since the European Union rolled out the General Data Protection Regulation (GDPR). App developers have limited tool support to reason about data protection throughout their app development process. Although many Android applications state a privacy policy, privacy policy compliance checks are currently manual, expensive, and prone to error. One of the major challenges in privacy audits is the significant gap between legal privacy statements (in English text) and technical measures that Android apps use to protect their user's privacy. In this thesis, we will explore to what extent we can use static analysis to answer important questions regarding data protection. Our main goal is to design a tool based approach that aids app developers and auditors in ensuring data protection in Android applications, based on automated static program analysis.}}, author = {{Khedkar, Mugdha}}, booktitle = {{2023 IEEE/ACM 45th International Conference on Software Engineering: Companion Proceedings (ICSE-Companion), Melbourne, Australia, 2023, pp. 197-199}}, keywords = {{static analysis, data protection and privacy, GDPR compliance}}, title = {{{Static Analysis for Android GDPR Compliance Assurance}}}, doi = {{10.1109/ICSE-Companion58688.2023.00054}}, year = {{2023}}, } @inproceedings{34171, abstract = {{State estimation when only a partial model of a considered system is available remains a major challenge in many engineering fields. This work proposes a joint, square-root unscented Kalman filter to estimate states and model uncertainties simultaneously by linear combinations of physics-motivated library functions. Using a sparsity promoting approach, a selection of those linear combinations is chosen and thus an interpretable model can be extracted. Results indicate a small estimation error compared to a traditional square-root unscented Kalman filter and exhibit the enhancement of physically meaningful models.}}, author = {{Götte, Ricarda-Samantha and Timmermann, Julia}}, booktitle = {{12th IFAC Symposium on Nonlinear Control Systems (NOLCOS 2022)}}, keywords = {{joint estimation, unscented transform, Kalman filter, sparsity, data-driven, compressed sensing}}, location = {{Canberra, Australien}}, number = {{1}}, pages = {{85--90}}, title = {{{Estimating States and Model Uncertainties Jointly by a Sparsity Promoting UKF}}}, doi = {{https://doi.org/10.1016/j.ifacol.2023.02.015}}, volume = {{56}}, year = {{2023}}, } @inproceedings{48012, abstract = {{3D printing is a well-established technology with rapidly increasing usage scenarios both in the industry and consumer context. The growing popularity of 3D printing has also attracted security researchers, who have analyzed possibilities for weakening 3D models or stealing intellectual property from 3D models. We extend these important aspects and provide the first comprehensive security analysis of 3D printing data formats. We performed our systematic study on the example of the 3D Manufacturing Format (3MF), which offers a large variety of features that could lead to critical attacks. Based on 3MF’s features, we systematized three attack goals: Data Exfiltration (dex), Denial of Service, and UI Spoofing (uis). We achieve these goals by exploiting the complexity of 3MF, which is based on the Open Packaging Conventions (OPC) format and uses XML to define 3D models. In total, our analysis led to 352 tests. To create and run these tests automatically, we implemented an open-source tool named 3MF Analyzer (tool), which helped us evaluate 20 applications.}}, author = {{Rossel, Jost and Mladenov, Vladislav and Somorovsky, Juraj}}, booktitle = {{Proceedings of the 26th International Symposium on Research in Attacks, Intrusions and Defenses}}, keywords = {{Data Format Security, 3D Manufacturing Format, 3D Printing, Additive Manufacturing}}, location = {{Hongkong}}, publisher = {{ACM}}, title = {{{Security Analysis of the 3MF Data Format}}}, doi = {{10.1145/3607199.3607216}}, year = {{2023}}, } @article{48878, abstract = {{Due to the rise of continuous data-generating applications, analyzing data streams has gained increasing attention over the past decades. A core research area in stream data is stream classification, which categorizes or detects data points within an evolving stream of observations. Areas of stream classification are diverse\textemdash ranging, e.g., from monitoring sensor data to analyzing a wide range of (social) media applications. Research in stream classification is related to developing methods that adapt to the changing and potentially volatile data stream. It focuses on individual aspects of the stream classification pipeline, e.g., designing suitable algorithm architectures, an efficient train and test procedure, or detecting so-called concept drifts. As a result of the many different research questions and strands, the field is challenging to grasp, especially for beginners. This survey explores, summarizes, and categorizes work within the domain of stream classification and identifies core research threads over the past few years. It is structured based on the stream classification process to facilitate coordination within this complex topic, including common application scenarios and benchmarking data sets. Thus, both newcomers to the field and experts who want to widen their scope can gain (additional) insight into this research area and find starting points and pointers to more in-depth literature on specific issues and research directions in the field.}}, author = {{Clever, Lena and Pohl, Janina Susanne and Bossek, Jakob and Kerschke, Pascal and Trautmann, Heike}}, issn = {{2076-3417}}, journal = {{Applied Sciences}}, keywords = {{big data, data mining, data stream analysis, machine learning, stream classification, supervised learning}}, number = {{18}}, pages = {{9094}}, publisher = {{{Multidisciplinary Digital Publishing Institute}}}, title = {{{Process-Oriented Stream Classification Pipeline: A Literature Review}}}, doi = {{10.3390/app12189094}}, volume = {{12}}, year = {{2022}}, } @article{35728, abstract = {{Technological developments such as Cloud Computing, the Internet of Things, Big Data and Artificial Intelligence continue to drive the digital transformation of business and society. With the advent of platform-based ecosystems and their potential to address complex challenges, there is a trend towards greater interconnectedness between different stakeholders to co-create services based on the provision and use of data. While previous research on digital transformation mainly focused on digital transformation within organizations, it is of growing importance to understand the implications for digital transformation on different layers (e.g., interorganizational cooperation and platform ecosystems). In particular, the conceptualization and implications of public data spaces and related ecosystems provide promising research opportunities. This special issue contains five papers on the topic of digital transformation and, with the editorial, further contributes by providing an initial conceptualization of public data spaces' potential to foster innovative progress and digital transformation from a management perspective.}}, author = {{Beverungen, Daniel and Hess, Thomas and Köster, Antonia and Lehrer, Christiane}}, issn = {{1019-6781}}, journal = {{Electronic Markets}}, keywords = {{Digital transformation, Public data spaces, Digital platforms, GAIA-X}}, pages = {{493--501}}, publisher = {{Springer Science and Business Media LLC}}, title = {{{From private digital platforms to public data spaces: implications for the digital transformation}}}, doi = {{10.1007/s12525-022-00553-z}}, volume = {{32}}, year = {{2022}}, } @article{35732, abstract = {{While the Information Systems (IS) discipline has researched digital platforms extensively, the body of knowledge appertaining to platforms still appears fragmented and lacking conceptual consistency. Based on automated text mining and unsupervised machine learning, we collect, analyze, and interpret the IS discipline’s comprehensive research on platforms—comprising 11,049 papers spanning 44 years of research activity. From a cluster analysis concerning platform concepts’ semantically most similar words, we identify six research streams on platforms, each with their own platform terms. Based on interpreting the identified concepts vis-à-vis the extant research and considering a temporal perspective on the concepts’ application, we present a lexicon of platform concepts, to guide further research on platforms in the IS discipline. Researchers and managers can build on our results to position their work appropriately, applying a specific theoretical perspective on platforms in isolation or combining multiple perspectives to study platform phenomena at a more abstract level.}}, author = {{Bartelheimer, Christian and zur Heiden, Philipp and Lüttenberg, Hedda and Beverungen, Daniel}}, issn = {{1019-6781}}, journal = {{Electronic Markets}}, keywords = {{Platform, Text mining, Machine learning, Data communications, Interpretive research, Systems design and implementation}}, pages = {{375--396}}, publisher = {{Springer Science and Business Media LLC}}, title = {{{Systematizing the lexicon of platforms in information systems: a data-driven study}}}, doi = {{10.1007/s12525-022-00530-6}}, volume = {{32}}, year = {{2022}}, } @inproceedings{26539, abstract = {{In control design most control strategies are model-based and require accurate models to be applied successfully. Due to simplifications and the model-reality-gap physics-derived models frequently exhibit deviations from real-world-systems. Likewise, purely data-driven methods often do not generalise well enough and may violate physical laws. Recently Physics-Guided Neural Networks (PGNN) and physics-inspired loss functions separately have shown promising results to conquer these drawbacks. In this contribution we extend existing methods towards the identification of non-autonomous systems and propose a combined approach PGNN-L, which uses a PGNN and a physics-inspired loss term (-L) to successfully identify the system's dynamics, while maintaining the consistency with physical laws. The proposed method is demonstrated on two real-world nonlinear systems and outperforms existing techniques regarding complexity and reliability.}}, author = {{Götte, Ricarda-Samantha and Timmermann, Julia}}, booktitle = {{2022 3rd International Conference on Artificial Intelligence, Robotics and Control (AIRC)}}, keywords = {{data-driven, physics-based, physics-informed, neural networks, system identification, hybrid modelling}}, location = {{Cairo, Egypt}}, pages = {{67--76}}, title = {{{Composed Physics- and Data-driven System Identification for Non-autonomous Systems in Control Engineering}}}, doi = {{10.1109/AIRC56195.2022.9836982}}, year = {{2022}}, } @inproceedings{31066, abstract = {{While trade-offs between modeling effort and model accuracy remain a major concern with system identification, resorting to data-driven methods often leads to a complete disregard for physical plausibility. To address this issue, we propose a physics-guided hybrid approach for modeling non-autonomous systems under control. Starting from a traditional physics-based model, this is extended by a recurrent neural network and trained using a sophisticated multi-objective strategy yielding physically plausible models. While purely data-driven methods fail to produce satisfying results, experiments conducted on real data reveal substantial accuracy improvements by our approach compared to a physics-based model. }}, author = {{Schön, Oliver and Götte, Ricarda-Samantha and Timmermann, Julia}}, booktitle = {{14th IFAC Workshop on Adaptive and Learning Control Systems (ALCOS 2022)}}, keywords = {{neural networks, physics-guided, data-driven, multi-objective optimization, system identification, machine learning, dynamical systems}}, location = {{Casablanca, Morocco}}, number = {{12}}, pages = {{19--24}}, title = {{{Multi-Objective Physics-Guided Recurrent Neural Networks for Identifying Non-Autonomous Dynamical Systems}}}, doi = {{https://doi.org/10.1016/j.ifacol.2022.07.282}}, volume = {{55}}, year = {{2022}}, } @inproceedings{22480, abstract = {{In this publication important aspects for the implementation of inductive locating are explained. The miniaturized sensor platform called Sens-o-Spheres is used as an application of this locating method. The sensor platform is applied in bioreactors in order to obtain the environmental parameters, which makes a localization by magnetic fields necessary. Since the properties of magnetic fields in the localization area are very different from the wave characteristics, the principle of inductive localization is investigated in this publication and explained by using electrical equivalent circuit diagrams. Thereby, inductive localization uses the coupling or the mutual inductivities between coils, which is noticeable by an induced voltage. Therefore some properties and procedures are explained to extract the location of Sens-o-Spheres or other industrial sensor platforms from the couplings of the coils. One method calculates the location from an adapted ratio calculation and the other method uses neural networks and stochastic filters to obtain the results. In the end, these results are evaluated and compared.}}, author = {{Lange, Sven and Schröder, Dominik and Hedayat, Christian and Kuhn, Harald and Hilleringmann, Ulrich}}, booktitle = {{22nd IEEE International Conference on Industrial Technology (ICIT)}}, isbn = {{9781728157306}}, keywords = {{Location awareness, Coils, Couplings, Nonuniform electric fields, Magnetic separation, Neural networks, Training data}}, location = {{Valencia, Spain }}, publisher = {{IEEE}}, title = {{{Development of Methods for Coil-Based Localization by Magnetic Fields of Miniaturized Sensor Platforms in Bioprocesses}}}, doi = {{10.1109/icit46573.2021.9453609}}, year = {{2021}}, } @inproceedings{27381, abstract = {{Graph neural networks (GNNs) have been successfully applied in many structured data domains, with applications ranging from molecular property prediction to the analysis of social networks. Motivated by the broad applicability of GNNs, we propose the family of so-called RankGNNs, a combination of neural Learning to Rank (LtR) methods and GNNs. RankGNNs are trained with a set of pair-wise preferences between graphs, suggesting that one of them is preferred over the other. One practical application of this problem is drug screening, where an expert wants to find the most promising molecules in a large collection of drug candidates. We empirically demonstrate that our proposed pair-wise RankGNN approach either significantly outperforms or at least matches the ranking performance of the naive point-wise baseline approach, in which the LtR problem is solved via GNN-based graph regression.}}, author = {{Damke, Clemens and Hüllermeier, Eyke}}, booktitle = {{Proceedings of The 24th International Conference on Discovery Science (DS 2021)}}, editor = {{Soares, Carlos and Torgo, Luis}}, isbn = {{9783030889418}}, issn = {{0302-9743}}, keywords = {{Graph-structured data, Graph neural networks, Preference learning, Learning to rank}}, location = {{Halifax, Canada}}, pages = {{166--180}}, publisher = {{Springer}}, title = {{{Ranking Structured Objects with Graph Neural Networks}}}, doi = {{10.1007/978-3-030-88942-5}}, volume = {{12986}}, year = {{2021}}, } @inproceedings{24551, abstract = {{Access to precise meteorological data is crucial to be able to plan and install renewable energy systems such as solar power plants and wind farms. In case of solar energy, knowledge of local irradiance and air temperature values is very important. For this, various methods can be used such as installing local weather stations or using meteorological data from different organizations such as Meteonorm or official Deutscher Wetterdienst (DWD). An alternative is to use satellite reanalysis datasets provided by organizations like the National Aeronautics and Space Administration (NASA) and European Centre for Medium-Range Weather Forecasts (ECMWF). In this paper the “Modern-Era Retrospective analysis for Research and Applications” dataset version 2 (MERRA-2) will be presented, and its performance will be evaluated by comparing it to locally measured datasets provided by Meteonorm and DWD. The analysis shows very high correlation between MERRA-2 and local measurements (correlation coefficients of 0.99) for monthly global irradiance and air temperature values. The results prove the suitability of MERRA-2 data for applications requiring long historical data. Moreover, availability of MERRA-2 for the whole world with an acceptable resolution makes it a very valuable dataset.}}, author = {{Khatibi, Arash and Krauter, Stefan}}, booktitle = {{Proceedings of the 38th European Photovoltaic Solar Energy Conference and Exhibition (EUPVSEC 2021)}}, isbn = {{3-936338-78-7}}, keywords = {{Energy potential estimation, Photovoltaic, Solar radiation, Temperature measurement, Satellite data, Meteonorm, MERRA-2, DWD}}, pages = {{1141 -- 1147}}, title = {{{Comparison and Validation of Irradiance Data: Satellite Meteorological Dataset MERRA-2 vs. Meteonorm and German Weather Service (DWD)}}}, doi = {{10.4229/EUPVSEC20212021-5BV.4.11}}, year = {{2021}}, } @inproceedings{24547, abstract = {{Over the last years, several approaches for the data-driven estimation of expected possession value (EPV) in basketball and association football (soccer) have been proposed. In this paper, we develop and evaluate PIVOT: the first such framework for team handball. Accounting for the fast-paced, dynamic nature and relative data scarcity of hand- ball, we propose a parsimonious end-to-end deep learning architecture that relies solely on tracking data. This efficient approach is capable of predicting the probability that a team will score within the near future given the fine-grained spatio-temporal distribution of all players and the ball over the last seconds of the game. Our experiments indicate that PIVOT is able to produce accurate and calibrated probability estimates, even when trained on a relatively small dataset. We also showcase two interactive applications of PIVOT for valuing actual and counterfactual player decisions and actions in real-time.}}, author = {{Müller, Oliver and Caron, Matthew and Döring, Michael and Heuwinkel, Tim and Baumeister, Jochen}}, booktitle = {{8th Workshop on Machine Learning and Data Mining for Sports Analytics (ECML PKDD 2021)}}, keywords = {{expected possession value, handball, tracking data, time series classification, deep learning}}, location = {{Online}}, title = {{{PIVOT: A Parsimonious End-to-End Learning Framework for Valuing Player Actions in Handball using Tracking Data}}}, year = {{2021}}, } @inproceedings{27491, abstract = {{ Students often have a lack of understanding and awareness of where, how, and why personal data about them is collected and processed. Especially, when interacting with data-driven digital artifacts, an appropriate perception of the data collection and processing is necessary for self-determination. This dissertation deals with the development and evaluation of a concept called data awareness which aims to foster students’ self-determination interacting with data-driven digital artifacts.}}, author = {{Höper, Lukas}}, booktitle = {{21st Koli Calling International Conference on Computing Education Research}}, isbn = {{9781450384889}}, keywords = {{data awareness, machine learning, data science education, data-driven digital artifacts, artificial intelligence}}, publisher = {{Association for Computing Machinery}}, title = {{{Developing and Evaluating the Concept Data Awareness for K12 Computing Education}}}, doi = {{10.1145/3488042.3490509}}, year = {{2021}}, } @inproceedings{24540, abstract = {{With its growing population and industrialization, DREs, and solar technologies in particular, provide a sustainable means of bridging the current energy deficit in Africa, increasing supply reliability and meeting future demand. Data acquisition and data management systems allow real time monitoring and control of energy systems as well as performance analysis. However commercial data acquisition systems often have cost implications that are prohibitive for small PV systems and installations in developing countries. In this paper, a multi-user, multi-purpose microgrid database system is designed and implemented. MAVOWATT 270 power quality analyzers by GOSSEN METRAWATT, raspberry pi modules and sensors are used for measuring, recording and storing electrical and meteorological data in East Africa. Socio-economic data is also stored in the database. The designed system employs open source software and hardware solutions which are best suited to developing regions like East Africa due to the lower cost implications. The expected results promise a comprehensive database covering different electro-technical and socio-economic parameters useful for optimal design of microgrid systems.}}, author = {{Kakande, Josephine Nakato and Philipo, Godiana Hagile and Krauter, Stefan}}, booktitle = {{Proceedings of the 38th European Photovoltaic Solar Energy Conference and Exhibition (EUPVSEC 2021)}}, isbn = {{3-936338-78-7}}, keywords = {{Art-D, Afrika, Demand side management, MySQL, Raspberry pi, Data acquisition}}, pages = {{1505--1510}}, title = {{{Load Data Acquisition in Rural East Africa for the Layout of Microgrids and Demand–Side–Management Measures}}}, doi = {{10.4229/EUPVSEC20212021-6BV.5.38}}, year = {{2021}}, }