@article{64678, abstract = {{One of the major topics in the modern automotive industry is reducing emissions and increasing the mileage range. To tackle this challenge, on the one hand, modifying the powertrain system is a possibility, and on the other hand, lightweight design offers various possibilities. Multi-Material Design (MMD) involves designing car bodies that combine different materials that require joining. Given the variety of materials, mechanical joining processes are preferred. Especially the current development of the Giga/Mega-casting process concerning aluminium casting and the subsequent mechanical joining illustrates the challenges of this material group. In car production, aluminium castings are mainly made from aluminium-silicon (AlSi) alloys. Ultimately, the alloy system's insufficient ductility leads to crack initiation during mechanical joining. Cast parts are therefore often used in areas of the car body that are exposed to high-pressure loads. For example, self-piercing riveting (SPR) is used due to its high load-bearing capacity. In this study, improved joinability is demonstrated by influencing the microstructure through tailored solidification rates and a developed heat-treatment chain strategy adapted for hypoeutectic AlSi systems. Data on microstructure, mechanical, and joining properties are used to develop a solidification-joining correlation for the SPR process across a range of Si contents and solidification rates. The purpose is to develop the ability to produce suitable aluminium castings with sufficient joinability, thereby improving versatility.}}, author = {{Neuser, Moritz and Kaimann, Pia Katharina and Stratmann, Ina and Bobbert, Mathias and Klöckner, Johann Moritz Benedikt and Mann, Moritz and Hoyer, Kay-Peter and Meschut, Gerson and Schaper, Mirko}}, journal = {{Journal of Manufacturing Processes}}, keywords = {{Mechanical joining, Aluminium, Self-piercing riveting, Casting, Microstructure, Joinability AlSi-alloys}}, publisher = {{Elsevier}}, title = {{{Solidification-joinability correlation of hypoeutectic aluminium casting alloys for self-piercing riveting (SPR)}}}, doi = {{https://doi.org/10.1016/j.jmapro.2026.02.040}}, volume = {{164}}, year = {{2026}}, } @article{64985, abstract = {{Modern industrial development has necessitated a wide range of joining technologies. Self-pierce riveting has become a prevalent technique for sheet metal assembly, especially in automotive applications. Achieving proper joint geometry and adequate load-bearing capacity depends on appropriate tool selection and precise process control. Material properties and condition also play a significant role in process performance. To accommodate the inevitable variations in component characteristics during production, a robust and stable joining process is essential. The study focuses on investigating the influence of preformed joining partners on the joining process and the joint's load capacity. An EN AW-6014 in T4 condition, as well as an HCT590X, are used as materials for this study. For this purpose, an exemplary process chain consisting of the steps of performing, joining, and shear load testing is studied. Each process step is implemented using an FE model to predict the outcome of subsequent steps. For analysis of the influence of pre-strain, an optimisation software is used to plan and execute variations of the process. These variations are used to create a meta-model that can describe the relationships between pre-forming and characteristic parameters of subsequent process steps. The resulting model is validated by comparing simulation and experimental data. Finally, in a novel approach, the robustness of the presented process chain is analyzed in terms of a tolerable performance level for the joining partners.}}, author = {{Ludwig, Jean-Patrick and Tolke, Emil and Schlichter, Malte Christian and Bobbert, Mathias and Meschut, Gerson}}, issn = {{2666-3309}}, journal = {{Journal of Advanced Joining Processes}}, keywords = {{Self-pierce riveting, FE modelling, Plastic pre-deformation, Meta modelling}}, publisher = {{Elsevier BV}}, title = {{{Numerical analysis of the robustness of self-pierce riveting with pre-formed joining partners}}}, doi = {{10.1016/j.jajp.2026.100391}}, volume = {{13}}, year = {{2026}}, } @inproceedings{59483, abstract = {{Abstract. The assessment of mechanically joined connections, such as clinched connections, is usually conducted destructively. Applicable non-destructive testing methods like computed tomography are time-consuming and costly, or, like electrical resistance measurement, provide only a limited amount of information. A fast, non-destructive evaluation of the joints condition shall be made possible by using transient dynamic analysis (TDA). It is based on the introduction of sound waves and the evaluation of the response behavior after passing through the structure. This study focuses the application of TDA to clinched shear connections to evaluate the performance of the tactile measuring setup. Twenty-one series were investigated, covering variations in joining task, manufacturing and defect. The evaluation was carried out using machine learning to determine for which series characteristic signals may be detected. It was shown that a classification of the investigated specimens is possible, whereby the classification accuracy depends on the examined variation. Furthermore, the accuracy was evaluated as a function of frequency and results were concluded to identify the limits of the used measuring setup.}}, author = {{Reschke, Gregor and Brosius, Alexander}}, booktitle = {{Materials Research Proceedings}}, issn = {{2474-395X}}, keywords = {{Joining, Machine Learning, Transient Dynamic Analysis}}, location = {{Paderborn}}, pages = {{293--300}}, publisher = {{Materials Research Forum LLC}}, title = {{{Transient dynamic analysis: Performance evaluation of tactile measurement}}}, doi = {{10.21741/9781644903551-36}}, volume = {{52}}, year = {{2025}}, } @article{59708, abstract = {{Die Arbeitszufriedenheit von Lehrkräften gilt als zentrale Komponente für die Qualität des Bil­dungssystems. In inklusiven Schulen müssen Regelschullehrkräfte und sonderpädagogische Lehrkräfte kooperieren, um allen Schüler:innen eine bestmögliche Förderung zu gewährleisten. Dazu benötigen sie jedoch Zeitfenster, die von vielen Lehrkräften als nicht ausreichend benannt werden. Ziel des vorliegenden Beitrags ist es, empirisch zu untersuchen, welche Bedeutung festen Zeitfenstern für die Lehrkräftekooperation im Klassenteam, im Jahrgangsteam und im Fachteam für die Arbeitszufriedenheit zukommt. Weiterhin soll überprüft werden, ob Teile der Zusammenhänge über die Zufriedenheit mit der Kooperationshäufigkeit und die kollektive Selbstwirksamkeitsüberzeugung der Lehrkräfte erklärt werden können. Dazu werden Daten aus dem BMBF-geförderten Projekt BiFoKi mit N=194 Lehrkräften und N=28 Schulleitungen analy­siert. Die Ergebnisse zeigen, dass feste Zeitfenster für die Kooperation in den unterschiedlichen Teams mit einer erhöhten Arbeitszufriedenheit im Zusammenhang stehen und in Teilen über die kollektive Selbstwirksamkeitsüberzeugung mediiert werden.}}, author = {{Wohnhas, Verena and Neumann, Phillip and Lütje-Klose, Birgit}}, issn = {{2699-2477}}, journal = {{QfI - Qualifizierung für Inklusion. Online-Zeitschrift zur Forschung über Aus-, Fort- und Weiterbildung pädagogischer Fachkräfte}}, keywords = {{Arbeitszufriedenheit, Inklusion, Sonderpädagogik, Kooperation, Selbstwirksamkeit, Schulentwicklung, job satisfaction, Inclusion, Special Education, Self-efficacy, school development}}, number = {{2}}, publisher = {{University Library J. C. Senckenberg}}, title = {{{Zeit für Arbeitszufriedenheit? Eine quantitativ-empirische Studie zur Bedeutung fester Kooperationszeiten für die Arbeitszufriedenheit von Lehrkräften in inklusiven Schulen}}}, doi = {{10.21248/qfi.167}}, volume = {{6}}, year = {{2025}}, } @article{59872, abstract = {{Lightweight design is a driving concept in modern automotive engineering to minimize resource consumption over a vehicle's lifecycle through multi-material design, which relies on the use of joining techniques in car body fabrication. Multi-material design and the increasing trend towards producing large structural components using the megacasting process pose considerable challenges, particularly in the mechanical joining of aluminium-silicon (AlSi) castings. These castings typically exhibit low ductility and are prone to cracking when mechanically joined. Based on the excellent castability of hypoeutectic AlSi alloys, these are applied in sand casting and die casting as well as in megacasting. With a silicon content between 7 wt% and 12 wt%, these AlSi-alloys have a plate-like silicon phase that initiates cracks during mechanical joining. To enhance the joinability of castings, the research hypothesis is that improved solidification conditions enable a significant modification in the microstructure and therefore, increase the mechanical properties. During the manufacture of the castings using the sand casting process, the solidification conditions within the structural elements are varied to modify the microstructure to obtain castings with graded microstructure. The castings are evaluated using mechanical, microstructural and joining testing methods and finally, a microstructure-joinability correlation is established.}}, author = {{Neuser, Moritz and Schlichter, Malte Christian and Hoyer, Kay-Peter and Bobbert, Mathias and Meschut, Gerson and Schaper, Mirko}}, journal = {{44th Conference of the International Deep Drawing Research Group (IDDRG 2025)}}, keywords = {{Joining, Casting, Self-pierce riveting, Aluminium casting alloy}}, location = {{Lissabon (Portugal)}}, title = {{{Mechanical joinability of microstructurally graded structural components manufactured from hypoeutectic aluminium casting alloys}}}, doi = {{10.1051/matecconf/202540801081}}, volume = {{408}}, year = {{2025}}, } @inproceedings{62080, abstract = {{The failure behavior of fiber reinforced polymers (FRP) is strongly influenced by their microstructure, i.e. fiber arrangement or local fiber volume content. However, this information cannot be directly used for structural analyses, since it requires a discretization on micrometer level. Therefore, current failure theories do not directly account for such effects, but describe the behavior averaged over an entire specimen. This foundation in experimentally accessible loading conditions leads to purely theory based extension to more complex stress states without direct validation possibilities. This work aims at leveraging micro-scale simulations to obtain failure information under arbitrary loading conditions. The results are propagated to the meso-scale, enabling efficient structural analyses, by means of machine learning (ML). It is shown that the ML model is capable of correctly assessing previously unseen stress states and therefore poses an efficient tool of exploiting information from the micro-scale in larger simulations.}}, author = {{Gerritzen, Johannes and Hornig, Andreas and Gude, Maik}}, booktitle = {{Sheet Metal 2025}}, editor = {{Meschut, G. and Bobbert, M. and Duflou, J. and Fratini, L. and Hagenah, H. and Martins, P. and Merklein, M. and Micari, F.}}, isbn = {{978-1-64490-354-4}}, keywords = {{Failure, Fiber Reinforced Plastic, Machine Learning}}, pages = {{260–267}}, publisher = {{Materials Research Forum LLC, Materials Research Foundations}}, title = {{{Efficient failure information propagation under complex stress states in fiber reinforced polymers: From micro- to meso-scale using machine learning}}}, doi = {{10.21741/9781644903551-32}}, year = {{2025}}, } @inproceedings{61149, abstract = {{The use of continuous fiber-reinforced thermoplastics (FRTP) in automotive industry increases due to their excellent material properties and possibility of rapid processing. The scale spanning heterogeneity of their material structure and its influence on the material behavior, however, presents significant challenges for most joining technologies, such as self-piercing riveting (SPR). During mechanical joining, the material structure is significantly altered within and around the joining zone, heavily influencing the material behavior. A comprehensive understanding of the underlying phenomena of material alteration during the SPR process is essential as basis for validating numerical simulations. This study examines the material structure at ten stages of a step-setting test of SPR with two FRTP sheets with glass-fiber reinforcement. Utilizing X-ray computed tomography (CT), the damage phenomena within different areas of the setting test are analyzed three-dimensionally and key parameters are quantified. Dominating phenomena during the penetration of the rivet into the laminate are fiber failure (FF), interfiber failure (IFF) and fiber bending, while delamination, fiber kinking and roving splitting are also observed. At the final stages, the bottom layers of the second sheet collapse and form a bulge into the cavity of the die.}}, author = {{Dargel, Alrik and Gröger, Benjamin and Schlichter, Malte Christian and Gerritzen, Johannes and Köhler, Daniel and Meschut, Gerson and Gude, Maik and Kupfer, Robert}}, booktitle = {{Proceedings of the 8th International Conference on Integrity-Reliability-Failure (IRF2025)}}, editor = {{Gomes, J.F. Silva and Meguid, Shaker A.}}, isbn = {{9789727523238}}, keywords = {{self-piercing riveting, computed tomography, thermoplastic composites, process-structure-interaction}}, location = {{Porto}}, publisher = {{FEUP}}, title = {{{LOCAL DEFORMATION AND FAILURE OF COMPOSITES DURING SELF-PIERCING RIVETING: A CT BASED MICROSTRUCTURE INVESTIGATION}}}, doi = {{10.24840/978-972-752-323-8}}, year = {{2025}}, } @article{58807, abstract = {{One of the most important strategies for reducing CO2 emissions in the mobility sector is lightweight construction. In particular, the car body offers several opportunities for weight reduction. Multi-material designs are increasingly being applied to select the most suitable material for the respective load and ultimately achieve synergy effects. For example, aluminium castings are used at the nodes of a spaceframe body. Subsequently, these are joined with profiles to form the bodyshell. To join different materials mechanical joining techniques, such as semi-tubular self-piercing riveting, are deployed. According to the current state of the art, cracks occur in the aluminium castings during the mechanical joining process as a result of the high degree of deformation. Although the aluminium casting alloys of the AlSi-system exhibit low ductility, these alloys reveal excellent castability. In particular, the ability to cast thin structural parts is enabled by the low liquidus point of the near eutectic aluminium casting alloys. This study addresses the mechanical joining properties of the near eutectic aluminium casting alloy AlSi12, depending on different microstructures. These are achieved by annealing processes and modifying agents. Through an adapted heat treatment, the previously lamellar morphology can be transformed into a globular morphology, which leads to increased ductility and prevents the formation of cracks during the self-piercing riveting (SPR). The joinability is investigated using different die geometries, whereas the joint formation is analysed regarding crack initiation. To evaluate the increased ductility, microstructural and mechanical tests are performed and finally, a microstructure-joinability correlation is established.}}, author = {{Neuser, Moritz and Holtkamp, Pia Katharina and Hoyer, Kay-Peter and Kappe, Fabian and Yildiz, Safak and Bobbert, Mathias and Meschut, Gerson and Schaper, Mirko}}, journal = {{The Journal of Materials: Design and Applications, Part L}}, keywords = {{aluminium, casting, microstructure, joinability, self-piercing riveting}}, location = {{Porto, Portugal}}, publisher = {{Sage Publications}}, title = {{{Mechanical properties and joinability of the near-eutectic aluminium casting alloy AlSi12}}}, doi = {{10.1177/14644207251319922}}, year = {{2025}}, } @article{58885, abstract = {{There have been several attempts to conceptualize and operationalize pedagogical content knowledge (PCK) in the context of teachers' professional competencies. A recent and popular model is the Refined Consensus Model (RCM), which proposes a framework of dispositional competencies (personal PCK—pPCK) that influence more action-related competencies (enacted PCK—ePCK) and vice versa. However, descriptions of the internal structure of pPCK and possible knowledge domains that might develop independently are still limited, being either primarily theoretically motivated or strictly hierarchical and therefore of limited use, for example, for formative feedback and further development of the RCM. Meanwhile, a non-hierarchical differentiation for the ePCK regarding the plan-teach-reflect cycle has emerged. In this study, we present an exploratory computational approach to investigate pre-service teachers' pPCK for a similar non-hierarchical structure using a large dataset of responses to a pPCK questionnaire (N=846). We drew on theoretical foundations and previous empirical findings to achieve interpretability by integrating this external knowledge into our analyses using the Computational Grounded Theory (CGT) framework. The results of a cluster analysis of the pPCK scores indicate the emergence of prototypical groups, which we refer to as competency profiles: (1) a group with low performance, (2) a group with relatively advanced competency in using pPCK to create instructional elements, (3) a group with relatively advanced competency in using pPCK to assess and analyze described instructional elements, and (4) a group with high performance. These groups show tendencies for certain language usage, which we analyze using a structural topic model in a CGT-inspired pattern refinement step. We verify these patterns by demonstrating the ability of a machine learning model to predict the competency profile assignments. Finally, we discuss some implications of the results for the further development of the RCM and their potential usability for an automated formative assessment.}}, author = {{Zeller, Jannis and Riese, Josef}}, issn = {{1098-2736}}, journal = {{Journal of Research in Science Teaching}}, keywords = {{computational grounded theory, language analysis, machine learning, pedagogical content knowledge, unsupervised learning}}, title = {{{Competency Profiles of PCK Using Unsupervised Learning: What Implications for the Structures of pPCK Emerge From Non-Hierarchical Analyses?}}}, doi = {{10.1002/tea.70001}}, year = {{2025}}, } @inproceedings{60290, abstract = {{The constantly increasing demand for climate protection and resource conservation requires innovative and versatile joining processes that improve adaptability to the joining task and robustness to enable flexible manufacturing on a production line. Therefore, the versatile SPR (V-SPR) and tumbling SPR (T-SPR) were developed. Using the example of a mixed material combination HCT590X+Z (t0 = 1.0 mm) / EN AW-6014 T4 (t0 = 2.0 mm), these processes were examined and compared with regard to the binding mechanisms form closure and force closure using micrographs, non-destructive resistance measurements and destructive torsion tests. For this purpose, a new sample geometry was defined, and the methods were adapted to the SPR process variants.}}, author = {{Lüder, Stephan and Holtkamp, Pia Katharina and Wituschek, Simon and Bobbert, Mathias and Meschut, Gerson and Lechner, Michael and Schmale, Hans Christian}}, booktitle = {{Materials Research Proceedings}}, editor = {{Meschut, Gerson and Bobbert, Mathias and Duflou, Joost and Fratini, Livan and Hagenah, Hinnerk and Martins, Paulo A. F. and Merklein, Marion and Micari, Fabrizio}}, issn = {{2474-395X}}, keywords = {{Joining, Self-Piercing Riveting, Sheet Metal}}, location = {{Paderborn}}, pages = {{101 -- 108}}, publisher = {{Materials Research Forum LLC}}, title = {{{Analysis of the binding mechanisms depending on versatile process variants of self-piercing riveting}}}, doi = {{10.21741/9781644903551-13}}, volume = {{52}}, year = {{2025}}, } @inproceedings{60680, abstract = {{Classical machine learning techniques often struggle with overfitting and unreliable predictions when exposed to novel conditions. Introducing causality into the modelling process offers a promising way to mitigate these challenges by enhancing predictive robustness. However, constructing an initial causal graph manually using domain knowledge is time-consuming, particularly in complex time series with numerous variables. To address this, causal discovery algorithms can provide a preliminary causal structure that domain experts can refine. This study investigates causal feature selection with domain knowledge using a data center system as an example. We use simulated time-series data to compare different causal feature selection with traditional machine-learning feature selection methods. Our results show that predictions based on causal features are more robust compared to those derived from traditional methods. These findings underscore the potential of combining causal discovery algorithms with human expertise to improve machine learning applications.}}, author = {{Zapata Gonzalez, David Ricardo and Meyer, Marcel and Müller, Oliver}}, keywords = {{Causal Machine Learning, Causality in Time Series, Causal Discovery, Human-Machine Collaboration}}, location = {{Amman, Jordan}}, title = {{{Bridging the gap between data-driven and theory-driven modelling – leveraging causal machine learning for integrative modelling of dynamical systems}}}, year = {{2025}}, } @article{55400, abstract = {{This study contributes to the evolving field of robot learning in interaction with humans, examining the impact of diverse input modalities on learning outcomes. It introduces the concept of "meta-modalities" which encapsulate additional forms of feedback beyond the traditional preference and scalar feedback mechanisms. Unlike prior research that focused on individual meta-modalities, this work evaluates their combined effect on learning outcomes. Through a study with human participants, we explore user preferences for these modalities and their impact on robot learning performance. Our findings reveal that while individual modalities are perceived differently, their combination significantly improves learning behavior and usability. This research not only provides valuable insights into the optimization of human-robot interactive task learning but also opens new avenues for enhancing the interactive freedom and scaffolding capabilities provided to users in such settings.}}, author = {{Beierling, Helen and Beierling, Robin and Vollmer, Anna-Lisa}}, journal = {{Frontiers in Robotics and AI}}, keywords = {{human-robot interaction, human-in-the-loop learning, reinforcement learning, interactive robot learning, multi-modal feedback, learning from demonstration, preference-based learning, scaffolding in robot learning}}, publisher = {{Frontiers }}, title = {{{The power of combined modalities in interactive robot learning}}}, volume = {{12}}, year = {{2025}}, } @article{61327, abstract = {{Robot learning from humans has been proposed and researched for several decades as a means to enable robots to learn new skills or adapt existing ones to new situations. Recent advances in artificial intelligence, including learning approaches like reinforcement learning and architectures like transformers and foundation models, combined with access to massive datasets, has created attractive opportunities to apply those data-hungry techniques to this problem. We argue that the focus on massive amounts of pre-collected data, and the resulting learning paradigm, where humans demonstrate and robots learn in isolation, is overshadowing a specialized area of work we term Human-Interactive-Robot-Learning (HIRL). This paradigm, wherein robots and humans interact during the learning process, is at the intersection of multiple fields (artificial intelligence, robotics, human-computer interaction, design and others) and holds unique promise. Using HIRL, robots can achieve greater sample efficiency (as humans can provide task knowledge through interaction), align with human preferences (as humans can guide the robot behavior towards their expectations), and explore more meaningfully and safely (as humans can utilize domain knowledge to guide learning and prevent catastrophic failures). This can result in robotic systems that can more quickly and easily adapt to new tasks in human environments. The objective of this paper is to provide a broad and consistent overview of HIRL research and to guide researchers toward understanding the scope of HIRL, and current open or underexplored challenges related to four themes — namely, human, robot learning, interaction, and broader context. The paper includes concrete use cases to illustrate the interaction between these challenges and inspire further research according to broad recommendations and a call for action for the growing HIRL community}}, author = {{Baraka, Kim and Idrees, Ifrah and Faulkner, Taylor Kessler and Biyik, Erdem and Booth, Serena and Chetouani, Mohamed and Grollman, Daniel H. and Saran, Akanksha and Senft, Emmanuel and Tulli, Silvia and Vollmer, Anna-Lisa and Andriella, Antonio and Beierling, Helen and Horter, Tiffany and Kober, Jens and Sheidlower, Isaac and Taylor, Matthew E. and van Waveren, Sanne and Xiao, Xuesu}}, journal = {{Transactions on Human-Robot Interaction}}, keywords = {{Robot learning, Interactive learning systems, Human-robot interaction, Human-in-the-loop machine learning, Teaching and learning}}, title = {{{Human-Interactive Robot Learning: Definition, Challenges, and Recommendations}}}, year = {{2025}}, } @inbook{62701, abstract = {{Learning continuous vector representations for knowledge graphs has significantly improved state-of-the-art performances in many challenging tasks. Yet, deep-learning-based models are only post-hoc and locally explainable. In contrast, learning Web Ontology Language (OWL) class expressions in Description Logics (DLs) is ante-hoc and globally explainable. However, state-of-the-art learners have two well-known lim-itations: scaling to large knowledge graphs and handling missing infor-mation. Here, we present a decision-tree-based learner (tDL) to learn Web Ontology Languages (OWLs) class expressions over large knowl-edge graphs, while imputing missing triples. Given positive and negative example individuals, tDL firstly constructs unique OWL expressions in .SHOIN from concise bounded descriptions of individuals. Each OWL class expression is used as a feature in a binary classification problem to represent input individuals. Thereafter, tDL fits a CART decision tree to learn Boolean decision rules distinguishing positive examples from nega-tive examples. A final OWL expression in.SHOIN is built by traversing the built CART decision tree from the root node to leaf nodes for each positive example. By this, tDL can learn OWL class expressions without exploration, i.e., the number of queries to a knowledge graph is bounded by the number of input individuals. Our empirical results show that tDL outperforms the current state-of-the-art models across datasets. Impor-tantly, our experiments over a large knowledge graph (DBpedia with 1.1 billion triples) show that tDL can effectively learn accurate OWL class expressions, while the state-of-the-art models fail to return any results. Finally, expressions learned by tDL can be seamlessly translated into natural language explanations using a pre-trained large language model and a DL verbalizer.}}, author = {{Demir, Caglar and Yekini, Moshood and Röder, Michael and Mahmood, Yasir and Ngonga Ngomo, Axel-Cyrille}}, booktitle = {{Lecture Notes in Computer Science}}, isbn = {{9783032060655}}, issn = {{0302-9743}}, keywords = {{Decision Tree, OWL Class Expression Learning, Description Logic, Knowledge Graph, Large Language Model, Verbalizer}}, location = {{Porto, Portugal}}, publisher = {{Springer Nature Switzerland}}, title = {{{Tree-Based OWL Class Expression Learner over Large Graphs}}}, doi = {{10.1007/978-3-032-06066-2_29}}, year = {{2025}}, } @inproceedings{62007, abstract = {{Ensemble methods are widely employed to improve generalization in machine learning. This has also prompted the adoption of ensemble learning for the knowledge graph embedding (KGE) models in performing link prediction. Typical approaches to this end train multiple models as part of the ensemble, and the diverse predictions are then averaged. However, this approach has some significant drawbacks. For instance, the computational overhead of training multiple models increases latency and memory overhead. In contrast, model merging approaches offer a promising alternative that does not require training multiple models. In this work, we introduce model merging, specifically weighted averaging, in KGE models. Herein, a running average of model parameters from a training epoch onward is maintained and used for predictions. To address this, we additionally propose an approach that selectively updates the running average of the ensemble model parameters only when the generalization performance improves on a validation dataset. We evaluate these two different weighted averaging approaches on link prediction tasks, comparing the state-of-the-art benchmark ensemble approach. Additionally, we evaluate the weighted averaging approach considering literal-augmented KGE models and multi-hop query answering tasks as well. The results demonstrate that the proposed weighted averaging approach consistently improves performance across diverse evaluation settings.}}, author = {{Sapkota, Rupesh and Demir, Caglar and Sharma, Arnab and Ngonga Ngomo, Axel-Cyrille}}, booktitle = {{Proceedings of the Thirteenth International Conference on Knowledge Capture(K-CAP 2025)}}, keywords = {{Knowledge Graphs, Embeddings, Ensemble Learning}}, location = {{Dayton, OH, USA}}, publisher = {{ACM}}, title = {{{Parameter Averaging in Link Prediction}}}, doi = {{https://doi.org/10.1145/3731443.3771365}}, year = {{2025}}, } @inbook{58874, author = {{Fahrbach, Manuel and Jenert, Tobias and Fust, Alexander and Bellwald, Noah and Winkler, Christoph}}, booktitle = {{Annals of Entrepreneurship Education and Pedagogy - 2025}}, isbn = {{9781035325795}}, keywords = {{Self-Regulated Learning, Entrepreneurship Education, Entrepreneurship Research}}, pages = {{249–265}}, publisher = {{Edward Elgar Publishing}}, title = {{{Fostering self-regulated entrepreneurial learning in entrepreneurship education}}}, doi = {{10.4337/9781035325795.00021}}, year = {{2025}}, } @article{63498, author = {{Kirchgässner, Wilhelm and Förster, Nikolas and Piepenbrock, Till and Schweins, Oliver and Wallscheid, Oliver}}, journal = {{IEEE Transactions on Power Electronics}}, keywords = {{Mathematical models, Estimation, Data models, Convolutional neural networks, Accuracy, Magnetic hysteresis, Magnetic cores, Temperature measurement, Magnetic domains, Temperature distribution, Convolutional neural network (CNN), machine learning (ML), magnetics}}, number = {{2}}, pages = {{3326--3335}}, title = {{{HARDCORE: H-Field and Power Loss Estimation for Arbitrary Waveforms With Residual, Dilated Convolutional Neural Networks in Ferrite Cores}}}, doi = {{10.1109/TPEL.2024.3488174}}, volume = {{40}}, year = {{2025}}, } @article{51518, abstract = {{In applications of piezoelectric actuators and sensors, the dependability and particularly the reliability throughout their lifetime are vital to manufacturers and end-users and are enabled through condition-monitoring approaches. Existing approaches often utilize impedance measurements over a range of frequencies or velocity measurements and require additional equipment or sensors, such as a laser Doppler vibrometer. Furthermore, the non-negligible effects of varying operating conditions are often unconsidered. To minimize the need for additional sensors while maintaining the dependability of piezoelectric bending actuators irrespective of varying operating conditions, an online diagnostics approach is proposed. To this end, time- and frequency-domain features are extracted from monitored current signals to reflect hairline crack development in bending actuators. For validation of applicability, the presented analysis method was evaluated on piezoelectric bending actuators subjected to accelerated lifetime tests at varying voltage amplitudes and under external damping conditions. In the presence of a crack and due to a diminished stiffness, the resonance frequency decreases and the root-mean-square amplitude of the current signal simultaneously abruptly drops during the lifetime tests. Furthermore, the piezoelectric crack surfaces clapping is reflected in higher harmonics of the current signal. Thus, time-domain features and harmonics of the current signals are sufficient to diagnose hairline cracks in the actuators.}}, author = {{Aimiyekagbon, Osarenren Kennedy and Bender, Amelie and Hemsel, Tobias and Sextro, Walter}}, issn = {{2079-9292}}, journal = {{Electronics}}, keywords = {{piezoelectric transducer, self-sensing, fault detection, diagnostics, hairline crack, condition monitoring}}, number = {{3}}, publisher = {{MDPI AG}}, title = {{{Diagnostics of Piezoelectric Bending Actuators Subjected to Varying Operating Conditions}}}, doi = {{10.3390/electronics13030521}}, volume = {{13}}, year = {{2024}}, } @unpublished{53793, abstract = {{We utilize extreme learning machines for the prediction of partial differential equations (PDEs). Our method splits the state space into multiple windows that are predicted individually using a single model. Despite requiring only few data points (in some cases, our method can learn from a single full-state snapshot), it still achieves high accuracy and can predict the flow of PDEs over long time horizons. Moreover, we show how additional symmetries can be exploited to increase sample efficiency and to enforce equivariance.}}, author = {{Harder, Hans and Peitz, Sebastian}}, keywords = {{extreme learning machines, partial differential equations, data-driven prediction, high-dimensional systems}}, title = {{{Predicting PDEs Fast and Efficiently with Equivariant Extreme Learning Machines}}}, year = {{2024}}, } @inproceedings{54960, abstract = {{Das Fachdidaktische Wissen (FDW) wird als zentrale Komponente des Professionswissens von Lehrkräften bereits lange intensiv untersucht. Bislang liegen Ergebnisse zu Zusammenhängen des FDW mit anderen Professionswissensbereichen, zur Performanz in prototypischen Handlungssituationen und erste datengestützte inhaltlich-hierarchische Analysen auf Basis von Item Response Modellen (IRT-Modellen) vor. Im Zusammenhang mit einem projektübergreifend durchgeführten Vergleich entsprechender IRT-Modelle haben sich jedoch Limitationen bei der Vereinbarkeit und der inhaltlichen Reichhaltigkeit entsprechender Ergebnisse gezeigt, wie im Beitrag vorgestellt wird . Daher werden Analysemethoden aus dem Bereich des Machine Learning (unsupervised) vorgeschlagen, welche im Gegensatz zu IRT-Modellen auch nicht-hierarchische inhaltliche Strukturen aufdecken können. Es werden Ergebnisse entsprechender Clusteranalysen sowie Analysepläne zur Unterstützung dieser auf Basis der authentischen Sprachproduktionen von Proband:innen mithilfe von Natural Language Processing vorgestellt.}}, author = {{Zeller, Jannis and Riese, Josef}}, booktitle = {{Frühe naturwissenschaftliche Bildung, Tagungsband der GDCP Jahrestagung 2023}}, editor = {{van Vorst, Helena}}, keywords = {{Physikdidaktisches Wissen, Fähigkeitsprofile, Machine Learning}}, location = {{Hamburg}}, pages = {{122--125}}, publisher = {{Gesellschaft für Didaktik der Chemie und Physik}}, title = {{{Fähigkeitsprofile im Physikdidaktischen Wissen mithilfe von Machine Learning}}}, year = {{2024}}, }