Offenburg University of Applied Sciences
Hochschulschriftenserver der Hochschule OffenburgNot a member yet
6641 research outputs found
Sort by
Thigh muscle activity in experienced female handball players during preplanned and unplanned sidestep cuts
No full textThe purpose of this study was to assess if there is a difference in the thigh muscle activation patterns between a preplanned and unplanned sidestep cut performed by n = 31 experienced female handball players. Electromyogram vector fields containing the muscle activity of the vastus medialis, vastus lateralis, semitendinosus, and biceps femoris from 100 ms before ground contact until toe-off were created and compared using Statistical Parametric Mapping. Results show lower activity in the unplanned cut. When comparing individual muscles, vastus medialis was the only muscle showing differences between tasks, with the unplanned task eliciting lower activity right before initial ground contact. The findings of this study indicate that the knee joint might be more vulnerable to external knee joint moments in unplanned cutting tasks due to lower muscle pre-activity
Editorial on the Special Section of CELLMAT 2022
No full textCellular materials are an established field of research, often driven by applications. Manufactur-ing issues traditionally play a significant role in such established topics. New manufacturing pro-cesses frequently create cellular structures, and the question of the industrial usability of these techniques remains a key concern for the community. The boundaries between traditional mate-rial classes often blur, as manufacturing processes can be applied to a wide variety of materials. This trend is exemplified by the ongoing use of additive manufacturing methods, particularly in the production of highly porous materials. The contributions published in this special section are selected works presented during the CELLMAT 2022 conference, highlighting the advancements in eco-friendly and sustainable techniques in the field of cellular materials
Simulation Environment for the Evaluation of LiDAR Odometry Algorithms
No full textThis study focused on enhancing odometry estimation for self-driving cars using LiDAR-based sensor technology. The project involves integrating LiDAR sensors into the car’s sensor suite, which generates detailed 3D point clouds of the environment. This integration can be useful when gaps-based odometry estimation is not accurate enough. These point clouds are then used to accurately estimate the vehicle’s movement and position using learning-based and model-based odometry estimation methods
Gesetz über den Schutz von Marken und sonstigen Kennzeichen (Markengesetz – MarkenG) (Auszug)
No full textKommentierung des Markenrecht
Semi-supervised mold differentiation using typical laboratory results as label data
No full textThis study applies semi-supervised learning to automate the differen-tiation of mold colonies, thereby reducing the time and cost associated with airquality assessments. EfficientNet V2 and Normalization-Free Net (NfNet) weretrained on a dataset of mold colony images, created in a semi-supervised way.NfNet demonstrated superior performance, particularly on non-padded images,with explainable AI techniques enhancing interpretability. The models exhibitedgeneralization capabilities to environmental samples, indicating the potential forautomating mold identification and streamlining air quality monitoring, therebyreducing manual effort and costs. Future work will focus on refining species han-dling and integrating the system into laboratory workflows
Erstellung von ‚Lösungen‘ optimal gestalten – Ein Best-Practice-Beispiel aus der Industrie
No full textAnhand einer Best Practice wird untersucht, wie ein Lösungsanbieter die Lösungserstellung im Sinne der Balance zwischen Standardisierung und Individualisierung gestalten kann. Die Anwendung von zwei Projekttypen hat sich als lösungsadäquat herausgestellt. Der erste Projekttyp konzentriert sich auf die Erstellung von Lösungskomponenten, die dem Vertrieb an der Kundenschnittstelle zur Generierung von kundenindividuellen Lösungen zur Verfügung stehen. Wenn dieser Projekttyp das Kundenproblem nicht lösen kann, dann kommt der zweite Projekttyp zum Einsatz, bei dem das Kundenproblem durch den Vertrieb ins Unternehmen getragen wird, um anschließend die Lösungsgenerierung in Gang zu setzen
Urban Sound Propagation: a Benchmark for 1-Step Generative Modeling of Complex Physical Systems
No full textData-driven modeling of complex physical systems is receiving a growing amount of attention in the simulation and machine learning communities. Since most physical simulations are based on compute-intensive, iterative implementations of differential equation systems, a (partial) replacement with learned, 1-step inference models has the potential for significant speedups in a wide range of application areas. In this context, we present a novel benchmark for the evaluation of 1-step generative learning models in terms of speed and physical correctness.
Our Urban Sound Propagation benchmark is based on the physically complex and practically relevant, yet intuitively easy to grasp task of modeling the 2d propagation of waves from a sound source in an urban environment. We provide a dataset with 100k samples, where each sample consists of pairs of real 2d building maps drawn from OpenStreetmap, a parameterized sound source, and a simulated ground truth sound propagation for the given scene. The dataset provides four different simulation tasks with increasing complexity regarding reflection, diffraction and source variance. A first baseline evaluation of common generative U-Net, GAN and Diffusion models shows, that while these models are very well capable of modeling sound propagations in simple cases, the approximation of sub-systems represented by higher order equations systematically fails
Bibliometric Analysis as a Means of Efficiently Assessing Trends in Artificial Intelligence
No full textTransportation planners are increasingly relying on AI to optimize logistics and solve persistent challenges. However, as AI advances rapidly, most software vendors are unable to evaluate and implement all new developments. This paper uses bibliometric methods to track and evaluate the emerging trend of neurosymbolic AI, which combines neural networks with symbolic AI to improve decision making. By analyzing literature and citation data, we gain insights into the development and impact of neurosymbolic AI. The results provide a scalable approach for practitioners to efficiently identify and evaluate AI trends to facilitate the strategic adoption of technologies and innovations in transportation planning
Machine Learning Based Prediction of One Year Mortality after Allogeneic Hematopoietic Cell Transplantation (alloHCT) Highlights Importance of Pre-Transplant Immunocompetence
No full textFine-Grained Product Classification on Leaflet Advertisements
No full textIn this paper, we describe a first publicly available fine-grained product recognition dataset based on leaflet images. Using advertisement leaflets, collected over several years from different European retailers, we provide a total of 41.6k manually annotated product images in 832 classes. Further, we investigate three different approaches for this fine-grained product classification task, Classification by Image, Classification by Text, as well as Classification by Image and Text. The last both approaches use the text extracted directly from the leaflet product images. We show, that the combination of image and text as input improves the classification of visual difficult to distinguish products. The final model leads to an accuracy of 96.4% with a Top-3 score of 99.2%.
https://github.com/ladwigd/Leaflet-Product-Classificatio