Offenburg University of Applied Sciences
Hochschulschriftenserver der Hochschule OffenburgNot a member yet
6641 research outputs found
Sort by
Design of an Energy Harvesting-Based Vibration Sensor for Predictive Maintenance
No full textThis research involved the design of a passive vibration harvester utilized as a sensor for measuring the frequency of periodic vibrations. The oscillator design is aligned to a specific frequency and uses the eigenfrequencies of the material and geometry. Combined with a piezoelectric structure, energy conversion sufficient for signal generation occurs only at resonance. This creates an active sensor system that does not need an external energy supply for signal generation
Can Machine Learning and Explainable Artificial Intelligence Help to Improve an Expert Model for Predicting Thermomechanical Fatigue?
No full textMachine learning (ML) models are increasingly used for predictive tasks, yet traditional data-based models relying on expert knowledge remain prevalent. This paper examines the enhancement of an expert model for thermomechanical fatigue (TMF) life prediction of turbine components using ML. Using explainable artificial intelligence (XAI) methods such as Permutation Feature Importance (PFI) and SHAP values, we analyzed the patterns and relationships learned by the ML models. Our findings reveal that ML models can be trained on TMF data, but integrating domain knowledge remains crucial. The study concludes with a proposal to further refine the expert model using insights gained from ML models, aiming for a synergistic improvement
Marketingentscheidungen zielgenau vorbereiten – Wie User Experience Testings die Bedürfnisse und Wünsche der Zielgruppe entschlüsseln
No full textDer Beitrag zeigt, dass Marketingentscheidungen auf Basis von User Experience-Untersuchungen besser getroffen werden können, indem die Maßnahmen zielgenau auf die Bedürfnisse und Wünsche der Kunden und Kundinnen abgestimmt und anhand geeigneter UX-Kennzahlen überprüft werden. Unternehmen, die ihre User Experience so gestalten, dass sie für ihre Zielgruppen soziale Bedeutung erlangt und deren Erwartungen entspricht, werden an viralen Effekten, wachsenden Kundenzahlen und langfristigen Kundenbeziehungen teilhaben können
UX-Optimized Lottery Customer Acquisition Processes Through Automated Content Creation: Framework of an Industry-University Cooperation
No full textArtificial intelligence (AI) and Machine Learning (ML) are rapidly turning from trending topics to requirement for competitiveness for enterprises. For marketing departments, AI and ML offer potential for improvement of their processes such as optimizing user experience and personalizing campaigns for selected audiences. Nevertheless, the integration of new technologies such as AI and ML into the existing marketing mix portfolio means a great challenge for marketing managers as their implementation requires new skills and knowledge which is not always already developed. The objective of the paper is to demonstrate how an industry-university cooperation (IUC) can enable the adaptation to new business contexts. Thus, this paper proposes a framework on IUC involving different project phases. It describes the process for placing AI-generated individual content, recommendations and references for specific interests
Advancing our ability to quantify an individual’s habitual motion path and deviation when running
No full textThe habitual motion path theory states that exhibiting kinematic differences between running and habitual movement tasks may increase the risk of running-related injury. Staying near one’s habitual motion path when running has been shown to reduce compression of the knee joint cartilage, a proxy for decreased soft tissue loading. Previous efforts to quantify one’s habitual motion path and deviation when running have utilised just one habitual movement and one time point during the stance phase of running. The methodology advancement described in this manuscript focused on advancing habitual motion path theory research by (1) increasing the number of movements for quantifying an individual’s habitual motion path; and (2) utilising the entire stance phase when running to quantify deviations as opposed to one time point. We liken the advancements in the method described in this manuscript as with the first method we were using a ruler to assess one’s habitual motion path and deviations, and now we are using calipers; providing a more accurate understanding of an individual’s unique habitual movement and deviation when running. We also discuss future potential research avenues related to understanding running biomechanics and footwear effects that this tool will allow us to explore
Effect of increased shoe longitudinal bending stiffness on ankle and foot biomechanics in jump-cut movements of low and high degrees
No full textLateral ankle sprains are the most common injuries in indoor and court sports, with ankle inversion being a primary injury driver. Stabilising the ankle during multidirectional changes is crucial for injury prevention. Conversely, increased shoe stiffness has been hypothesised to influence the magnitude of ankle inversion and may raise the risk for ankle injuries. Therefore, the purpose of this study was to investigate the influence of shoe longitudinal bending stiffness on ankle biomechanics during indoor and court sport-specific cutting movements. Biomechanical data from 19 participants were collected using a motion capture system and force plate. A jump-cut protocol with two different cutting directions after landing was performed in indoor shoes with and without carbon plate inserts of varying stiffness. Ankle kinematics and kinetics were analysed with statistical parametric mapping and repeated measures analysis of variance. A significant increase in ankle inversion during the 180° cut and a reduction in forefoot inversion (foot torsion) for stiffer footwear conditions during both the 45° and 180° cut were observed. While dorsiflexion moments differed during the last 10% of ground contact, ankle inversion moments did not significantly diverge between shoe conditions. Furthermore, a noteworthy correlation between footwear longitudinal bending stiffness and torsional stiffness was identified. In conclusion, increased bending stiffness significantly affected ankle and foot kinematics. The ankle compensated for restricted mobility and higher demands during high-degree jump-cuts, while foot torsion played a more prominent role in low-degree cuts. The heightened ankle inversion during high-degree cuts may induce an elevated risk for lateral ankle sprains. Further longitudinal studies are necessary to comprehensively understand injury incidence and the role of shoe stiffness in injury prevention
Gesetz über Urheberrecht und verwandte Schutzrechte (Urheberrechtsgesetz – UrhG)
No full textKommentierung des Urheberrecht
WoodYOLO: A Novel Object Detector for Wood Species Detection in Microscopic Images
Get PDFWood species identification plays a crucial role in various industries, from ensuring the legality of timber products to advancing ecological conservation efforts. This paper introduces WoodYOLO, a novel object detection algorithm specifically designed for microscopic wood fiber analysis. Our approach adapts the YOLO architecture to address the challenges posed by large, high-resolution microscopy images and the need for high recall in localization of the cell type of interest (vessel elements). Our results show that WoodYOLO significantly outperforms state-of-the-art models, achieving performance gains of 12.9% and 6.5% in F2 score over YOLOv10 and YOLOv7, respectively. This improvement in automated wood cell type localization capabilities contributes to enhancing regulatory compliance, supporting sustainable forestry practices, and promoting biodiversity conservation efforts globally
AI-Guided Noise Reduction for Urban Geothermal Drilling
No full textUrban geothermal energy production plays a critical role in achieving global climate objectives. However, drilling operations in densely populated areas generate significant noise pollution, posing challenges to community acceptance and regulatory compliance. This research presents an artificial intelligence-driven approach to dynamically reduce noise emissions during geothermal drilling. We integrate Deep Reinforcement Learning (DRL) with generative neural network models to provide real-time recommendations for optimal drilling parameters. Specifically, the Drill-LSTM model forecasts future machine states, while the Sound-GAN framework predicts sound propagation based on varying operational conditions. These models feed into a DRL-Agent that learns to balance drilling efficiency with noise minimization. Additionally, an interactive assistance system GUI presents predictions, forecasts, and recommendations to human operators, facilitating informed decision-making. Our system demonstrates significant potential in reducing noise levels, enhancing operational efficiency, and fostering greater acceptance of urban geothermal projects. Future work will focus on refining the models and validating the system in real-world drilling scenarios