Offenburg University of Applied Sciences
Hochschulschriftenserver der Hochschule OffenburgNot a member yet
6641 research outputs found
Sort by
Positive joint work redistribution in running: the role of plantar flexor fatigue and the effect of advanced footwear technology
No full textOver the course of a near-maximal effort 10 km run, positive mechanical work decreases at the ankle and increases at the knee. Although plantar flexor fatigue is believed to be responsible for the proximal shift in mechanical work generation, this has yet to be confirmed experimentally
KINLI: Time Series Forecasting for Monitoring Poultry Health in Complex Pen Environments
Get PDFWe analyze how to perform accurate time series forecasting for monitoring poultry health in a complex pen environment. To this end, we make use of a novel dataset consisting of a collection of real-world sensor data in the housing of turkeys. The dataset comprises features such as food intake, water intake, and various environmental values, which come with high variance, sensor defects, and unreliable timestamps. In this paper, we investigate different state-of-the-art forecasting algorithms to predict different features, as well as a variety of deep learning models such as different transformer models and time series foundational models. We evaluate both their forecasting accuracy as well as the efforts required to run the models in the first place. Our findings show that some of these aforementioned algorithms are able to produce satisfactory forecasting results on this highly challenging dataset while still remaining easy to use, which is key in a tech-distant industry such as poultry farming
Engineering intervertebral disc replacements using 3D-printed open gyroid architectures
No full textDegenerative disc disease is a leading cause of chronic back pain, and current surgical treatments such as fusion and disc arthroplasty remain limited by implant wear, stress shielding, and mechanical mismatch with the native intervertebral disc (IVD). This study investigates three-dimensional (3D) printed thermoplastic polyurethane (TPU) Gyroid structures as biomimetic disc replacements. Using filaments of varying stiffness, 3D-printed constructs demonstrated high geometric fidelity and mechanical performance within physiological load and deformation ranges. Dynamic compression testing revealed damping coefficients of approximately 16%, closely matching native IVD behavior. Stiffness scaled predictably with structural density, allowing mechanical tuning toward physiological properties. These findings highlight the potential of Gyroid-structured TPU implants to replicate the natural damping and load distribution of human discs, offering a pathway toward customizable, patient-specific disc replacements. Future work will focus on medically approved TPU, biological responses, and multiaxial loading
Empfehlungen zur Auswahl von Zielparametern und Prozessempfehlungen bei audiologisch-technischen Funktionsprüfungen des Cochlea-Implantats
Get PDFContinuous monitoring of the technical and physiological function of cochlear implants (CI) is a central part of the care process. Despite worldwide efforts to standardise procedures, there is still considerable variation between CI centres, particularly in terms of the methods used, their practical implementation and the definition of meaningful target parameters. A standardised structured test procedure is needed for reliable quality assurance and better comparability. Against this background, the ADANO Working Group for Evoked Response Audiometry (AG-ERA), in close cooperation with the Cochlear Implants and Implantable Hearing Systems Committee of the German Society of Audiology (DGA), developed a minimum standard for audiological and technical functional testing of CIs in an open consensus process. This standard defines basic requirements for performance and documentation and serves as a practical recommendation for CI centres. It is intended to improve interdisciplinary cooperation, increase the quality of care and enable structured long-term optimised care for CI patients.Die kontinuierliche Kontrolle der technischen und physiologischen Funktion von Cochlea-Implantaten (CI) stellt einen zentralen Baustein im gesamten Versorgungsprozess dar. Trotz weltweiter Bestrebungen zur Vereinheitlichung der Verfahren zeigen sich nach wie vor erhebliche Unterschiede zwischen den CI-versorgenden Einrichtungen – insbesondere hinsichtlich der eingesetzten Methoden, ihrer praktischen Umsetzung und der Festlegung aussagekräftiger Zielgrößen. Für eine verlässliche Qualitätssicherung und verbesserte Vergleichbarkeit ist ein einheitlicher, strukturierter Prüfprozess erforderlich. Vor diesem Hintergrund wurde in einem offenen Konsensverfahren der Arbeitsgruppe Elektrische Reaktionsaudiometrie (AG-ERA) der ADANO, gemeinsam mit dem Fachausschuss „Cochlea-Implantate und implantierbare Hörsysteme“ der DGA, ein Minimalstandard für die audiologisch-technische Funktionsprüfung von CI entwickelt. Dieser definiert grundlegende Anforderungen an Durchführung und Dokumentation und dient als praxisnahe Empfehlung für CI-versorgende Einrichtungen. Ziel ist eine standardisierte, nachvollziehbare Vorgehensweise, die die interdisziplinäre Zusammenarbeit verbessert, die Versorgungsqualität erhöht und eine strukturierte, langfristig optimierte Betreuung von CI-Tragenden ermöglicht
A Proposal for a Taxonomy of AI-Related Use Cases in Higher Education
No full textArtificial Intelligence (AI)-based technologies are increasingly transforming higher education, leading to substantial advances in educational methodologies. Universities must document and classify existing or newly developed AI-based teaching and learning scenarios. Such classification is essential for helping instructors make informed decisions, estimate associated development and operational costs, and facilitate effective utilization. Existing literature frequently focuses classifications on either
technological tool characteristics or the student's viewpoint. In contrast, this article proposes a complementary educator-centered taxonomy to make the pedagogical benefits and constraints of AIsupported educational scenarios more transparent, particularly from the educator’s perspective. We
propose evaluating the three core dimensions: repetition (R), data access (D), and semantic discrimination (S). By assessing these dimensions, educators gain a better understanding of which teaching scenarios benefit significantly from AI support. After reviewing existing classification literature
in higher education contexts, we introduce our taxonomy and demonstrate its practical applicability in selected educational use cases
Schutz vor Social Engineering (Teil 1)
No full textDie Tatsache, dass digitalwirtschaftliche Geschäftsmodelle zunehmend mit Cyberangriffen zu rechnen haben, verlangt nach einer resilienten Abwehr in Form eines wirksamen Internen Kontrollsystems. Da der Beginn der Angriffsvektoren häufig mit dem Social Engineering verknüpft ist, empfiehlt sich eine Härtung/Festigung der organisatorischen Außenschichten, bevor ein Eindringen in die IT-Infrastruktur gelingt. Im Rahmen dieser dreiteiligen Artikelserie beschäftigt sich die erste Abhandlung mit generischen Risikomodellen und der inhaltlichen Ausgestaltung des Social Engineering als Vorbereitung für ein besseres Verständnis der konkreten Angriffsschritte und Gegenmaßnahmen
A Visual RAG Pipeline for Few-Shot Fine-Grained Product Classification
No full textDespite the rapid evolution of learning and computer vision algorithms, Fine-Grained Classification (FGC) still poses an open problem in many practically relevant applications. In the retail domain, for example, the identification of fast changing and visually highly similar products and their properties are key to automated price-monitoring and product recommendation. This paper presents a novel Visual RAG pipeline that combines the Retrieval Augmented Generation (RAG) approach and Vision Language Models (VLMs) for few-shot FGC. This Visual RAG pipeline extracts product and promotion data in advertisement leaflets from various retailers and simultaneously predicts fine-grained product ids along with price and discount information. Compared to previous approaches, the key characteristic of the Visual RAG pipeline is that it allows the prediction of novel products without retraining, simply by adding a few class samples to the RAG database. Comparing several VLM back-ends like GPT-4o [23]. GPT-4o-mini [24], and Gemini 2.0 Flash [10], our approach achieves 86.8% accuracy on a diverse dataset
Encoding Spatio-Temporal Coordinates in Seismic Demultiple with Convolutional Neural Networks
No full textMultiple attenuation is an essential step in seismic processing, as it significantly improves data inversion and interpretation. Deep learning (DL) has emerged as a promising alternative for various seismic processing tasks, including multiple attenuation. In particular, Convolutional Neural Networks (CNNs), originally designed for natural image processing, have been applied to seismic problems as image-to-image translation tasks. However, existing CNN-based deep learning approaches neglect the spatio-temporal characteristics of seismic recordings, which are critical for interpreting seismic data as signals rather than images. In this study, we introduce a novel methodology to integrate spatio-temporal information into CNNs for seismic data processing tasks. Specifically, we focus on seismic multiple discrimination based on moveout in CDP gathers. We evaluate the impact of incorporating spatio-temporal
