Publikationsserver der Ostbayerischen Technischen Hochschule Regensburg
Not a member yet
6172 research outputs found
Sort by
Die Komplexität nachhaltiger Physiotherapie
No full textUm mögliche Forschungsperspektiven in Bezug auf die UN-Nachhaltigkeitsziele 3 (Gesundheit und Wohlergehen) und 13 (Maßnahmen zum Klimaschutz) aufzeigen zu können, stellten sich die Autor*innen dieses Beitrags die Frage, wie Physiotherapie langfristig Nachhaltigkeit fördern kann und was es dafür in der Versorgung braucht. Wie Physiotherapeut*innen ihre Therapie nachhaltig gestalten können wurde mit Teilnehmenden des Workshops Planetare Gesundheit auf dem 6. Forschungssymposium der Deutschen Gesellschaft für Physiotherapiewissenschaft (DGPTW) in Freiburg diskutiert. Dabei stellte sich heraus, dass sich die Physiotherapeut*innen neben dem Wie? vor allem die Frage nach dem Warum (wir)? stellten und angaben unsicher mit dem Thema Klimawandel in der Behandlung zu sein. Daraus wurden zwei Schwerpunktthemen abgeleitet, welche in diesem Beitrag ausgearbeitet werden. 1) Emotionalität im professionellen Handeln: Wie Professionalität die richtigen Emotionen zur Bewältigung der heutigen Krisen fördern kann und 2) Komplexe Entscheidungsprozesse fördern – ‚sustainable decision-making‘ am Beispiel der Teletherapie. Aus den Ausarbeitungen kann geschlossen werden, dass Physiotherapie in ihrer Komplexität zunehmen wird, wenn sie nachhaltig sein soll, weil sie vielfältige Probleme berücksichtigen muss. Dafür braucht es qualifizierte Physiotherapeut*innen, die befähigt und bemächtigt sind, die komplexen Anforderungen zu bewältigen
Embedding Circular Economy in the Construction Sector Policy Framework: Experiences from EU, U.S., and Japan for Better Future Cities
No full textThe transition towards a Circular Economy (CE) in the construction sector is essential to achieving sustainable, inclusive smart cities. This study examines the integration of CE principles into construction policies across four key global contexts: the European Union (focusing on Italy and Germany), the United States, and Japan. Through a comparative policy analysis, the research identifies best practices, implementation barriers, and the role of digitalization in advancing CE strategies. In Europe, CE is embedded in policy frameworks such as the Green Deal and the New Circular Economy Action Plan, driving the shift toward sustainable urban development. The United States, while in the early stages of CE adoption, is fostering circular initiatives at local levels, particularly in waste management and building deconstruction. Japan’s policy landscape integrates CE within a broader strategy for resource efficiency, emphasizing technological innovation. The findings highlight the necessity of a research-driven approach to inform policies that leverage digital tools, such as Building Information Modeling and Digital Product Passports, to enhance material traceability and urban circularity. This study contributes to the global effort of designing smart cities that are not only technologically advanced but also environmentally and socially sustainable through the adoption of CE principles in the built environment
Deepfake Detection of Face Images based on a Convolutional Neural Network
No full textFake News and especially deepfakes (generated, non-real image or video content) have become a serious topic over the last years. With the emergence of machine learning algorithms it is now easier than ever before to generate such fake content, even for private persons. This issue of generated fake images is especially critical in the context of politics and public figures. We want to address this conflict by building a model based on a Convolutions Neural Network in order to detect such generated and fake images showing human portraits. As a basis, we use a pre-trained ResNet-50 model due to its effectiveness in terms of classifying images. We then adopted the base model to our task of classifying a single image as authentic/real or fake by adding an fully connected output layer containing a single neuron indicating the authenticity of an image. We applied fine tuning and transfer learning to develop the model and improve its parameters. For the training process we collected the image data set ’Diverse Face Fake Dataset’ containing a wide range of different image manipulation methods and also diversity in terms of faces visible on the images. With our final model we reached the following outstanding performance metrics: precision = 0.98, recall 0.96, F1-Score = 0.97 and an area-under-curve = 0.99
Cross lingual transfer learning does not improve aphasic speech recognition
No full textIn addressing the particular linguistic challenges posed by patients suffering from aphasia, a language disorder, this paper proposes a fine-tuning approach to enhance the speech recognition capabilities of existing models. The available aphasic research data in German is highly limited. To address this constraint, we propose a cross-lingual transfer approach to utilize English data to improve performance in German. This advancement aims to support the development of a therapy platform tailored for patients with aphasia. For the base speech recognition model, we choose to use OpenAI’s Whisper model, and for fine-tuning, we make use of TalkBank’s AphasiaBank. The experimental findings demonstrate that the transcription of aphasic audio with Whisper is less successful than non-aphasic audio. However, fine-tuning the transcription in the respective language resulted in an enhancement of its quality. In contrast, fine-tuning the transcription in another language and expecting a transfer of the learned aphasic speech properties led to a deterioration in its quality
Modellierung des Verkehrsmittelwahlverhaltens mittels erklärbarem Maschinellem Lernen
No full textDie Modellierung der Verkehrsmittelwahl ist für die Vorhersage und das Verständnis des Mobilitätsverhaltens unerlässlich. Hierbei wurden in den letzten Jahren mit maschinellem Lernen vielversprechende Ergebnisse erzielt, insbesondere für XGBoost- und Random-Forest-Modelle.
Aufgrund der zunehmenden Verwendung von Tracking-basierten Smartphone-Apps zur Aufzeichnung des Mobilitätsverhaltens, wenden wir diese Modelle auf einen solchen Datensatz
an. Zudem analysieren wir eingehend deren Interpretierbarkeit. Wir kommen zu dem Schluss,
dass das XGBoost-Modell am leistungsstärksten und dennoch erklärbar ist. Die von solchen
Modellen gewonnenen Erkenntnisse können beispielsweise genutzt werden, um die Verkehrsmittelwahl für beliebige Quelle-Ziel-Paare vorherzusagen
One- and two-sided prediction intervals for future Pareto record values with applications
No full textBased on upper record values in a series of observations over time from a Pareto distribution, an exact and several approximate one-sided and two-sided prediction intervals for the next record value (or for another future record value) to appear are studied and compared by means of an extensive simulation study. The performances of the prediction intervals are evaluated and recommendations are proposed for what method should be used in a given situation with respect to the form of the prediction interval on the one hand and to the tail behaviour on the other. The proposed methods are applied to insurance, environmental and sports data, where the respectively fitted Pareto distributions show a different tail behaviour. As a result, it is seen that although the number of observed record values in the presented real data applications is rather small, as it is usually the case, the selected prediction intervals are of practical use
Introduction to the Minitrack on Simulation Modeling, Artificial Intelligence and Digital Twins for Decision Making in Production and Logistics
No full textThe minitrack contains contributions with a focus on simulation modeling and digital twins and decision making in the context of Industry 4.0. The use of simulation models and digital twins is manifold, from planning to virtual commission and real-time operational decision support. Cyber-physical systems integrate the real world and the virtual world to enable decision making in the age of Industry 4.0.
For example, customer decisions and supply disruptions which directly influence manufacturing and logistics systems require immediate decisions. Thus, models must have the capability to support decision making in manufacturing as well as in internal and external logistics in real-time. Methods include discrete-event simulation, discrete-rate simulation, hybrid simulation, system dynamics simulation, the combination of simulation modeling with machine learning or optimization heuristics, prescriptive analytics, and adaptive systems. Furthermore, this minitrack addresses simulation education and simulation models and digital twins used for education and training in manufacturing and logistics
Nachhaltigkeit im Gesundheitswesen: Ökologische Transformation im Unternehmen Krankenhaus
No full textDie Gesundheitswirtschaft ist nicht nur für die Versorgung der Bevölkerung unerlässlich, sondern sie hat auch eine große ökonomische Bedeutung: Im Jahr 2020 wurden im Gesundheitssektor 12,1 % des deutschen Bruttoinlandsprodukts erwirtschaftet, in etwa die Hälfte davon in der Gesundheitsversorgung. Gleichzeitig ist der ökologische Fußabdruck der Gesundheitswirtschaft erheblich: Sie ist z. B. in Deutschland für 5,2 % der gesamten klimaschädlichen Emissionen verantwortlich. Ein relevanter Anteil der Emissionen fällt dabei in der stationären Gesundheitsversorgung in Krankenhäusern an, die einen hohen Ressourcenverbrauch (Energie, Wasser und Verbrauchsmittel) und ein hohes Abfallaufkommen haben. In den letzten Jahrzehnten haben sich politische Initiativen entwickelt, die sich für mehr Nachhaltigkeit in Krankenhäusern einsetzen: Zum einen engagieren sich in einer globalen Bewegung die Gesundheitsberufe für den Erhalt der natürlichen Lebensgrundlagen und ein nachhaltiges Gesundheitswesen (Klimaschutz als Gesundheitsschutz). Zum anderen sind Krankenhäuser zunehmend unter Effizienz- und Regulierungsdruck, Managementstrategien und Berichterstattung zu Nachhaltigkeit einzuführen. Der Buchbeitrag wird den Stand der Forschung und Praxis in Bezug auf die Transformation von Krankenhäusern zu nachhaltigen Organisationen beschreiben, und ihre spezifischen ökologischen Herausforderungen und Handlungsfelder vorstellen
Prediction of the wear behavior of a conveyor belt with flexible rollers
No full textThis paper introduces a method to predict wear behavior in conveyor belt systems using a lumped mass modeling approach. While previous research has focused primarily on lateral belt walking, this study shifts attention to belt deformation and its associated wear. Both significantly affect system efficiency and component lifespan. The authors propose using local frictional power as a wear indicator, leveraging its direct relation to frictional work in established wear models. To validate the method, the study simulates a conveyor belt with three flexible rollers and a deformable belt modeled through rigid spheres connected by spring-damper elements. The authors quantify and visualize frictional power density across the belt width, distinguishing between running and transverse directions. The results demonstrate that the frictional power distribution depends heavily on discretization quality, particularly due to the polygon effect inherent in the lumped mass approach. A convergence analysis reveals a minimum discretization of nine sphere rows with 557 spheres per row to achieve reliable qualitative insights. This method enables researchers to evaluate wear distribution in flexible conveyor systems and adapt the approach for broader applications in multibody dynamics. Future work should refine discretization techniques and friction models to enhance quantitative accuracy