Publication Server of Kempten University
Not a member yet
2351 research outputs found
Sort by
Digitalisierung im deutschen Gesundheitssystem als Chance für mehr Gesundheitsförderung und Prävention in einer alternden Bevölkerung
No full textZeitgleich zum demografischen Wandel verändert die Digitalisierung unsere Gesellschaft und somit auch das Gesundheitswesen. Während die medizinische und pflegerische Versorgung älterer Menschen zumeist im reaktiven Modus agiert – also erst bei Krankheit oder Pflegebedürftigkeit eingreift – eröffnen digitale Technologien neue Wege für einen Paradigmenwechsel: Digitalisierung kann die Chance bieten, den Fokus auf Gesundheitsförderung und Prävention zu verlagern. Dafür ist ein ganzheitlicher Ansatz erforderlich, der ältere Menschen nicht nur als Empfangende von Behandlungen und Pflege betrachtet, sondern sie aktiv in die Gestaltung ihrer Gesundheit einbezieht
Versorgungsinfrastrukturen in der ambulanten Pflege mit Digitalisierung neu gestalten
No full textInfrastrukturen sind das Fundament für reibungslose, effektive und nachhaltige Abläufe – in sämtlichen Lebens- und Arbeitsbereichen und somit auch im Kontext der Pflege
Data-Driven Performance Evaluation of Machine Learning for Velocity Estimation Based on Scan Artifacts from LiDAR Sensors
No full textLight detection and ranging (LiDAR) sensors are increasingly applied to automated driving vehicles. Microelectromechanical systems are an established technology for making LiDAR sensors costeffective and mechanically robust for automotive applications. These sensors scan their environment using a pulsed laser to record a point cloud. The scanning process leads in the point cloud to a distortion of objects with a relative velocity to the sensor. The consecutive generation and processing of points offers the opportunity to enrich the measured object data from the LiDAR sensors with velocity information by extracting information with the help of machine learning, without the need for object tracking. Turning it into a so-called 4D-LiDAR. This allows object detection, object tracking, and sensor data fusion based on LiDAR sensor data to be optimized. Moreover, this affects all overlying levels of autonomous driving functions or advanced driver assistance systems. However, since such sensor-specific effects are rarely available in public datasets and the velocities of target
objects are not included as ground truth in these datasets, it makes sense to enrich the limited real-world data with synthetic data. Therefore, this article discusses how such datasets can be created and combined to efficiently estimate velocities on real-world data using the novel method named VeloPoints
Synthetic Data Generation for AI-Based Quality Inspection of Laser Welds in Lithium-Ion Batteries
No full textManufacturing companies are increasingly confronted with critical challenges such as a shortage of skilled labor, rising production costs, and ever-stricter quality requirements. These challenges become particularly acute when defect types exhibit high visual variance, making consistent and accurate inspection difficult. Traditionally, visual inspection of high variance errors is performed manually by human operators—a process that is both costly and prone to errors. Consequently, there is a growing interest in replacing human inspection with AI-based visual quality control systems. However, the adoption of such systems is often hindered by limited access to training data, labor-intensive labeling processes, or the absence of real production data during early development stages. To address these challenges, this paper presents a methodology for training AI models using synthetically generated image data. The synthetic images are created using Physically Based Rendering, which enables precise control over rendering parameters and facilitates automated labeling. This approach allows for a systematic analysis of parameter importance and bypasses the need for large real training datasets. As a case study, the focus is on the inspection of laser welds in battery connectors for fully electric vehicles—a particularly demanding application due to the criticality of each weld. The results demonstrates the effectiveness of synthetic data in training robust AI models, thereby providing a scalable and efficient alternative to traditional data acquisition and labeling methods. The trained binary classifier reaches a precision of 0.94 with a recall of 0.98 solely trained on synthetic data and tested on real image data
"Wir sind auf halbem Weg"
No full textIn dieser Publikation werden theoretisch-konzeptionelle Grundlagen von Agilität sowie unsere Fallstudien und Expert*inneninterviews zur agilen Praxis im sozialen wie privatwirtschaftlichen Bereich vorgestellt. Für unser Forschungsprojekt gilt dabei wie auch für die agile Praxis: "Wir sind auf halbem Weg
Smart Green Island Makeathon
No full textThe Smart Green Island Makeathon has been organised on Gran Canaria since 2016. At the event, student teams carry out interdisciplinary projects developed using agile methods. The focus of the projects’ tasks is on sustainability. This article presents the history, background, and the current Smart Green Island Makeathon 2024 in particular
Self-perception versus objective driving behavior: Subject study of lateral vehicle guidance
No full textTechnological advances are steering attention toward creating comfortable and acceptable driving characteristics in autonomous vehicles. Ensuring a safe and comfortable ride experience is vital for the widespread adoption of autonomous vehicles, as mismatches in driving styles between humans and autonomous systems can impact passenger confidence. Current driving functions possess fixed parameters, and a universally agreed-upon driving style for autonomous vehicles does not exist. Integrating driving style preferences into automated vehicles may enhance acceptance and reduce uncertainty, expediting their adoption. A controlled subject study focusing on human factors was conducted with a variety of German participants to identify the individual lateral driving behavior of human drivers, specifically emphasizing rural roads. Vehicle and environment-dependent signals were collected during real-world drives with an instrumented vehicle on a predefined Image 1 route. These signals included acceleration and jerk values and the distance to the lane-center. A set of original indicators for analyzing stationary and transient curve negotiation are introduced, directly applicable in developing personalized lateral driving functions. The MDSI-DE, the German version of the Multidimensional Driving Style Inventory, is used to evaluate the predictability of these indicators using self-reports. The results demonstrate that self-reported driving styles can manifest in specific driving behaviors, with statistically significant correlations found mainly with acceleration and jerk values. However, they do not accurately reflect detailed lateral driving behaviors such as curve cutting. Hence, objective indicators for online driving style estimation benefit autonomous vehicle personalization. The gathered dataset is publicly available at https://www.kaggle.com/datasets/jhaselberger/spodb-subject-study-of-lateral-vehicle-guidanc
QualiCheese – Haltbarkeitsoptimierung von Schnittkäse in ökologisch nachhaltigen Verpackungen
No full textKäseverpackungen aus Mehrschichtverbünden sind aktuell nicht recyclebar, weshalb nachhaltige Verpackungslösungen von der Industrie verlangt werden, um, unter anderem, besseres Recycling zu ermöglichen. Im dem Interreg-Projekt QualiCheese wird untersucht, welche praktischen Probleme bei der Umstellung auf neue Verpackungsmaterialien auftreten. In dieser Arbeit werden erste Ergebnisse aus dem laufenden Projekt vorgestellt.
Konkret wurde Tiroler Bergkäse am Block in einem Cellulose-Stärke-Verbund verpackt und mit einer PA-PE-Referenz verglichen. Die ersten Ergebnisse bei Standardbedingungen deuten nicht darauf hin, dass eine der beiden Verpackungen für den untersuchten Käse ungeeignet ist. Bei Extrembedingungen außerhalb des Anwendungsszenarios mit erhöhter Luftfeuchtigkeit konnte jedoch beobachtet werden, dass die Sauerstoffbarriere der Referenzverpackung abnimmt und es zu Schimmelbildung kommt
Automated Tracking of User Interactions in Web-Based Adaptive Learning for Software Engineering
No full textThis paper explores the automation of generating and dispatching Experience API (xAPI) statements for comprehensive tracking of user interactions in e-learning environments. It introduces the react-xapi-wrapper library, an extension of the xAPI JavaScript library designed for use in web applications. Key aspects discussed include the library’s features, its integration into a web-based adaptive learning system (ALS) for software engineering, and the custom verbs used. The goal is to reduce implementation effort for tutors and developers while taking advantage of xAPI’s interoperability, scalability, and ability to track student learning activities and behaviors, laying the foundation for more responsive and personalized learning experiences