OPUS - Publikationenserver der Technischen Hochschule Nürnberg Georg Simon Ohm
Not a member yet
2332 research outputs found
Sort by
Near real-time change detection tool for photogrammetric flood preparedness
No full textThrough the mobilization of movable objects due to the extreme hydraulic conditions during a flood event, blockages, damage to infrastructure, and endangerment of human lives can occur. To identify potential hazards from aerial imagery and take appropriate precautions, a change detection tool (CDT) was developed and tested using a study area along the Aisch River in Germany. The focus of the CDT development was on near real-time analysis of point cloud data generated by structure from motion from aerial images of temporally separated surveys, enabling rapid and targeted implementation of measures. The differences identified in the study area using distance comparison (M3C2) were segmented into individual components and categorized. Subsequently, the data was compared to existing two-dimensional hydrodynamic numerical calculation results (HQ100). The implementation of the CDT is feasible for a variety of RGB camera-equipped aerial vehicles due to the point cloud-based analysis and postprocessing. By overlaying and visualizing the detected changes with numerical simulation results, a quick assessment of the hazard potential in the event of a possible flood can be made. In the case of the study area along the Aisch River, the localization of construction materials, a steel container with debris pile, and a motor vehicle in the flood hazard zone of a potential HQ100 event could be confirmed, although no mobilization of the materials was to be expected due to the expected hydraulic conditions of a flood event
Auswirkungen des EU AI Act auf den Einsatz von Künstlicher Intelligenz in der Hochschullehre
No full textBei der Untersuchung der Auswirkungen des AI Act auf den Einsatz von KI in der Hochschullehre wird die Mehrheit der relevanten Tools der Kategorie des transparenzpflichtigen Risikos zugewiesen. Entscheidend für die daraus entstehenden Pflichten ist, ob die Hochschule Software selbst entwickelt und
anbietet oder nur betreibt. Die Ermittlung der indirekten Auswirkungen erfolgt unter Zuhilfenahme des PESTEL-Modells. Zu den hochschulpolitischen Folgen zählt insbesondere die Notwendigkeit einer Anpassung der Lehrpläne sowie eine Weiterbildung des Hochschulpersonals. Auf soziokultureller Ebene
lässt sich eine verstärkte Akzeptanz von KI-Systemen beobachten. Gleichzeitig birgt aus wirtschaftlicher Perspektive die Einführung strengerer Anforderungen an Hochrisiko-KI-Systeme eine Kostensteigerung. Aus technologischer Perspektive lässt sich eine zunehmende Relevanz neuer Tools im Hochschulbereich beobachten. Die rechtliche Dimension betont die
Bedeutung von Compliance-Management-Systemen
40 Jahre Agnes-Sapper-Haus auf dem Hintergrund der Psychiatrie-Enquete
No full textDurch die Reformideen der Psychiatrie-Enquete entstand vor 40 Jahren das Übergangswohnheim Agnes-Sapper-Haus in Würzburg
HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models
No full textSafety guard models that detect malicious queries aimed at large language models(LLMs) are essential for ensuring the secure and responsible deployment of LLMs in real-world applications. However, deploying existing safety guard models with billions of parameters alongside LLMs on mobile devices is impractical due to substantial memory requirements and latency. To reduce this cost, we distill a large teacher safety guard model into a smaller one using a labeled dataset of instruction-response pairs with binary harmfulness labels. Due to the limited diversity of harmful instructions in the existing labeled dataset, naively distilled models tend to underperform compared to larger models. To bridge the gap between small and large models, we propose HarmAug, a simple yet effective data augmentation method that involves jailbreaking an LLM and prompting it to generate harmful instructions. Given a prompt such as, “Make a single harmful instruction prompt that would elicit offensive content”, we add an affirmative prefix (e.g., “I have an idea for a prompt:”) to the LLM’s response. This encourages the LLM to continue generating the rest of the response, leading to sampling harmful instructions. Another LLM generates a response to the harmful instruction, and the teacher model labels the instruction-response pair. We empirically show that our HarmAug outperforms other relevant baselines. Moreover, a 435-millionparameter safety guard model trained with HarmAug achieves an F1 score comparable to larger models with over 7 billion parameters, and even outperforms them in AUPRC, while operating at less than 25% of their computational cost. Our code, safety guard model, and synthetic dataset are publicly available
Quorn Foods: the road to supply chain resilience
No full textIn 2025, Quorn Foods faced a pivotal strategic decision as the United Kingdom’s government called for greater national food resilience amid ongoing global disruptions. As a global pioneer in sustainable meat-free mycoprotein produced through fermentation, Quorn Foods possessed the technology and capacity to advance the UK’s self-sufficiency agenda. Yet financial constraints demanded caution. With rising raw material costs, weakening consumer demand, and growing geopolitical uncertainty, the company’s leaders confronted the tension between short-term cost control and long-term investment in innovation. Weighing the opportunities to supply public institutions with homegrown protein, they examined how biotechnology and operational efficiency might together redefine food security and resilience for a nation seeking stability in an increasingly volatile world
Reduzierte Schwingungen – Entkoppelte Antriebe machen Schluss mit dem Drehzahlsperrbereich
No full textInnomotics und die Technische Hochschule Nürnberg haben ein System zur Reduktion von Schwingungen in elektrischen Antrieben entwickelt. Damit lassen sich die Antriebe ohne Drehzahlsperrbereiche einsetzen und eine höhere Anlagenverfügbarkeit erreichen