Repository der Technischen Hochschule Ingolstadt
Not a member yet
4170 research outputs found
Sort by
Accelerated Real-Life (ARL) Testing and Characterization of Automotive LiDAR Sensors to facilitate the Development and Validation of Enhanced Sensor Models
No full textIn the realm of automated driving simulation and sensor modeling, the need for highly accurate sensor models is paramount for ensuring the reliability and safety of advanced driving assistance systems (ADAS). Hence, numerous works focus on the development of high-fidelity models of ADAS sensors, such as camera, Radar as well as modern LiDAR systems to simulate the sensor behavior in different driving scenarios, even under varying environmental conditions, considering for example adverse weather effects. However, aging effects of sensors, leading to suboptimal system performance, are mostly overlooked by current simulation techniques. This paper introduces a cutting-edge Hardware-in-the-Loop (HiL) test bench designed for the automated, accelerated aging and characterization of Automotive LiDAR sensors. The primary objective of this research is to address the aging effects of LiDAR sensors over the product life cycle, specifically focusing on aspects such as laser beam profile deterioration, output power reduction and intrinsic parameter drift, which are mostly neglected in current sensor models. By that, this proceeding research is intended to path the way, not only towards identifying and modeling respective degradation effects, but also to suggest quantitative model validation metrics
Efficient Cross-Architecture Binary Function Embeddings through Knowledge Distillation
No full textDeep learning has recently been shown to be effective in various tasks related to static binary analysis. One important analysis task is the binary function similarity problem: Given the binary code of two functions compiled with different compilers, different settings, and different processor architectures, the goal is to decide whether the functions are semantically equivalent (i.e. "similar") or not. This problem has numerous applications for embedded systems, for example plagiarism detection, validation of compliance restrictions with usable software licenses, more efficient reverse engineering of existing binary codebases, or vulnerability scanning by detecting known vulnerable functions. In this paper, we propose a novel training scheme for the popular transformer neural network architecture to learn function embeddings directly from instruction listings. Unlike existing approaches, our solution explicitly considers the cross-architecture scenario: we propose a training method to adapt the model to different instruction set architectures (ISA) without having to train a new model from scratch, which allows the model to also be used efficiently for embedded systems, where there are a variety of different processor architectures. We show that our solution achieves a similarity classification accuracy of 89.6% on a dataset consisting of several real-world open source software projects. Finally, we conduct extensive experiments to demonstrate the effectiveness of knowledge distillation in increasing the computational efficiency of the embedding model. We demonstrate a reduction in the number of parameters from 87M to 23M, while still maintaining a classification accuracy of 87.8%. Our code and artifacts are available as open source
Advanced Analytics in Smart Factories: Towards an actionable Taxonomy for Prescriptive Analytics Use Cases
No full textPrescriptive analytics use cases support in the decision-making process and focus on providing actionable guidance (e.g. in the smart factory) based on a set of problems and possible solutions. Smart factories represent the core of Industry 4.0 and can greatly benefit from the implementation of advanced analytics use cases. Prescriptive analytics enables operational excellence in smart factories by providing actionable insights and decisions to (autonomously) steer and govern areas of a factory. Still, a widespread adoption of principles of prescriptive analytics is not reached, due to the complexity and interconnectivity of different use cases. Additionally, a lack of methodological support for developing prescriptive analytics use cases is observed. We support the adoption and ideation of prescriptive analytics use cases by providing a taxonomy for prescriptive analytics use cases in smart factories for researchers. To make the findings from the taxonomy actionable, we develop a concept on how to transform existing analytics use cases or use case ideas into prescriptive analytics use cases to support practitioners. We focus on the transformation of existing analytics use cases into prescriptive analytics use cases to lower the barrier to entry for the development of prescriptive use cases. The findings are based on the taxonomy development method by Nickerson. Our evaluation is supported by expert interviews as well as focus groups
Services im Omnichannel Handel – Eine kundenorientierte Sichtweise
No full textDie fortschreitende Digitalisierung nahezu aller Lebensbereiche führt im Handel durch ein verändertes Kundenverhalten zu einer Anpassung des Serviceangebotes. Ergänzend den Aspekt des Omnichannel Handels weiter vorantreibend, bieten viele Handelsunternehmen
- Click & Collect,
- Click & Reserve,
- Instore Order,
- Home Delivery sowie
- Return Instore
als innovative Serviceleistungen an. In wieweit diese Services beim Kunden bekannt sind und welchen Nutzen der Kunde mit diesen verbindet, ist dem Handel nicht bekannt. Vielmehr glaubt dieser den hiermit verbundenen Kundennutzen zu kennen. Eine Studie der TH Ingolstadt hinterfragt mit Hilfe der KANO Methode diese Services und den damit verbundenen Kundennutzen.
Die kundenseitige Wahrnehmung und Einordnung der Services zeigt, dass seitens des Handels ein signifikanter Handlungsbedarf besteht, der u.a. die Kommunikation der Inhalte der Services sowie den mit der Nutzung der Services verbundenen Vorteilen für den Kunden beinhaltet, sofern der Handel eine suboptimale Verwendung seiner ohnehin knappen Ressourcen vermeiden will. Der Beitrag leistet damit einen nachhaltig wertvollen Beitrag zur Sicherstellung der Wettbewerbsfähigkeit von Handelsunternehmens
Auswirkungen der Digitalisierung auf die Nachhaltigkeit
No full textDie digitale Transformation verändert Geschäftsmodelle und -prozesse ebenso wie die Art und Weise der Kommunikation. Diese Entwicklung birgt bekanntermaßen sowohl Chancen als auch Risiken. In dieser Entwicklung nur die ökonomischen Auswirkungen zu suchen wäre nicht umfassend genug. Eine derartige Transformation wirkt sich gewiss auch auf gesellschaftliche Bereiche aus und hat gegebenenfalls auch einen ökologischen Kontext. Zu diesem Zweck haben die Autoren eine Analyse zur Auswirkung der Digitalisierung auf die Nachhaltigkeit vorgenommen. Ziel war dabei den Zusammenhang zwischen der Digitalisierung und dem
ökonomischen, ökologischen und sozialen Wohlstand herauszuarbeiten. Es wurden somit alle drei Säulen der Nachhaltigkeit untersucht. In die Untersuchung wurden 97 Länder einbezogen
