Repository der Technischen Hochschule Ingolstadt
Not a member yet
4170 research outputs found
Sort by
Machine Learning Models for Soil Parameter Prediction Based on Satellite, Weather, Clay and Yield Data
Get PDFEfficient nutrient management and precise fertilization are essential for advancing modern agriculture, particularly in regions striving to optimize crop yields sustainably. The AgroLens project endeavors to address this challenge by develop ing Machine Learning (ML)-based methodologies to predict soil nutrient levels without reliance on laboratory tests. By leveraging state of the art techniques, the project lays a foundation for acionable insights to improve agricultural productivity in resource-constrained areas, such as Africa. The approach begins with the development of a robust European model using the LUCAS Soil dataset and Sentinel-2 satellite imagery to estimate key soil properties, including phosphorus, potassium, nitrogen, and pH levels. This model is then enhanced by integrating supplementary features, such as weather data, harvest rates, and Clay AI-generated embeddings. This report details the methodological framework, data preprocessing strategies, and ML pipelines employed in this project. Advanced algorithms, including Random Forests, Extreme Gradient Boosting (XGBoost), and Fully Connected Neural Networks (FCNN), were implemented and finetuned for precise nutrient prediction. Results showcase robust model performance, with root mean square error values meeting stringent accuracy thresholds. By establishing a reproducible and scalable pipeline for soil nutrient prediction, this research paves the way for transformative agricultural applications, including precision fertilization and improved resource allocation in underresourced regions like Africa
Economics of Polymer Electrolyte Membrane Fuel Cells
Get PDFHydrogen is considered a key component of the renewable energy transition for the 21st century, with potential applications using fuel cells in the transportation sector, decentralized heating systems, and energy storage. However, the conversion from fossil fuels to hydrogen implies comprehensive research to address technological and socio economic challenges, enabling its widespread adoption. This paper discusses the economics of fuel cells. A cost analysis of the polymer electrolyte membrane fuel cells (PEMFC) is performed, and current market data and developments are presented
Benchmarking CNN Architectures for Tool Classification: Evaluating CNN Performance on a Unique Dataset Generated by Novel Image Acquisition System
Get PDFIn this study, we introduce the ToolSurface-144 dataset, which is presented here for the first time. It comprises four subsets – Full R, Full S, Top R, and Top S – each containing 144 tool classes captured under varying illumination conditions and fields of view. A newly developed, patented imaging approach was employed to acquire the data. It is compared with conventional diffuse ring illumination to assess its effectiveness in evaluating state-of-the-art convolutional neural networks. This enabled a more targeted investigation of the role of global shape characteristics such as silhouettes versus localized features like the tool face, cutting edges, and delicate geometrical structures under different training strategies. In this study, we evaluate six state-of-the-art convolutional neural networks—AlexNet, DenseNet161, EfficientNet-B0, ResNet152, ResNet50, and VGG16—using three training strategies: fine-tuning, freezing of pre-trained layers, and training from scratch. The results show that EfficientNet-B0 consistently achieved the highest classification accuracy in nearly all experiments and data sets. Especially using the fine-tuning training strategy, the model achieved 99% accuracy in tool classification. ResNet50 benefited greatly from fine-tuning and freezing, achieving a significant increase in performance compared to training from scratch. In contrast, ResNet152, AlexNet, and VGG16 consistently showed poor classification performance, indicating difficulties regarding learning and generalisation. The results show that diffuse illumination and complete tool views provide the best classification conditions, while restricted image sections with homogeneous illumination negatively affect model performance. Among the evaluated training strategies, fine-tuning proved the most efficient training method for developing CNN models for tool classification
Empathic vehicle design: Use cases and design directions from two workshops
No full textEmpathic vehicles are expected to improve user experience in automated vehicles and to help increase user acceptance of technology. However, little is known about potential real-world implementations and designs using empathic interfaces in vehicles with higher levels of automation. Given advances in affect detection and emotion mitigation, we conducted two workshops (N1 =24, N2 = 22, Ntotal = 46) on the design of empathic vehicles and their potential utility in a variety of applications. This paper recapitulates key opportunities in the design and application of empathetic interfaces in automated vehicles which emerged from the two workshops hosted at the ACM AutoUI conferences
Towards a Multivariate Scoring Metric for the Evaluation of Simulation Scenarios in Automated Driving
No full textPerformance Improvements in Cooperative Downloading: Encoding and Strategies for Heterogeneous Vehicular Networks
No full text
Provably Safe Reinforcement Learning via Action Projection Using Reachability Analysis and Polynomial Zonotopes
No full textWhile reinforcement learning produces very promising results for many applications, its main disadvantage is the lack of safety guarantees, which prevents its use in safety-critical systems. In this work, we address this issue by a safety shield for nonlinear continuous systems that solve reach-avoid tasks. Our safety shield prevents applying potentially unsafe actions from a reinforcement learning agent by projecting the proposed action to the closest safe action. This approach is called action projection and is implemented via mixed-integer optimization. The safety constraints for action projection are obtained by applying parameterized reachability analysis using polynomial zonotopes, which enables to accurately capture the nonlinear effects of the actions on the system. In contrast to other state-of-the-art approaches for action projection, our safety shield can efficiently handle input constraints and dynamic obstacles, eases incorporation of the spatial robot dimensions into the safety constraints, guarantees robust safety despite process noise and measurement errors, and is well suited for high-dimensional systems, as we demonstrate on several challenging benchmark systems