Machine Learning-based Fast Fading Analysis in Industrial Environment

This thesis explores the application of machine learning to model fast fading effects in industrial wireless networks, specifically focusing on the Rice Factor (K-factor), a critical parameter in wireless communication. Fast fading, a result of multipath propagation, significantly affects the reliability and quality of signal transmission. The study employs machine learning models trained on a synthetically generated dataset to predict and analyze the impact of environmental variables on the K-factor, which is essential for optimizing wireless network design in industrial settings. By integrating empirical and deterministic modeling techniques with advanced machine learning algorithms, this research not only enhances the understanding of wave propagation dynamics but also contributes to the development of more robust wireless communication systems capable of adapting to the complex and variable conditions of industrial environments. Initial results have shown that machine learning can significantly improve the prediction accuracy of fast fading effects, supporting the creation of more efficient and reliable communication systems for industrial applications. The findings of this study are expected to have broad implications for the design and implementation of future wireless networks in similar settings.