A Deep Learning Approach to Multipath Component Detection in Power Delay Profiles

A Deep Learning Approach to Multipath Component Detection in Power Delay Profiles

Paper in proceedings (conference paper)

Power Delay Profile (PDP) plays a crucial role in wireless communications, providing information on multipath propagation and signal strength variations over time. Accurate detection of peaks within PDP is essential to identify dominant signal paths, which are critical for tasks such as channel esti mation, localization, and interference management. Traditional approaches to PDP analysis often struggle with noise, low resolution, and the inherent complexity of wireless environments. In this paper, we evaluate the application of traditional and modern deep learning neural networks to reconstruction-based anomaly detection to detect multipath components within the PDP. To further refine detection and robustness, a framework is proposed that combines autoencoders and Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering. To compare the performance of individual models, a relaxed F1 score strategy is defined. The experimental results show that the proposed framework with transformer-based autoencoder shows superior performance both in terms of reconstruction and anomaly detection.

Power Delay Profile (PDP) plays a crucial role in wireless communications, providing information on multipath propagation and signal strength variations over time. Accurate detection of peaks within PDP is essential to identify dominant signal paths, which are critical for tasks such as channel esti mation, localization, and interference management. Traditional approaches to PDP analysis often struggle with noise, low resolution, and the inherent complexity of wireless environments. In this paper, we evaluate the application of traditional and modern deep learning neural networks to reconstruction-based anomaly detection to detect multipath components within the PDP. To further refine detection and robustness, a framework is proposed that combines autoencoders and Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering. To compare the performance of individual models, a relaxed F1 score strategy is defined. The experimental results show that the proposed framework with transformer-based autoencoder shows superior performance both in terms of reconstruction and anomaly detection.

signal propagation, channel measurement, power delay profile, multipath components, peak detection, anomaly detection, machine learning, deep learning

signal propagation, channel measurement, power delay profile, multipath components, peak detection, anomaly detection, machine learning, deep learning

ZELENÝ, O.; ZÁVORKA, R.; PROKEŠ, A.; FRÝZA, T.; WOJTUŃ, J.; KELNER, J.; ZIÓŁKOWSKI, C.; CHANDRA, A.

24.05.2025

IEEE

Hnanice, Czech republic

979-8-3315-4447-8

Proceeding of the 35th International Conference Radioelektronika (RADIOELEKTRONIKA)

319

323

345

https://ieeexplore.ieee.org/document/11008404