Seminar:Measurement-based Deep Learning Framework for EMF Exposure Mapping in Complex Urban Environments
时间：2025年5月27日 星期二 上午 10：00-11：00
地点：无线谷1319会议室
Abstract:
The prediction of the electric field (E-field) plays a crucial role in monitoring radiofrequency electromagnetic field (RF-EMF) exposure induced by cellular networks. In this work, a deep learning framework is proposed to predict E-field levels in complex urban environments. First, the measurement campaign and publicly accessible databases used to construct the training dataset are introduced, with a detailed explanation provided on how these datasets are formulated and integrated to enhance their suitability for Convolutional Neural Networks (CNNs)-based models. Then, we present the proposed model, ExposNet. Its network architecture and workflow are thoroughly explained. Two variations of the network structure are proposed, and extensive experimental analyses are conducted, demonstrating that ExposNet achieves good prediction accuracy with both configurations. Furthermore, the generalization capability of the model is evaluated. The overall results indicate that, despite being trained and tested on real-world measurements, the model performs well and achieves better accuracy compared to previous studies.
Bio:Shanshan WANG is currently an assistant professor in the Institut Polytechnique de Paris (Telecom Paris), with Chair C2M in department of Communications and electronics (COMELEC). She received the Ph.D. degree from L2S, Paris-Saclay University, France, in 2019. She received Master degree (with Distinction) from University of Bristol in 2014. From 2014 to 2015, she was a research engineer with the Toshiba Telecommunication Laboratory, Bristol, U.K. After PhD, she worked as postdoctoral researcher in the chair C2M in Télécom Paris, on the topic of EMF exposure mapping using AI. From 2023 to 2024, she was assistant professor in the ETIS lab, CY Cergy Paris University. She has participated several European Horizon projects, such as, 5GWireless (2015-2018), SEAWave (2022-2025), Goliat (2022-2027). She received Marie-Curie PhD fellowship in 2015 in CNRS France. Her research interests include EMF exposure characterization and AI-based prediction, stochastic geometry and system-level modeling of wireless networks, machine learning. She is also an expert in IEC and CENELEC TC106x.
