Physics-informed generative neural networks for RF propagation prediction with application to indoor body perception

TL;DR

This paper introduces physics-informed generative neural networks, specifically a VAE model, to efficiently predict RF propagation effects caused by human motion, enabling real-time indoor sensing applications.

Contribution

It presents a novel VAE-based model that incorporates electromagnetic principles to simulate human-induced RF propagation effects, improving speed and accuracy over traditional methods.

Findings

Model accurately reproduces EM effects compared to classical tools

Enables real-time RF propagation prediction in indoor environments

Outperforms traditional EM simulation methods in speed

Abstract

Electromagnetic (EM) body models designed to predict Radio-Frequency (RF) propagation are time-consuming methods which prevent their adoption in strict real-time computational imaging problems, such as human body localization and sensing. Physics-informed Generative Neural Network (GNN) models have been recently proposed to reproduce EM effects, namely to simulate or reconstruct missing data or samples by incorporating relevant EM principles and constraints. The paper discusses a Variational Auto-Encoder (VAE) model which is trained to reproduce the effects of human motions on the EM field and incorporate EM body diffraction principles. Proposed physics-informed generative neural network models are verified against both classical diffraction-based EM tools and full-wave EM body simulations.