Physics-informed generative neural networks for RF propagation prediction with application to indoor body perception
This work addresses the need for faster computational imaging in human body localization and sensing, though it appears incremental as it builds on existing physics-informed GNN approaches.
The paper tackles the problem of slow electromagnetic body models for real-time RF propagation prediction in indoor body perception by proposing a physics-informed generative neural network, achieving verification against classical diffraction-based tools and full-wave simulations.
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.