Use of Machine Learning for the Estimation of Down- and Up-Link Field Exposure in Multi-Source Indoor WiFi Scenarios.

Gabriella Tognola,Serena Fiocchi,Paolo Ravazzani,Marta Bonato,Marta Parazzini,Silvia Gallucci,Luc Martens,Wout Joseph,David Plets,Emma Chiaramello

doi:10.1002/bem.22361

Abstract

A novel Machine Learning (ML) method based on Neural Networks (NN) is proposed to assess radio‐frequency (RF) exposure generated by WiFi sources in indoor scenarios. The aim was to build an NN capable of addressing the complexity and variability of real‐life exposure setups, including the effects of not only down‐link transmission access points (APs) but also up‐link transmission by different sources (e.g. laptop, printers, tablets, and smartphones). The NN was fed with easy to be found data, such as the position and type of WiFi sources (APs, clients, and other users) and the position and material characteristics (e.g. penetration loss) of walls. The NN model was assessed using an additional new layout, distinct from that one used to build and optimize the NN coefficients. The NN model achieved a remarkable field prediction accuracy across exposure conditions in both layouts, with a median prediction error of −0.4 to 0.6 dB and a root mean square error of 2.5−5.1 dB, compared with the target electric field estimated by a deterministic indoor network planner. The proposed approach performs well for the different layouts and is thus generally used to assess RF exposure in indoor scenarios. © 2021 The Authors. Bioelectromagnetics published by Wiley Periodicals LLC on behalf of Bioelectromagnetics Society.

Highlights

The use of Machine Learning (ML) to solve electromagnetic problems is a recent topic
We propose an ML method based on Neural Networks (NN) for the estimation of field exposure generated by multiple WiFi sources (2,400 MHz) in an indoor scenario
We investigated the feasibility and accuracy of an NN approach to model and estimate the field of exposure generated by WiFi sources in indoor scenarios

Summary

Introduction

The use of Machine Learning (ML) to solve electromagnetic problems is a recent topic. The estimation of field exposure in such a scenario is not trivial due to the complexity and variability of the setup, which should take into account the effects of multiple and diverse sources and the variability of the position of the sources in the room. Such exposure scenario cannot be modeled with deterministic methods only but requires the application of novel advanced statistical approaches (such as stochastic dosimetry and ML) capable of modeling the complexity and variability of the setup. A few recent studies demonstrated that stochastic dosimetry could be

Objectives

Methods

Results

Discussion

Conclusion