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

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.