Prediction of RF-EMF Exposure by Outdoor Drive Test Measurements

Abstract

In this paper, we exploit the artificial neural network (ANN) model for a spatial reconstruction of radio-frequency (RF) electromagnetic field (EMF) exposure in an outdoor urban environment. To this end, we have carried out a drive test measurement campaign covering a large part of Paris, along a route of approximately 65 Km. The electric (E) field strength has been recorded over a wide band ranging from 700 to 2700 MHz. From these measurement data, the E-field strength is extracted and computed for each frequency band of each telecommunication operator. First, the correlation between the E-fields at different frequency bands is computed and analyzed. The results show that a strong correlation of E-field levels is observed for bands belonging to the same operator. Then, we build ANN models with input data encompassing information related to distances to N neighboring base stations (BS), receiver location and time variation. We consider two different models. The first one is a fully connected ANN model, where we take into account the N nearest BSs ignoring the corresponding operator. The second one is a hybrid model, where we consider locally connected blocks with the N nearest BSs for each operator, followed by fully connected layers. The results show that the hybrid model achieves better performance than the fully connected one. Among N∈{3,5,7}, we found out that with N=3, the proposed hybrid model allows a good prediction of the exposure level while the maintaining acceptable complexity of the model.

Large-Area Monitoring of Radiofrequency Electromagnetic Field Exposure Levels from Mobile Phone Base Stations and Broadcast Transmission Towers by Car-Mounted Measurements around Tokyo

“…Measurements of RF EMF exposure levels in a wide area were also carried out in Japan and overseas by installing measuring instruments in a car [24][25][26][27][28][29][30]. Unlike spot measurements, the main advantage of measurements with a moving car is that RF EMF levels can be easily measured in a wide area.…”

“…In particular, in [24,26], the authors used a head phantom, which simulates the electric properties of a human head, to measure RF EMF levels in a situation similar to that during voice calls. In [25,[28][29][30], the authors measured RF EMF exposure levels from mobile phone base stations using an isotropic E-field probe. Estenberg and Augustsson reported their car-mounted measurements in Sweden at a frequency range of 30 MHz to 3 GHz using a three-axis antenna over a driving distance of 115 km [28].…”

“…Aerts et al investigated a method of predicting EMF exposure levels based on car-measured results [29]. Wang et al also studied the prediction using an artificial neural network (ANN) model with car measurements [30]. They carried out E-field measurements along a 65 km route in Paris to evaluate the prediction using the ANN.…”

Assessment of Electromagnetic Field Exposure on European Roads: A Comprehensive In Situ Measurement Campaign

“…Moreover, in [5], the exposure to EMFs of the car driver was assessed in a realistic V2V communication scenario. A limited number of works have considered EMF exposure in urban areas using outdoor drive test measurements [31,32].…”

Machine Learning Modeling for Radiofrequency Electromagnetic Fields (RF-EMF) Signals From mmWave 5G Signals

“…Bayesian optimization is a technique used to optimise the hyperparameters of machine learning models. Bayesian optimization has been used to optimise the hyperparameters of machine learning models used to model RF-EMF signals from 5G networks [20,21].…”