Comparative experimental study on modeling the path loss of an UWB channel in a mine environment using MLP and RBF neural networks

Channel modeling is an important task when conceiving Ultra-Wideband communication systems (UWB). Having a precise and accurate model of the channel is necessary for designing telecommunication systems. Moreover, modeling the channel in an underground mine environment presents more difficulties and challenges to accomplish the task. The objective of this paper is to present a comparative experimental study on modeling an UWB channel in a mine environment using two types of artificial neural networks (ANN), Multilayer Perceptron (MLP) and Radial Basis Function (RBF), focusing on the change of the path loss attenuation as a function of distance and frequency.