UWB Channel Classification Using Convolutional Neural Networks

In this paper, a novel convolutional neural network (CNN) algorithm for ultra-wideband (UWB) line-of-sight (LOS) and non-line-of-sight (NLOS) channel classification is proposed. Unlike the existing methods, which are based on machine learning algorithms and require suitable information/parameters for classification to be extracted for classification procedure, the proposed method uses deep learning approaches in which the model learns discriminating information for classification automatically by itself during the “training” phase. The performance of the proposed method is investigated in the IEEE 802.15.4a standard for UWB channels in indoor office LOS and NLOS environments.