UWB target classification using SVM

Ultra-Wideband (UWB) radar signals are characterized for having both high frequency carrier and high bandwidth. This makes the scattered field from the targets when irradiated with UWB pulses highly dependent of the composition and shape of the target. Our goal is to classify objects by their composition from their scattered responses. In this paper, we propose to use a Support Vector Machine (SVM) to solve the problem for distinct dielectric materials and sphere elements. For a problem considering M different materials and R radii, we compare performance of three different SVM configurations. The first one considers the general problem where each class corresponds to a different material. In this approach, each class is trained with data corresponding to all R radii. On a second approach, we classify by both radii and material. This gives a larger problem to solve, where the number of classes of the SVM is M × R + 1. Finally, a third approach considers a cascade of SVMs where the first layer consists of a SVM for R + 1 classes, each class associated with one radius, while the second layer is composed of R different SVMs, each corresponding to a different radius, that classify between the M materials. Monte Carlo experiments are run to compare performance among the different proposed schemes. We analyze the results considering both classification and algorithmic complexity.