Sonar target recognition using radial basis function networks

In this paper, we consider the problem of active sonar target classification based on the targets' material composition using a Radial Basis Function (RBF) network. Sonar target responses were measured under controlled laboratory conditions in a laboratory tank. Spherical targets of different material composition were used. An important task in the design of RBF networks is the appropriate choice of the RBF centers. In this paper, we propose a Karhunen-Loeve (KL) expansion based approach for centre selection. Results on the classification performance of the RBF network trained using the KL expansion based training pror dure are provided.