Robust Direction of Arrival (DOA) estimation using RBF neural network in impulsive noise environment

Abstract

The DOA problem in impulsive noise environment is approached as a mapping which can be modeled using a radial-basis function neural network (RBFNN). To improve the robustness, the input pairs are preprocessed by Fractional Low-Order Statistics (FLOS) technique. The performance of this network is compared to that of the FLOM-MUSIC for both uncorrelated and correlated source. Numerical results show the good performance of the RBFNN-based DOA estimation. © Springer-Verlag Berlin Heidelberg 2005.