Experimental validation of a neural network direction finder

Abstract

This paper discusses an experimental neural network based smart antenna capable of performing direction finding. A cylindrical eight-element phased array antenna is used to collect complex signals radiated by two sources. Three direction of arrival (DOA) estimation algorithms are applied to the measured data, namely, the Fourier transform, the MUSIC algorithm and the radial basis function neural network (RBFNN) algorithm. Comparisons show the superior performance of the RBFNN and its ability to overcome many limitations of the conventional and other superresolution techniques, specifically by reducing the computational complexity and the ability to deal with highly correlated sources.