Direction of Arrival (DOA) Estimation Algorithm Based on the Radial Basis Function Neural Networks

Abstract

According to the problem of the large calculated quantity and unavailable of multiple sources tracking in real time in the traditional DOA estimation algorithm which is disabled when locating sources that are greater than the number of array elements number, a new direction of arrival estimation algorithm based on the radial basis function neural networks in smart antenna is proposed in this paper to solve the problem. The proposed neural multiple-source tracking (N-MUST) algorithm is based on architecture of a family of radial basis function neural networks (RBFNN) to perform both detection and direction of arrival estimation. The model of neural network in direction of arrival estimation is created and trained in this paper. Simulation results which compared the traditional algorithm and the new one are indicated that the direction of arrival (DOA) estimation algorithm based on the radial basis function neural networks implement multiple-source tracking exactly and fast.