Searching over DOA parameter space via neural networks
Lin Sheng, Qinye Yin · 2002
In this paper, we propose a neural method to solve the orthogonality search problem arising in direction-of-arrival (DOA) estimation. The most important feature of this method hinges upon the fact that it can offer the potential of real-time solutions to the above problem by utilizing the fast relaxation properties of the Hopfield's linear programming neural network. Theoretical analysis and simulation results show that the performance of neural method is exactly equivalent to that of the standard MUSIC method or the Real Domain DOA estimation method (RD method). That is to say, the method proposed in this paper is a neural implementation of the MUSIC method and RD method.>