A neural network for direction finding in array processing
Jerry Zhijian Yang, Qiang Wu, James P. Reilly · 1992
In array processing, the direction-of-arrival (DOA) estimation problem can be solved by the nonlinear least-squares method. However, this method has two problems: the complexity of computation and the global convergence of the numerical algorithm. A simple neural network structure is presented to reduce the computational complexity, and a simulated annealing structure is proposed in order to solve the global convergence problem.>