Blind MPSK signal detection based on complex-valued multistate continuous Hopfield neural networks
Ruan Xiu-kai · Journal of Chongqing University of Posts and Telecommunications · 2012
An optimization performance function is constructed to detect M-ary phase shift keying(MPSK) signals blindly and directly.To use complex-valued Hopfield neural network(CVHNN) for solving above optimization performance function,a novel complex-valued multistate continuous activation function is given to improve network performance,and a new energy function is proposed to prove the stability of CVHNN with the given activation function.Computer simulation results show that the proposed method has faster convergence for the blind detection of MPSK signals than classical algorithms such as subspace algorithm and so on.