Blind Detection of QAM with a complex discrete Hopfield network

A new algorithms based on discrete Hopfield network(DHNN) are proposed to blindly detect multi-value signals in this paper. Based on the relationship between received signals and projection operator of transmitted signals, the paper will construct new optimization performance functions to blindly detect signals, A quadratic programming performance functions with alphabet constraints is mapped to energy function of DHNN to blindly detect signals, and the globally optimal solution is mapped to minimum equilibrium point. A complex multi-value descrete Hopfield neural network (DHNN) is constructed in the paper. Simulation results show that the algorithm needs shorter received signals and show high speed to blindly detect multi-value signals in statistics insignificance case.