An Improved Algorithm for Blind Signal Separation Based on Maximum Likelihood Criterion and Quasi-Newton Method

In this article, we propose an improved algorithm of blind signal separation that jointly exploits the selection of rational nonlinear functions and quasi-Newton method. The proposed algorithm uses rational nonlinear functions in constructing the cost function, which have less computational complexity than the usual nonlinear functions such as hyperbolic tangent and Gaussian functions. We use quasi-Newton method to solve the solution procedure of the cost function based on maximum likelihood criterion which has good asymptotic performance. The source data for simulation are taken from generalized Gaussian distribution series, as well as realistic voice signal. Simulation results show superior performance of the proposed algorithm compared with classical ones such as JadeR and fastica.