Algorithm for nonlinear blind source separation based on generalized eigenvalue decomposition and kernel feature space
Gao Ying, Yao Zhen-jian · Systems engineering and electronics · 2006
A linear blind source separation algorithm based on generalized eigenvalue decomposition is presented.Then a nonlinear blind source separation algorithm is proposed by extending the linear blind source separation algorithm to the nonlinear domain.The received mixing signals are first mapped to high-dimensional kernel feature space,and an orthonormal basis of the kernel feature space is constructed.Next,in the kernel feature space,the mixing signals are parameterized by the orthonormal basis.Finally,the linear blind source separation algorithm based on signal variability is applied to the parameterized mixing signals.The proposed algorithm has a closed-form solution and simple computation,and is characterized by high accuracy,and robustness.Simulation results illustrate the efficiency and good performance of the algorithm.