Blind Separation of Noisy Pseudoperiodic Chaotic Signals

Abstract

The blind source separation (BSS) algorithm based on nonlinear phase-space reconstruction, nonorthogonal joint approximate diagonalization (JAD) of several time-delayed covariance matrices and nonlinear noise reduction is investigated by applying it to noisy mixed pseudoperiodic chaotic Rossler signals and Mackey-Glass signals. The time-delayed covariance matrices are estimated corresponding to the data matrix of first embedding dimension and data matrix of the every another embedding dimension. Simulation results show that algorithm gives a good performance in the separation and denoising of mixed noisy signals in the presence of a white Gaussian noise or stationary colored noise up to SNR=(5–10) dB and can be applied to separation signals, that have non-zero autocorrelation function for a non-zero time lag, i. e. when analysis based on the second-order statistics (SOS) is applicable. Ill 2, bibl. 12 (in English; summaries in English, Russian and Lithuanian).