Single-Channel Blind Signal Separation Based on Empirical Mode Decomposition and Fast Independent Component Analysis

摘要

In order to solve the blind signal separation (BSS) of the number of sensor observations less than the number of source signals, a single-channel method using empirical mode decomposition (EMD) and fast independent component analysis (FastICA) is proposed. Firstly, we get the intrinsic mode functions (IMF) by EMD, then the relevant IMFs are grouped together. Secondly, BSS can be achieved by FastICA. Finally, the simulation experiment of single-channel blind signal separation has been finished. The similar coefficients of separation signals obtained by this method and source signals are higher than 98%. The simulation experiment results have shown that this method can solve the problem of single-channel blind source separation. The effectiveness and feasibility of this method can also be verified by the simulation experiment results.