Independent component analysis of EEG signals

Abstract

Independent component analysis (ICA) technique is applied to the analysis of electroencephalographic (EEG) signal. The main task of ICA for a random vector includes searching for a linear transformation which minimizes the statistical dependence between the components involved in the signal. In practice, some artifacts problems limit the interpretation and analysis of clinical EEG signals since the rejected contaminated EEG segments results in an unacceptable data loss. In this contribution, ICA filters were trained based on the EEG data during these sessions were identified statistically independent source channels, which could then be further processed using other signal processing techniques. Finally, the applications of ICA to the multichannel EEG recordings from the human brain were investigated and compared. The experimental results indicated that the proposed ICA method for analyzing EEG significantly cancels the additive background noise and separate the mix signals.