Independent component analysis of electroencephalographic signals

Abstract

This paper discusses the independent component analysis (ICA) technique and its applications to the analysis of Electroencephalographic (EEG) signal. ICA of a random vector consists of searching for a linear transformation that minimizes the statistical dependence between its components. For the EEG interpretation and analysis, there are some artifacts problems when rejecting contaminated EEG segments results in an unacceptable data loss. The ICA filters trained on EEG data collected during these sessions identified statistically independent source channels which could then be further processed using event-related potential (ERP), event-related spectral perturbation (ERSP), and other signal processing techniques. In this paper some applications of ICA are described and its application to the EEG recordings from the human brain is demonstrated.