Blind Source Separation by ICA for EEG Multiple Sources Localization.

In this paper we describe that Independent Component Analysis (ICA) method for computing the brain signals of unknown source parameters for the inverse problem. We apply Blind Source Separation (BSS) based on ICA for separating multichannel EEG evoked by multiple dipoles into temporally independent stationary sources. For every independent source, we manage to know electrode potentials evoked by every dipole separately by the projection of independent activation maps back onto the electrode arrays. Then for every set of electrode potentials, we need to perform a source localization procedure, and search only for one dipole, thus dramatically reducing the search complexity. In the paper, it is explored that the possibility of applying ICA for EEG multiple dipoles localization when the data are corrupted by additive noise. Before ICA processing, we apply a method to estimate the dipoles number beforehand and reduce dimensionality that can reduce the ICA complexity and improve the unmixing accuracy. [ABSTRACT FROM AUTHOR]