ICA was applied on the entire collection of raw ERP signals y(t) = [y 1(t),…,y L(t)]T, where L indicated the number of channels on the scalp. The goal of ICA is to find an unmixing matrix W that initially produces the ERP signals y(t) based on statistically independent sources s(t) in the matrix form u = Wy → s. In contrast to correlation-based transformations such as principal component analysis (PCA), ICA reduces the statistical dependencies of the signals and attempts to make them as independent as possible. This technique has shown great promise for analyzing EEG recordings [16, 34–36]. There are many ways for learning W. We used the extended Infomax algorithm which minimizes the mutual information among the data projections in order to achieve the independence.
