Movement-Related EEG Decomposition Using Independent Component Analysis

This contribution describes one possible approach for EEG decomposition into movement-related and non-movement-related components with the help of independent components analysis (ICA). The application is targeted to the brain-computer interface (BCI) EEG preprocessing. Our previous work [1] has shown that it is possible to decompose EEG into movement-related and non-movement-related ICs. The selection of only movement related ICs might lead to BCI EEG classification score increasing. The real number of the independent sources in the brain is an important parameter of the whole process. In [1] we used principal component analysis (PCA) for number of the independent sources estimation. However, PCA estimates only the number of uncorrelated and not independent components ignoring the higher-order signal statistics. In this work we use another approach -selection of highly correlated ICs from several ICA runs.