Signal Processing Stack Exchange is a question and answer site for practitioners of the art and science of signal, image and video processing. It only takes a minute to sign up.
Sign up to join this community
From my knowledge about independent component analysis the number of channel or variables will not be affected by this algorithm and the number of independent components will be equal to number of variables. But when I tried to run FASTICA algorithm on EEG signal matrix which has 14 channels (or 14 variabls), the number of independent components was 9 not 14, which is confused me.
Does anyone have a clarification about this?
ICA can be seen as a dimension reduction technique similar to PCA. Although PCA consists of the eigenvectors of the covariance matrix i.e. second order statistics, ICA is not restricted and can contain higher order stat. The goal of ICA is to span the signal space in the most statistical independent vectors. So you might get a considerable dimension reduction.
