A fMRI Data Analysis Method using a Fast Infomax-Based ICA Algorithm

Independent Component Analysis (ICA) is a new technique in signal processing to extract statistically independent components from the observed multidimensional mixture of data. In this field, many algorithms have been proposed. In this paper, an infomax-based fast algorithm for ICA is proposed, using information maximum likelihood estimation with the Newton iterative algorithm. The algorithm is second-order convergent. We specifically applied the algorithm to functional magnetic resonance imaging (fMRI) data, and the result is positive. These results lend validity to the proposed method as providing a reasonable physiological explanation for the fMRI data.