As a blind source separation technique, independent component analysis (ICA) has many applications in functional magnetic resonance imaging (fMRI). Certain types of additional prior information, such as the sparsity, have seldom been added to the ICA algorithms as constraints. We proposed a SparseFastICA method by adding the source sparsity as a constraint to the FastICA algorithm to improve the performance of the FastICA. Here is the code of this SparseFastICA method. This code is modified based on Hugo et al.'s fpica code, please see more details from http://research.ics.aalto.fi/ica/fastica/
Mail to Author: [email protected]
If you use the simulation code, please cite:"Ruiyang Ge et al., Improved FastICA Algorithm in fMRI Data Analysis Using the Sparsity Property of the Sources, Journal of Neuroscience Methods, 2016;263:103-114 (https://www.sciencedirect.com/science/article/abs/pii/S0165027016000625)".