General Non-unitary Constrained ICA and its Application to Complex-valued fMRI Data.

IEEE Trans Biomed Eng. 2014 Nov 20;

Authors: Rodriguez P, Anderson M, Calhoun V, Adali T

Abstract
Constrained independent component analysis (CICA) algorithms provide an effective way to introduce prior information into the complex- and real-valued ICA framework. The work in this area has focus on adding constraints to the objective function of algorithms that assume a unitary demixing matrix. The unitary condition is required in order to decouple- isolate-the constraints applied for each individual source. This assumption limits the optimization space and therefore the separation performance of C-ICA algorithms. We generalize the existing C-ICA framework by using a novel decoupling method that preserves the larger optimization space for the demixing matrix. This framework allows for the constraining of either the sources or the mixing coefficients. A constrained version of the non-unitary entropy bound minimization algorithm is introduced and applied to actual complex-valued fMRI data.We show that constraining the mixing parameters using a temporal constraint improves the estimation of the spatial map and timecourses of task-related components.

PMID: 25420255 [PubMed - as supplied by publisher]