PROJECT TITLE:

An Adaptive Fixed -point IVA Algorithm Applied to Multisubject Complex Valued FMRIdata - 2016

ABSTRACT:

Independent vector analysis (IVA) has exhibited nice potential for the group analysis of magnitude-only fMRI information, however has rarely been applied to native complex-valued fMRI information. We tend to propose an adaptive mounted-point IVA algorithm by taking under consideration the very noisy nature, giant variability of the supply element vector (SCV) distribution, and non-circularity of the advanced-valued fMRI information. The multivariate generalized Gaussian distribution (MGGD) is exploited to match the SCV distribution based mostly on nonlinearity, the shape parameter of MGGD is estimated using most likelihood estimation, and the nonlinearity is updated in the dominant SCV subspace to attain denoising goal. Still, the pseudo-covariance matrix is incorporated into the algorithm to represent the non-circularity. Experimental results from simulated and actual fMRI data demonstrate vital improvements of our algorithm over a complicated-valued IVA-G algorithm and several circular and noncircular mounted-point IVA variants.