IngentaConnect Overcomplete Independent Component Analysis via Linearly Constrai...

Authors: Grosse-Wentrup, Moritz¹; Buss, Martin²

Source: The Journal of VLSI Signal Processing, Volume 48, Numbers 1-2, August 2007 , pp. 161-171(11)

Publisher: Springer

Abstract:

Independent Component Analysis (ICA) designed for complete bases is used in a variety of applications with great success, despite the often questionable assumption of having N sensors and M sources with N≥M. In this article, we assume a source model with more sources than sensors (M>N), only L<N of which are assumed to have a non-Gaussian distribution. We argue that this is a realistic source model for a variety of applications, and prove that for ICA algorithms designed for complete bases (i.e., algorithms assuming N=M) based on mutual information the mixture coefficients of the L non-Gaussian sources can be reconstructed in spite of the overcomplete mixture model. Further, it is shown that the reconstructed temporal activity of non-Gaussian sources is arbitrarily mixed with Gaussian sources. To obtain estimates of the temporal activity of the non-Gaussian sources, we use the correctly reconstructed mixture coefficients in conjunction with linearly constrained minimum variance spatial filtering. This results in estimates of the non-Gaussian sources minimizing the variance of the interference of other sources. The approach is applied to the denoising of Event Related Fields recorded by MEG, and it is shown that it performs superiorly to ordinary ICA.

Keywords: independent component analysis; blind source separation; overcomplete; underdetermined; EEG; MEG; denoising; event related fields; event related potentials; beamforming

Document Type: Research article

DOI: 10.1007/s11265-006-0028-3

Affiliations: 1: Email: moritz@tum.de 2: Email: mb@tum.de

The full text electronic article is available for purchase. You will be able to download the full text electronic article after payment.

$47.00 plus tax

Overcomplete Independent Component Analysis via Linearly Constrained Minimum Variance Spatial Filtering