Independent component analysis and source localization of ECoG data

Independent component analysis for unaveraged single-trial MEG data decomposition and single-dipole source localization

This paper presents a novel method for decomposing and localizing unaveraged single-trial magnetoencephalographic data based on the independent component analysis (ICA) approach associated with preand post-processing techniques. In the pre-processing stage, recorded single-trial raw data are 6rst decomposed into uncorrelated signals with the reduction of high-power additive noise. In the stage ...

Independent component analysis and blind source separation

Independent Component Analysis and Blind Source Separation

Blind source separation and independent component analysis

This special issue of Neurocomputing contains a selection of eleven papers about blind source separation and independent component analysis. The papers represent improved and extended versions of contributed papers presented at the ICA 2004 meeting held in Granada, Spain. A total of 15 manuscripts have been suggested for the special issue by the referees of the contributions submitted to the co...

Efficient source adaptivity in independent component analysis

A basic element in most independent component analysis (ICA) algorithms is the choice of a model for the score functions of the unknown sources. While this is usually based on approximations, for large data sets it is possible to achieve "source adaptivity" by directly estimating from the data the "true" score functions of the sources. We describe an efficient scheme for achieving this by exten...