Title :
From principal to independent component analysis of brain signals
Author_Institution :
GMD-FIRST, Berlin
Abstract :
The purpose of this paper is to introduce the attendee/reader of the special session on component analysis and brain signals to, or refresh the concepts of the classical principal component analysis (PCA) and the more recent independent component analysis (ICA). Some motivations for their use in the context of electromagnetic brain signal processing are given. An illustrative example in event related studies is as well provided.
Keywords :
bioelectric potentials; electroencephalography; magnetoencephalography; medical signal processing; principal component analysis; EEG; MEG; artifact removal; brain signals; electromagnetic brain signal processing; essential data structures; event related studies; independent component analysis; medical diagnostic techniques; multivariate data handling; Biological neural networks; Covariance matrix; Eigenvalues and eigenfunctions; Electroencephalography; Independent component analysis; Magnetic analysis; Magnetoencephalography; Principal component analysis; Signal analysis; Statistical distributions;
Conference_Titel :
Engineering in Medicine and Biology Society, 2001. Proceedings of the 23rd Annual International Conference of the IEEE
Print_ISBN :
0-7803-7211-5
DOI :
10.1109/IEMBS.2001.1020615
