Greater robustness of second order statistics than higher order statistics algorithms to distortions of the mixing matrix in blind source separation of human EEG: Implications for single-subject and group analyses.
Guillaume LioPhilippe BoulinguezPublished in: NeuroImage (2013)
Keyphrases
- blind source separation
- higher order statistics
- independent component analysis
- mixing matrix
- natural gradient
- source separation
- blind separation
- independent components
- signal processing
- principal component analysis
- non stationary
- random projections
- source signals
- machine learning
- factor analysis
- feature space
- support vector