Geometric subspace methods and time-delay embedding for EEG artifact removal and classification

Charles W Anderson; James N Knight; Tim O'Connor; Michael J Kirby; Artem Sokolov

doi:10.1109/TNSRE.2006.875527

Geometric subspace methods and time-delay embedding for EEG artifact removal and classification

IEEE Trans Neural Syst Rehabil Eng. 2006 Jun;14(2):142-6. doi: 10.1109/TNSRE.2006.875527.

Authors

Charles W Anderson¹, James N Knight, Tim O'Connor, Michael J Kirby, Artem Sokolov

Affiliation

¹ Department of Computer Science, Colorado State University, Fort Collins, CO 80523, USA. anderson@cs.colostate.edu

PMID: 16792280
DOI: 10.1109/TNSRE.2006.875527

Abstract

Generalized singular-value decomposition is used to separate multichannel electroencephalogram (EEG) into components found by optimizing a signal-to-noise quotient. These components are used to filter out artifacts. Short-time principal components analysis of time-delay embedded EEG is used to represent windowed EEG data to classify EEG according to which mental task is being performed. Examples are presented of the filtering of various artifacts and results are shown of classification of EEG from five mental tasks using committees of decision trees.

Publication types

Evaluation Study
Research Support, U.S. Gov't, Non-P.H.S.

MeSH terms

Algorithms*
Artifacts*
Brain / physiology*
Communication Aids for Disabled
Electroencephalography / methods*
Evoked Potentials / physiology*
Humans
Man-Machine Systems
Pattern Recognition, Automated / methods*
User-Computer Interface*