Please use this identifier to cite or link to this item: https://doi.org/10.1109/ICSMC.2008.4811434
Title: Automatic identification and removal of artifacts in EEG using a probabilistic multi-class SVM approach with error correction
Authors: Shao, S.-Y. 
Shen, K.-Q. 
Ong, C.-J. 
Li, X.-P. 
Wilder-Smith, E.P.V.
Keywords: Artifact removal
Electroencephalogram
Error correction
Support vector machine
Issue Date: 2008
Source: Shao, S.-Y.,Shen, K.-Q.,Ong, C.-J.,Li, X.-P.,Wilder-Smith, E.P.V. (2008). Automatic identification and removal of artifacts in EEG using a probabilistic multi-class SVM approach with error correction. Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics : 1134-1139. ScholarBank@NUS Repository. https://doi.org/10.1109/ICSMC.2008.4811434
Abstract: A novel electroencephalogram (EEG) artifact removal method is presented in this paper. The proposed method combines a probabilistic multi-class Support Vector Machine (SVM) and an error correction algorithm for component classification, where i) the probabilistic multi-class SVM is modified to properly handle the unbalanced nature of component classification and ii) the error correction algorithm is used to accommodate the structural information of the learning problem. The proposed component classifier was tested on real-life EEG data and it significantly outperformed the standard SVM used in the literature. A qualitative evaluation on the reconstructed EEG shows that the proposed artifact removal method greatly reduced the amount of artifacts while well preserving brain activities in almost all EEG epochs. © 2008 IEEE.
Source Title: Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
URI: http://scholarbank.nus.edu.sg/handle/10635/73208
ISSN: 1062922X
DOI: 10.1109/ICSMC.2008.4811434
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

4
checked on Dec 13, 2017

Page view(s)

13
checked on Dec 9, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.