Multiple time-lag canonical correlation analysis for removing muscular artifacts in EEG

Kaiquan Shen, Ke Yu, Aishwarya Bandla, Yu Sun, Nitish Thakor, Xiaoping Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this work, a new approach for joint blind source separation (BSS) of datasets at multiple time lags using canonical correlation analysis (CCA) is developed for removing muscular artifacts from electroencephalogram (EEG) recordings. The proposed approach jointly extracts sources from each dataset in a decreasing order of between-set source correlations. Muscular artifact sources that typically have lowest between-set correlations can then be removed. It is shown theoretically that the proposed use of CCA on multiple datasets at multiple time lags achieves better BSS under a more relaxed condition and hence offers better performance in removing muscular artifacts than the conventional CCA. This is further demonstrated by experiments on real EEG data.

Original languageEnglish (US)
Title of host publication2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013
Pages6792-6795
Number of pages4
DOIs
StatePublished - Oct 31 2013
Externally publishedYes
Event2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013 - Osaka, Japan
Duration: Jul 3 2013Jul 7 2013

Publication series

NameProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
ISSN (Print)1557-170X

Other

Other2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013
CountryJapan
CityOsaka
Period7/3/137/7/13

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Fingerprint Dive into the research topics of 'Multiple time-lag canonical correlation analysis for removing muscular artifacts in EEG'. Together they form a unique fingerprint.

Cite this