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

Kaiquan Shen, Ke Yu, Aishwarya Bandla, Yu Sun, Nitish V 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 publicationProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Pages6792-6795
Number of pages4
DOIs
StatePublished - 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

Other

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

Fingerprint

Blind source separation
Electroencephalography
Artifacts
Joints
Experiments
Datasets

ASJC Scopus subject areas

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

Cite this

Shen, K., Yu, K., Bandla, A., Sun, Y., Thakor, N. V., & Li, X. (2013). Multiple time-lag canonical correlation analysis for removing muscular artifacts in EEG. In Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS (pp. 6792-6795). [6611116] https://doi.org/10.1109/EMBC.2013.6611116

Multiple time-lag canonical correlation analysis for removing muscular artifacts in EEG. / Shen, Kaiquan; Yu, Ke; Bandla, Aishwarya; Sun, Yu; Thakor, Nitish V; Li, Xiaoping.

Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. 2013. p. 6792-6795 6611116.

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

Shen, K, Yu, K, Bandla, A, Sun, Y, Thakor, NV & Li, X 2013, Multiple time-lag canonical correlation analysis for removing muscular artifacts in EEG. in Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS., 6611116, pp. 6792-6795, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013, Osaka, Japan, 7/3/13. https://doi.org/10.1109/EMBC.2013.6611116
Shen K, Yu K, Bandla A, Sun Y, Thakor NV, Li X. Multiple time-lag canonical correlation analysis for removing muscular artifacts in EEG. In Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. 2013. p. 6792-6795. 6611116 https://doi.org/10.1109/EMBC.2013.6611116
Shen, Kaiquan ; Yu, Ke ; Bandla, Aishwarya ; Sun, Yu ; Thakor, Nitish V ; Li, Xiaoping. / Multiple time-lag canonical correlation analysis for removing muscular artifacts in EEG. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. 2013. pp. 6792-6795
@inproceedings{e121d37a05f84a8bb96e7ea8f3d80996,
title = "Multiple time-lag canonical correlation analysis for removing muscular artifacts in EEG",
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.",
author = "Kaiquan Shen and Ke Yu and Aishwarya Bandla and Yu Sun and Thakor, {Nitish V} and Xiaoping Li",
year = "2013",
doi = "10.1109/EMBC.2013.6611116",
language = "English (US)",
isbn = "9781457702167",
pages = "6792--6795",
booktitle = "Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS",

}

TY - GEN

T1 - Multiple time-lag canonical correlation analysis for removing muscular artifacts in EEG

AU - Shen, Kaiquan

AU - Yu, Ke

AU - Bandla, Aishwarya

AU - Sun, Yu

AU - Thakor, Nitish V

AU - Li, Xiaoping

PY - 2013

Y1 - 2013

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84886514601&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84886514601&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2013.6611116

DO - 10.1109/EMBC.2013.6611116

M3 - Conference contribution

C2 - 24111303

AN - SCOPUS:84886514601

SN - 9781457702167

SP - 6792

EP - 6795

BT - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

ER -