Modifying the spatially-constrained ICA for efficient removal of artifacts from EEG data

Muhammad Tahir Akhtar, Christopher J. James, Wataru Mitsuhashi

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

4 Citations (Scopus)

Abstract

This paper concerns artifact removal from multichannel EEG data. It has already been demonstrated that independent component analysis (ICA) can be an effective and applicable method for EEG de-noising. The goal of this paper is to propose a framework, based on ICA and wavelet denoising (WD), to improve the pre-processing of EEG signals. In particular we employ the concept of spatially constrained ICA (SCICA) to extract artifact-only independent components (ICs) from the given EEG data, use WD to remove any cerebral activity from extracted artifacts, and Anally project back the artifacts to be subtracted from EEG signals to get clean EEG data. The main advantage of the proposed approach is faster computation, as all ICs are not identified. The computer experiments are carried out, which demonstrate the effectiveness of the proposed approach in removing focal artifacts that can be well separated by SCICA.

Original languageEnglish
Title of host publication2010 4th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2010
DOIs
Publication statusPublished - 2010
Event4th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2010 - Chengdu, China
Duration: Jun 18 2010Jun 20 2010

Publication series

Name2010 4th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2010

Conference

Conference4th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2010
CountryChina
CityChengdu
Period6/18/106/20/10

Fingerprint

Independent component analysis
Electroencephalography
Artifacts
Wavelet Analysis
Processing
Experiments

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics

Cite this

Akhtar, M. T., James, C. J., & Mitsuhashi, W. (2010). Modifying the spatially-constrained ICA for efficient removal of artifacts from EEG data. In 2010 4th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2010 [5515306] (2010 4th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2010). https://doi.org/10.1109/ICBBE.2010.5515306

Modifying the spatially-constrained ICA for efficient removal of artifacts from EEG data. / Akhtar, Muhammad Tahir; James, Christopher J.; Mitsuhashi, Wataru.

2010 4th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2010. 2010. 5515306 (2010 4th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2010).

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

Akhtar, MT, James, CJ & Mitsuhashi, W 2010, Modifying the spatially-constrained ICA for efficient removal of artifacts from EEG data. in 2010 4th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2010., 5515306, 2010 4th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2010, 4th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2010, Chengdu, China, 6/18/10. https://doi.org/10.1109/ICBBE.2010.5515306
Akhtar MT, James CJ, Mitsuhashi W. Modifying the spatially-constrained ICA for efficient removal of artifacts from EEG data. In 2010 4th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2010. 2010. 5515306. (2010 4th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2010). https://doi.org/10.1109/ICBBE.2010.5515306
Akhtar, Muhammad Tahir ; James, Christopher J. ; Mitsuhashi, Wataru. / Modifying the spatially-constrained ICA for efficient removal of artifacts from EEG data. 2010 4th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2010. 2010. (2010 4th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2010).
@inproceedings{0bd96a210ab24537bae8cbfce7dc1dd0,
title = "Modifying the spatially-constrained ICA for efficient removal of artifacts from EEG data",
abstract = "This paper concerns artifact removal from multichannel EEG data. It has already been demonstrated that independent component analysis (ICA) can be an effective and applicable method for EEG de-noising. The goal of this paper is to propose a framework, based on ICA and wavelet denoising (WD), to improve the pre-processing of EEG signals. In particular we employ the concept of spatially constrained ICA (SCICA) to extract artifact-only independent components (ICs) from the given EEG data, use WD to remove any cerebral activity from extracted artifacts, and Anally project back the artifacts to be subtracted from EEG signals to get clean EEG data. The main advantage of the proposed approach is faster computation, as all ICs are not identified. The computer experiments are carried out, which demonstrate the effectiveness of the proposed approach in removing focal artifacts that can be well separated by SCICA.",
author = "Akhtar, {Muhammad Tahir} and James, {Christopher J.} and Wataru Mitsuhashi",
year = "2010",
doi = "10.1109/ICBBE.2010.5515306",
language = "English",
isbn = "9781424447138",
series = "2010 4th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2010",
booktitle = "2010 4th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2010",

}

TY - GEN

T1 - Modifying the spatially-constrained ICA for efficient removal of artifacts from EEG data

AU - Akhtar, Muhammad Tahir

AU - James, Christopher J.

AU - Mitsuhashi, Wataru

PY - 2010

Y1 - 2010

N2 - This paper concerns artifact removal from multichannel EEG data. It has already been demonstrated that independent component analysis (ICA) can be an effective and applicable method for EEG de-noising. The goal of this paper is to propose a framework, based on ICA and wavelet denoising (WD), to improve the pre-processing of EEG signals. In particular we employ the concept of spatially constrained ICA (SCICA) to extract artifact-only independent components (ICs) from the given EEG data, use WD to remove any cerebral activity from extracted artifacts, and Anally project back the artifacts to be subtracted from EEG signals to get clean EEG data. The main advantage of the proposed approach is faster computation, as all ICs are not identified. The computer experiments are carried out, which demonstrate the effectiveness of the proposed approach in removing focal artifacts that can be well separated by SCICA.

AB - This paper concerns artifact removal from multichannel EEG data. It has already been demonstrated that independent component analysis (ICA) can be an effective and applicable method for EEG de-noising. The goal of this paper is to propose a framework, based on ICA and wavelet denoising (WD), to improve the pre-processing of EEG signals. In particular we employ the concept of spatially constrained ICA (SCICA) to extract artifact-only independent components (ICs) from the given EEG data, use WD to remove any cerebral activity from extracted artifacts, and Anally project back the artifacts to be subtracted from EEG signals to get clean EEG data. The main advantage of the proposed approach is faster computation, as all ICs are not identified. The computer experiments are carried out, which demonstrate the effectiveness of the proposed approach in removing focal artifacts that can be well separated by SCICA.

UR - http://www.scopus.com/inward/record.url?scp=77956146728&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956146728&partnerID=8YFLogxK

U2 - 10.1109/ICBBE.2010.5515306

DO - 10.1109/ICBBE.2010.5515306

M3 - Conference contribution

AN - SCOPUS:77956146728

SN - 9781424447138

T3 - 2010 4th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2010

BT - 2010 4th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2010

ER -