Employing spatially constrained ICA and wavelet denoising, for automatic removal of artifacts from multichannel EEG data

Muhammad Tahir Akhtar, Wataru Mitsuhashi, Christopher J. James

Research output: Contribution to journalArticle

107 Citations (Scopus)

Abstract

Detecting artifacts produced in electroencephalographic (EEG) data by muscle activity, eye blinks and electrical noise, etc., is an important problem in EEG signal processing research. These artifacts must be corrected before further analysis because it renders subsequent analysis very error-prone. One solution is to reject the data segment if artifact is present during the observation interval, however, the rejected data segment could contain important information masked by the artifact. The independent component analysis (ICA) can be an effective and applicable method for EEG denoising. 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 concept of the spatially constrained ICA (SCICA) to extract artifact-only independent components (ICs) from the given EEG data, use WD to remove any cerebral activity from the extracted-artifacts ICs, and finally 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 it is not necessary to identify all ICs. Computer experiments are carried out, which demonstrate effectiveness of the proposed approach in removing focal artifacts that can be well separated by SCICA.

Original languageEnglish
Pages (from-to)401-416
Number of pages16
JournalSignal Processing
Volume92
Issue number2
DOIs
Publication statusPublished - Feb 2012

Fingerprint

Independent component analysis
Muscle
Signal processing
Processing
Experiments

Keywords

  • Artifact removal
  • EEG
  • Independent component analysis (ICA)
  • Spatially constrained ICA
  • Wavelet denoising

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Employing spatially constrained ICA and wavelet denoising, for automatic removal of artifacts from multichannel EEG data. / Akhtar, Muhammad Tahir; Mitsuhashi, Wataru; James, Christopher J.

In: Signal Processing, Vol. 92, No. 2, 02.2012, p. 401-416.

Research output: Contribution to journalArticle

@article{aee13fa89c994ec0a93df9d1981991b6,
title = "Employing spatially constrained ICA and wavelet denoising, for automatic removal of artifacts from multichannel EEG data",
abstract = "Detecting artifacts produced in electroencephalographic (EEG) data by muscle activity, eye blinks and electrical noise, etc., is an important problem in EEG signal processing research. These artifacts must be corrected before further analysis because it renders subsequent analysis very error-prone. One solution is to reject the data segment if artifact is present during the observation interval, however, the rejected data segment could contain important information masked by the artifact. The independent component analysis (ICA) can be an effective and applicable method for EEG denoising. 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 concept of the spatially constrained ICA (SCICA) to extract artifact-only independent components (ICs) from the given EEG data, use WD to remove any cerebral activity from the extracted-artifacts ICs, and finally 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 it is not necessary to identify all ICs. Computer experiments are carried out, which demonstrate effectiveness of the proposed approach in removing focal artifacts that can be well separated by SCICA.",
keywords = "Artifact removal, EEG, Independent component analysis (ICA), Spatially constrained ICA, Wavelet denoising",
author = "Akhtar, {Muhammad Tahir} and Wataru Mitsuhashi and James, {Christopher J.}",
year = "2012",
month = "2",
doi = "10.1016/j.sigpro.2011.08.005",
language = "English",
volume = "92",
pages = "401--416",
journal = "Signal Processing",
issn = "0165-1684",
publisher = "Elsevier",
number = "2",

}

TY - JOUR

T1 - Employing spatially constrained ICA and wavelet denoising, for automatic removal of artifacts from multichannel EEG data

AU - Akhtar, Muhammad Tahir

AU - Mitsuhashi, Wataru

AU - James, Christopher J.

PY - 2012/2

Y1 - 2012/2

N2 - Detecting artifacts produced in electroencephalographic (EEG) data by muscle activity, eye blinks and electrical noise, etc., is an important problem in EEG signal processing research. These artifacts must be corrected before further analysis because it renders subsequent analysis very error-prone. One solution is to reject the data segment if artifact is present during the observation interval, however, the rejected data segment could contain important information masked by the artifact. The independent component analysis (ICA) can be an effective and applicable method for EEG denoising. 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 concept of the spatially constrained ICA (SCICA) to extract artifact-only independent components (ICs) from the given EEG data, use WD to remove any cerebral activity from the extracted-artifacts ICs, and finally 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 it is not necessary to identify all ICs. Computer experiments are carried out, which demonstrate effectiveness of the proposed approach in removing focal artifacts that can be well separated by SCICA.

AB - Detecting artifacts produced in electroencephalographic (EEG) data by muscle activity, eye blinks and electrical noise, etc., is an important problem in EEG signal processing research. These artifacts must be corrected before further analysis because it renders subsequent analysis very error-prone. One solution is to reject the data segment if artifact is present during the observation interval, however, the rejected data segment could contain important information masked by the artifact. The independent component analysis (ICA) can be an effective and applicable method for EEG denoising. 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 concept of the spatially constrained ICA (SCICA) to extract artifact-only independent components (ICs) from the given EEG data, use WD to remove any cerebral activity from the extracted-artifacts ICs, and finally 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 it is not necessary to identify all ICs. Computer experiments are carried out, which demonstrate effectiveness of the proposed approach in removing focal artifacts that can be well separated by SCICA.

KW - Artifact removal

KW - EEG

KW - Independent component analysis (ICA)

KW - Spatially constrained ICA

KW - Wavelet denoising

UR - http://www.scopus.com/inward/record.url?scp=80054735370&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80054735370&partnerID=8YFLogxK

U2 - 10.1016/j.sigpro.2011.08.005

DO - 10.1016/j.sigpro.2011.08.005

M3 - Article

AN - SCOPUS:80054735370

VL - 92

SP - 401

EP - 416

JO - Signal Processing

JF - Signal Processing

SN - 0165-1684

IS - 2

ER -