Canonical Correlation Analysis Applied to Remove Muscle Artifacts From the Electroencephalogram

Author

Wim De Clercq ; Vergult, A. ; Vanrumste, B. ; Van Paesschen, W. ; Van Huffel, S.

Author_Institution

Dept. of Electr. Eng., Katholieke Univ., Leuven

Volume

53

Issue

12

fYear

2006

Firstpage

2583

Lastpage

2587

Abstract

The electroencephalogram (EEG) is often contaminated by muscle artifacts. In this paper, a new method for muscle artifact removal in EEG is presented, based on canonical correlation analysis (CCA) as a blind source separation (BSS) technique. This method is demonstrated on a synthetic data set. The method outperformed a low-pass filter with different cutoff frequencies and an independent component analysis (ICA)-based technique for muscle artifact removal. In addition, the method is applied on a real ictal EEG recording contaminated with muscle artifacts. The proposed method removed successfully the muscle artifact without altering the recorded underlying ictal activity

Keywords

blind source separation; correlation methods; electroencephalography; medical signal processing; muscle; EEG; blind source separation; canonical correlation analysis; electroencephalogram; independent component analysis; low-pass filter; muscle artifact removal; Autocorrelation; Blind source separation; Brain; Cutoff frequency; Electroencephalography; Independent component analysis; Low pass filters; Muscles; Signal analysis; Source separation; Blind source separation; EEG; canonical correlation analysis; muscle artifact removal; Action Potentials; Algorithms; Artifacts; Brain; Diagnosis, Computer-Assisted; Electroencephalography; Electromyography; Epilepsy; Humans; Muscle Contraction; Muscle, Skeletal; Reproducibility of Results; Sensitivity and Specificity; Statistics as Topic;

fLanguage

English

Journal_Title

Biomedical Engineering, IEEE Transactions on

Publisher

ieee

ISSN

0018-9294

Type

jour

DOI

10.1109/TBME.2006.879459

Filename

4015602