Title :
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
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;
Journal_Title :
Biomedical Engineering, IEEE Transactions on
DOI :
10.1109/TBME.2006.879459
