Ocular artifact suppression from EEG using ensemble empirical mode decomposition with principal component analysis. (August 2016)

• Record Type: Journal Article
• Authors: Patel, Rajesh; Sengottuvel, S.; Janawadkar, M.P.; Gireesan, K.; Radhakrishnan, T.S.; Mariyappa, N.
• Is Part Of: Computers & electrical engineering. Volume 54(2016)
• Page Start: 78
• Page End: 86
• Publication Date: 2016-08
• Subjects: Artifacts -- Electroencephalogram -- Ensemble empirical mode decomposition -- Principal component analysis -- Variance -- Skewness; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2015.08.019
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: A novel methodology for ocular artifact suppression in EEG data using EEMD with PCA. The proposed method eliminates the ocular artifacts from the measured EEG without using reference electrooculogram channel. The proposed method exhibits effective suppression of ocular artifact with low distortion compared to wavelet approach. Graphical abstract: Abstract: Signals associated with eye blinks (230–350 micro-volts) are orders of magnitude larger than electric potentials (7–20 micro-volts) generated on the scalp because of cortical activity. These and other such non-cortical biological artifacts spread across the scalp and contaminate the Electroencephalogram (EEG). We present here a novel approach for efficient detection and effective suppression of these artifacts using single channel EEG data by combining Ensemble Empirical Mode Decomposition (EEMD) along with Principal Component Analysis (PCA). We present a methodology for ocular artifact suppression, by performing EEMD on the contaminated EEG data segment to get the intrinsic mode functions (IMFs) and subsequent elimination of artifacts by automatic selection of particular principal components, which capture ocular artifact features after using PCA on IMFs.