REMOVAL OF OCULAR ARTIFACTS FROM EEG DATA USING RECURSIVE LEAST SQUARES INDEPENDENT COMPONENT ANALYSIS (RLS-ICA) ALGORITHM
The electroencephalogram (EEG), the record of the neuronal electrical activity, is a good indicator of abnormality in the nervous central system. The occurrence of electrical artifacts generated by eye movements and blink contamination produce a signal known as Electrooculogram (EOG). Different methods about automatic removal of EEG artifacts using independent component analysis (ICA) are developed. ICA allows separating components in complex signals with the possibility of discriminating between artifacts and brain waves. This method is widely used as a tool to eliminate artifacts with the possibility of combining it with other methods such as Bayesian classifier or high-order statistics. Adaptive filtering applied to EEG data components obtained by ICA for eliminating EOG contamination. The principal difference with other methods for ocular artifacts removal is the use of ICA components as reference inputs corresponding to noise that we want to eliminate. The adaptive filtering works under the ICA domain using the EEG reference electrodes localized close to the eyes. A method to eliminate eye movement artifacts based on Independent Component Analysis (ICA) and Recursive Least Squares (RLS) is designed using Matlab. The ICA-RLS algorithm combines the effective ICA capacity of separating artifacts from brain waves, together with the online interference cancellation achieved by adaptive filtering. The method uses separate electrodes localized close to the eyes, that register vertical and horizontal eye movements, to extract a reference signal. Each reference input is first projected into the ICA domain and then the interference is estimated using the RLS algorithm. This interference estimation is subtracted from the EEG components in the ICA domain. Results from Matlab(2015b) simulation data demonstrate that this approach is suitable for eliminating artifacts caused by eye movements, and the principles of this method can be extended to certain other sources of artifacts as well.
Reference Paper: Automatic Removal of Ocular Artifacts from EEG Data using Adaptive Filtering and Independent Component Analysis
Author’s Name: Carlos Guerrero-Mosquera, and Angel Navia Vazquez
Source: EURASIP
Year:2009
Request source code for academic purpose, fill REQUEST FORM or contact +91 7904568456 by WhatsApp or info@verilogcourseteam.com, fee applicable.
SIMULATION VIDEO DEMO
