EEG signal Extraction Utilizing Null Space Approach
Luay Yassin Taha, Esam Abdel‐Raheem · 2019
The aim of this paper is to apply the Null space algorithm to extract Electroencephalography (EEG) signals and remove the Electrocardiogram (ECG) artifact. First, the EEG signals are modelled using the linear mixture model. Then, the Null space algorithm is applied to extract all EEG signals. Simulation results, using synthesized EEG data, show that the model is successfully extracting all the unknown EEG signals and the readiness potential, as well. Results, using real EEG data, show that the model is successfully extracting the unknown EEG signal and removing the ECG artifacts. The algorithm is tested using the correlation and the signal-to-noise ratio extraction metrics, and the results show considerable improvements as compared to fast independent component analysis (FastICA) and parallel linear predictor (PLP) algorithms.