Design of an automatic hybrid system for removal of eye-blink artifacts from EEG recordings

摘要

Electroencephalography (EEG) signals are frequently used in several areas, such as diagnosis of diseases and BCI applications. It is important to remove noise sources for applications using EEG. This paper introduces a hybrid system to automatically remove eye-blink artifacts from the EEG by combining several methods, such as Independent Component Analysis (ICA), Kurtosis, K-means, Modified Z-Score (MZS) and Adaptive Noise Canceller (ANC). In the proposed method, all EEG recordings are first decomposed, and then the components related to the eye-blink artifacts are detected using Kurtosis and K-means. The MZS is used to detect regions of only eye-blink artifacts in the independent component. The classical Least Mean Squares (LMS) and Normalized LMS (NLMS) algorithms are used in the proposed ANC system. To comprehensively test the performance of the proposed method, simulated and real-world EEG datasets are used. The proposed system is compared with ANC systems having different reference inputs, Zeroing-ICA, and OD-ICA. In the simulated EEG dataset, the obtained overall RE, CC, SAR, SNR, Sensitivity, Specificity, and Area Under Curve (AUC) values are 0.1505, 0.9875, 1.3863, 2.7708, 100%, 93.8%, and 0.9380, respectively. In the real-world dataset, the obtained overall RE, CC, SAR, and SNR values are 0.0252, 0.9916, 2.8439, and 5.6944, respectively. The results suggest that the proposed method exhibits better performance concerning the given criteria. The proposed system does not require an external electrode for measuring eye-blink artifacts. This distinct advantage provided ensures a comfortable measurement for patients during long-term EEG recordings.