Automated eye blink artefact removal from EEG using support vector machine and autoencoder

Abstract

Electroencephalogram (EEG) is a highly sensitive instrument and is frequently corrupted with eye blinks. Methods based on adaptive noise cancellation (ANC) and discrete wavelet transform (DWT) have been used as a standard technique for removal of eye blink artefacts. However, these methods often require visual inspection and appropriate thresholding for identifying and removing artefactual components from the EEG signal. The proposed work describes an automated windowed method with a window size of 0.45 s that is slid forward and fed to a support vector machine (SVM) classifier for identification of artefacts, after the identification of artefacts, it is fed to an autoencoder for correction of artefacts. The proposed method is evaluated on the data collected from the project entitled 'Analysis of Brain Waves and Development of Intelligent Model for Silent Speech Recognition'. From the results it is observed that the proposed method performs better in identifying and removing artefactual components from EEG data than existing wavelet and ANC based methods. The proposed method does not require the application of independent component analysis (ICA) before processing and can be applied to multiple channels in parallel. Recently Sreeja et al. [17] proposed two sparsity-based techniques, namely morphological component analysis (MCA) and K-singular value decomposition (K-SVD). The MCA-based method depends on the choice of appropriate dictionaries (basis

Automatic EEG eyeblink artefact identification and removal technique using independent component analysis in combination with support vector machines and denoising autoencoder

“…How truly the artefacts were removed without disturbing the original EEG signal, is tested through simulated EEG signals in this study. Four performance metrics suggested by [22,41] are used in this work as described below.…”

“…The CC measures the degree of similarity between two signals [41]. In EEG artefact removal, high CC value reflects good performance in eyeblink removal.…”

“…The MI is a quantity that measures how much the Y * draws relevant information from its Y [41]. It is expressed as…”

“…The proposed method differs from the previous work described in [41]. In the previous method [41] a windowed method was adopted to identify artefacts and then filter it using an autoencoder.…”

“…After the correction, inverse ICA operation is performed to obtain the denoised EEG signal. The novelty of selecting the proposed methodology over the previous work, as described in [41], are as given below:…”