Deep learning denoising for EOG artifacts removal from EEG signals

TL;DR

This paper presents a deep learning approach using U-NET to effectively remove ocular artifacts from EEG signals by converting EEG data into images, achieving promising denoising accuracy.

Contribution

The study introduces a novel method converting EEG signals into images for U-NET based artifact removal, addressing the challenge of overlapping ocular artifacts in EEG analysis.

Findings

Achieved reliable reduction in mean square error between pure and contaminated EEGs.

Demonstrated the effectiveness of image-based deep learning for EEG artifact removal.

Proposed three different schemes for EEG denoising using U-NET.

Abstract

There are many sources of interference encountered in the electroencephalogram (EEG) recordings, specifically ocular, muscular, and cardiac artifacts. Rejection of EEG artifacts is an essential process in EEG analysis since such artifacts cause many problems in EEG signals analysis. One of the most challenging issues in EEG denoising processes is removing the ocular artifacts where Electrooculographic (EOG), and EEG signals have an overlap in both frequency and time domains. In this paper, we build and train a deep learning model to deal with this challenge and remove the ocular artifacts effectively. In the proposed scheme, we convert each EEG signal to an image to be fed to a U-NET model, which is a deep learning model usually used in image segmentation tasks. We proposed three different schemes and made our U-NET based models learn to purify contaminated EEG signals similar to the process used in the image segmentation process. The results confirm that one of our schemes can achieve a reliable and promising accuracy to reduce the Mean square error between the target signal (Pure EEGs) and the predicted signal (Purified EEGs).