EOG Artifact Removal from Single and Multi-channel EEG Recordings through the combination of Long Short-Term Memory Networks and Independent Component Analysis

TL;DR

This paper introduces a novel method combining LSTM neural networks and ICA to effectively remove EOG artifacts from EEG signals without needing simultaneous EOG recordings, outperforming existing deep learning approaches.

Contribution

The study presents a new approach that estimates and removes EOG artifacts from EEG using LSTM networks combined with ICA, applicable to pre-recorded datasets without EOG recordings.

Findings

Proposed method outperforms two state-of-the-art deep learning techniques.

Achieved lower mean squared error and mean absolute error in artifact removal.

Validated on a dataset of 27 participants with superior results.

Abstract

Introduction: Electroencephalogram (EEG) signals have gained significant popularity in various applications due to their rich information content. However, these signals are prone to contamination from various sources of artifacts, notably the electrooculogram (EOG) artifacts caused by eye movements. The most effective approach to mitigate EOG artifacts involves recording EOG signals simultaneously with EEG and employing blind source separation techniques, such as independent component analysis (ICA). Nevertheless, the availability of EOG recordings is not always feasible, particularly in pre-recorded datasets. Objective: In this paper, we present a novel methodology that combines a long short-term memory (LSTM)-based neural network with ICA to address the challenge of EOG artifact removal from contaminated EEG signals. Approach: Our approach aims to accomplish two primary objectives: 1) estimate the horizontal and vertical EOG signals from the contaminated EEG data, and 2) employ ICA to eliminate the estimated EOG signals from the EEG, thereby producing an artifact-free EEG signal. Main results: To evaluate the performance of our proposed method, we conducted experiments on a publicly available dataset comprising recordings from 27 participants. We employed well-established metrics such as mean squared error, mean absolute error, and mean error to assess the quality of our artifact removal technique. Significance: Furthermore, we compared the performance of our approach with two state-of-the-art deep learning-based methods reported in the literature, demonstrating the superior performance of our proposed methodology.