A novel EEG artifact removal algorithm based on an advanced attention mechanism

Abstract EEG is widely applied in emotion recognition, brain disease detection, and other fields due to its high temporal resolution and non-invasiveness. However, artifact removal remains a crucial issue in EEG signal processing. Recently, with the rapid development of deep learning, there has been...

Full description

Saved in:
Bibliographic Details
Main Authors: Rui Jiang, Shen Tong, Jiawei Wu, Haowei Hu, Ran Zhang, Heng Wang, Yan Zhao, Weixin Zhu, Shuyan Li, Xiao Zhang
Format: Article
Language:English
Published: Nature Portfolio 2025-06-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-98653-1
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Abstract EEG is widely applied in emotion recognition, brain disease detection, and other fields due to its high temporal resolution and non-invasiveness. However, artifact removal remains a crucial issue in EEG signal processing. Recently, with the rapid development of deep learning, there has been a significant transformation in the methods of EEG artifact removal. Nonetheless, existing research still exhibits some limitations: (1) insufficient capability to remove unknown artifacts; (2) inability to adapt to tasks where artifact removal needs to be applied to the overall input of multi-channel EEG data. Therefore, this study proposes CLEnet by integrating dual-scale CNN (Convolutional Neural Networks) and LSTM (Long Short-Term Memory), and incorporating an improved EMA-1D (One-Dimensional Efficient Multi-Scale Attention Mechanism). CLEnet can extract the morphological features and temporal features of EEG, thereby separating EEG from artifacts. We conducted experiments on three datasets, and the results showed that CLEnet performed best. Specifically, in the task of removing artifacts from multi-channel EEG data containing unknown artifacts, CLEnet shows improvements of 2.45% and 2.65% in SNR(signal-to-noise ratio) and CC(average correlation coefficient). Moreover, RRMSE t (relative root mean square error in the temporal domain) and RRMSE f (relative root mean square error in the frequency domain) decrease by 6.94% and 3.30%.
ISSN:2045-2322