AUTHOR=Xiong Wenjing , Ma Lin , Li Haifeng 

TITLE=A general dual-pathway network for EEG denoising

JOURNAL=Frontiers in Neuroscience

VOLUME=Volume 17 - 2023

YEAR=2024

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2023.1258024

DOI=10.3389/fnins.2023.1258024

ISSN=1662-453X

ABSTRACT=Scalp Electroencephalogram (EEG) analysis and interpretation are crucial for tracking and analyzing brain activity. The collected scalp EEG signals, however, are weak and frequently tainted with various sorts of artifacts. The models based on deep learning provided comparable performance with that of traditional techniques. However, current deep learning networks applied to scalp EEG noise reduction are large in scale and suffer from overfitting. Here, we propose a dual-pathway autoencoder modeling framework named DPAE for scalp EEG signal denoising and demonstrate the superiority of the model on MLP, CNN, and RNN, respectively. We validate the denoising performance on benchmark scalp EEG artifact datasets. The experimental results show that our model architecture not only significantly reduces the computational effort, but also outperforms existing deep learning denoising algorithms in RRMSE metrics, both in the time and frequency domains. The DPAE architecture does not require a priori knowledge of the noise distribution nor is it limited by the network layer structure, which is a general network model oriented towards blind source separation. This is a provisional file, not the final typeset article difficult to remove by simple filtering methods due to the irregularity of their movements and the frequency band overlap with the commonly used scalp EEG rhythm signals and need to be processed by suitable artifact removal algorithms.