EEG-DCNet: A Fast and Accurate MI-EEG Dilated CNN Classification Method

TL;DR

EEG-DCNet is a novel multi-scale dilated CNN model that improves the accuracy and efficiency of motor imagery EEG classification by capturing multi-scale features and utilizing attention mechanisms, outperforming existing methods.

Contribution

The paper introduces EEG-DCNet, a multi-scale atrous CNN with attention and sliding window, achieving superior classification accuracy and efficiency in MI-EEG tasks.

Findings

Outperforms state-of-the-art methods in accuracy and Kappa scores.

Requires fewer parameters, enhancing training efficiency.

Effective in capturing multi-scale EEG features.

Abstract

The electroencephalography (EEG)-based motor imagery (MI) classification is a critical and challenging task in brain-computer interface (BCI) technology, which plays a significant role in assisting patients with functional impairments to regain mobility. We present a novel multi-scale atrous convolutional neural network (CNN) model called EEG-dilated convolution network (DCNet) to enhance the accuracy and efficiency of the EEG-based MI classification tasks. We incorporate the $1\times1$ convolutional layer and utilize the multi-branch parallel atrous convolutional architecture in EEG-DCNet to capture the highly nonlinear characteristics and multi-scale features of the EEG signals. Moreover, we utilize the sliding window to enhance the temporal consistency and utilize the attension mechanism to improve the accuracy of recognizing user intentions. The experimental results (via the BCI-IV-2a ,BCI-IV-2b and the High-Gamma datasets) show that EEG-DCNet outperforms existing state-of-the-art (SOTA) approaches in terms of classification accuracy and Kappa scores. Furthermore, since EEG-DCNet requires less number of parameters, the training efficiency and memory consumption are also improved. The experiment code is open-sourced at \href{https://github.com/Kanyooo/EEG-DCNet}{here}.