A channel attention based MLP-Mixer network for motor imagery decoding with EEG

TL;DR

This paper introduces CAMLP-Net, a novel EEG motor imagery decoding model combining MLP-Mixer architecture with channel attention, effectively capturing global temporal and spatial features for improved classification accuracy.

Contribution

The paper proposes CAMLP-Net, integrating channel attention into MLP-Mixer for EEG MI decoding, addressing limitations of CNNs in perceiving global dependencies and channel importance.

Findings

CAMLP-Net outperforms existing algorithms on MI-2 dataset.

Effective capture of global temporal and spatial EEG features.

Enhanced classification accuracy in motor imagery decoding.

Abstract

Convolutional neural networks (CNNs) and their variants have been successfully applied to the electroencephalogram (EEG) based motor imagery (MI) decoding task. However, these CNN-based algorithms generally have limitations in perceiving global temporal dependencies of EEG signals. Besides, they also ignore the diverse contributions of different EEG channels to the classification task. To address such issues, a novel channel attention based MLP-Mixer network (CAMLP-Net) is proposed for EEG-based MI decoding. Specifically, the MLP-based architecture is applied in this network to capture the temporal and spatial information. The attention mechanism is further embedded into MLP-Mixer to adaptively exploit the importance of different EEG channels. Therefore, the proposed CAMLP-Net can effectively learn more global temporal and spatial information. The experimental results on the newly built MI-2 dataset indicate that our proposed CAMLP-Net achieves superior classification performance over all the compared algorithms.