A Spatial-Spectral and Temporal Dual Prototype Network for Motor Imagery Brain-Computer Interface

TL;DR

This paper introduces SST-DPN, a novel neural network architecture that combines spatial-spectral, temporal features, and dual prototype learning to improve motor imagery EEG decoding, especially with small datasets.

Contribution

The paper proposes a lightweight attention mechanism, a multi-scale variance pooling module, and dual prototype learning, advancing EEG decoding accuracy and generalization over existing models.

Findings

Achieved 84.11% accuracy on BCI4-2A dataset.

Achieved 86.65% accuracy on BCI4-2B dataset.

Validated generalization with 82.03% accuracy on smaller datasets.

Abstract

Motor imagery electroencephalogram (MI-EEG) decoding plays a crucial role in developing motor imagery brain-computer interfaces (MI-BCIs). However, decoding intentions from MI remains challenging due to the inherent complexity of EEG signals relative to the small-sample size. To address this issue, we propose a spatial-spectral and temporal dual prototype network (SST-DPN). First, we design a lightweight attention mechanism to uniformly model the spatial-spectral relationships across multiple EEG electrodes, enabling the extraction of powerful spatial-spectral features. Then, we develop a multi-scale variance pooling module tailored for EEG signals to capture long-term temporal features. This module is parameter-free and computationally efficient, offering clear advantages over the widely used transformer models. Furthermore, we introduce dual prototype learning to optimize the feature space distribution and training process, thereby improving the model's generalization ability on small-sample MI datasets. Our experimental results show that the SST-DPN outperforms state-of-the-art models with superior classification accuracy (84.11% for dataset BCI4-2A, 86.65% for dataset BCI4-2B). Additionally, we use the BCI3-4A dataset with fewer training data to further validate the generalization ability of the proposed SST-DPN. We also achieve superior performance with 82.03% classification accuracy. Benefiting from the lightweight parameters and superior decoding accuracy, our SST-DPN shows great potential for practical MI-BCI applications. The code is publicly available at https://github.com/hancan16/SST-DPN.