AMANet: a data-augmented multi-scale temporal attention convolutional network for motor imagery classification

TL;DR

This paper introduces AMANet, a deep learning model that improves motor imagery classification in brain-computer interfaces by using data augmentation and attention mechanisms.

Contribution

The novel contribution is a data-augmented multi-scale temporal attention convolutional network for motor imagery decoding.

Findings

AMANet achieved 84.06% and 85.09% accuracy on BCI Competition IV Datasets 2a and 2b.

It attained 95.48% accuracy on the High-Gamma dataset, outperforming baseline models.

The model effectively integrates spatial and temporal features using attention and convolution techniques.

Abstract

Motor imagery brain–computer interface (MI-BCI) has garnered considerable attention due to its potential for neural plasticity. However, the limited number of MI-EEG samples per subject and the susceptibility of features to noise and artifacts posed significant challenges for achieving high decoding performance. To address this problem, a Data-Augmented Multi-Scale Temporal Attention Convolutional Network (AMANet) was proposed. The network mainly consisted of four modules. First, the data augmentation module comprises three steps: sliding-window segmentation to increase sample size, Common Spatial Pattern (CSP) extraction of discriminative spatial features, and linear scaling to enhance network robustness. Then, multi-scale temporal convolution was incorporated to dynamically extract temporal and spatial features. Subsequently, the ECA attention mechanism was integrated to realize the adaptive adjustment of the weights of different channels. Finally, depthwise separable convolution was utilized to fully integrate and classify the deep extraction of temporal and spatial features. In 10-fold cross-validation, the results show that AMANet achieves classification accuracies of 84.06 and 85.09% on the BCI Competition IV Datasets 2a and 2b, respectively, significantly outperforming baseline models such as Incep-EEGNet. On the High-Gamma dataset, AMANet attains a classification accuracy of 95.48%. These results demonstrate the excellent performance of AMANet in motor imagery decoding tasks.

Figures