EEG Motor Imagery Classification Based on Multi-Perspective Attention-Based Multi-Scale Convolutional Neural Network

Electroencephalogram (EEG)-based motor imagery (MI) decoding is vital in brain–computer interface (BCI) systems. Although convolutional neural networks (CNNs) have achieved promising results, existing methods still face limitations in multi-scale feature extraction. Specifically, some CNN architectures focus primarily on local and global temporal features, while medium temporal information remains underexplored. Moreover, conventional feature integration strategies often overlook the distinct characteristics of features at different scales, limiting their effective utilization. To address these limitations, we propose a multi-perspective attention-based multi-scale CNN, called MPAMCNN. The model extracts local, medium, and global EEG features simultaneously by applying convolution kernels with different receptive fields. In addition, we incorporate different attention mechanisms into the corresponding branches to emphasize discriminative information and reduce feature redundancy before fusion. Extensive experiments on two benchmark datasets, BCI Competition IV-2a and IV-2b, demonstrate that MPAMCNN achieves classification accuracies of 79.71% and 88.02%, respectively, validating its efficacy for EEG motor imagery classification. Visualization analysis also reveals improved feature separability and clearer decision boundaries.