SincMSNet: a Sinc filter convolutional neural network for EEG motor imagery classification

Objective. Motor imagery (MI) is widely used in brain-computer interfaces (BCIs). However, the decode of MI-EEG using convolutional neural networks (CNNs) remains a challenge due to individual variability. Approach. We propose a fully end-to-end CNN called SincMSNet to address this issue. SincMSNet employs the Sinc filter to extract subject-specific frequency band information and utilizes mixed-depth convolution to extract multi-scale temporal information for each band. It then applies a spatial convolutional block to extract spatial features and uses a temporal log-variance block to obtain classification features. The model of SincMSNet is trained under the joint supervision of cross-entropy and center loss to achieve inter-class separable and intra-class compact representations of EEG signals. Main results. We evaluated the performance of SincMSNet on the BCIC-IV-2a (four-class) and OpenBMI (two-class) datasets. SincMSNet achieves impressive results, surpassing benchmark methods. In four-class and two-class inter-session analysis, it achieves average accuracies of 80.70% and 71.50% respectively. In four-class and two-class single-session analysis, it achieves average accuracies of 84.69% and 76.99% respectively. Additionally, visualizations of the learned band-pass filter bands by Sinc filters demonstrate the network's ability to extract subject-specific frequency band information from EEG. Significance. This study highlights the potential of SincMSNet in improving the performance of MI-EEG decoding and designing more robust MI-BCIs. The source code for SincMSNet can be found at: https://github.com/Want2Vanish/SincMSNet.