A neural network using special filters to classify imagined movements from brain signals

SincMSNet achieves average accuracies of 80.70% in four-class and 71.50% in two-class inter-session analyses of motor imagery EEG data.

• SincMSNet is a convolutional neural network designed to improve the decoding of motor imagery EEG signals, addressing individual variability.
• The model employs a Sinc filter to extract specific frequency band information and mixed-depth convolution for multi-scale temporal analysis.
• It incorporates a spatial convolutional block for spatial feature extraction and a temporal log-variance block for classification features.
• In single-session analysis, SincMSNet achieves average accuracies of 84.69% for four-class and 76.99% for two-class datasets.
• Visualizations indicate SincMSNet's capacity to extract subject-specific frequency band information from EEG signals.

Simplified