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

Sep 8, 2023Journal of neural engineering

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

AI simplified

Circadian Biology on OpenScience ↗PubMed ↗DOI ↗

Abstract

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.

AI simplified

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.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.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.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. Objective. Approach. Main results. Significance.

Full Text

Full text is available at the source.

View full text (HTML) ↗View full text (PDF) ↗

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

Abstract

Full Text

You found one interesting study. We’ll send the next 7.

what lands in your inbox each week:

Recent issues from the circadian biology brief

Abstract

Full Text

Related papers

You found one interesting study. We’ll send the next 7.

what lands in your inbox each week:

Recent issues from the circadian biology brief