Three-dimensional convolutional neural network based on spatial-spectral feature pictures learning for decoding motor imagery electroencephalography signal.
10.7507/1001-5515.202407038
- Author:
Xuejian WU
1
;
Yaqi CHU
1
;
Xingang ZHAO
1
;
Yiwen ZHAO
1
Author Information
1. State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, P. R. China.
- Publication Type:Journal Article
- Keywords:
Brain-computer interface;
Feature selection;
Motor imagery electroencephalography;
Signal decoding;
Spatial-spectral feature picture
- MeSH:
Electroencephalography/methods*;
Humans;
Brain-Computer Interfaces;
Neural Networks, Computer;
Imagination/physiology*;
Signal Processing, Computer-Assisted;
Brain/physiology*;
Convolutional Neural Networks
- From:
Journal of Biomedical Engineering
2024;41(6):1145-1152
- CountryChina
- Language:Chinese
-
Abstract:
The brain-computer interface (BCI) based on motor imagery electroencephalography (EEG) shows great potential in neurorehabilitation due to its non-invasive nature and ease of use. However, motor imagery EEG signals have low signal-to-noise ratios and spatiotemporal resolutions, leading to low decoding recognition rates with traditional neural networks. To address this, this paper proposed a three-dimensional (3D) convolutional neural network (CNN) method that learns spatial-frequency feature maps, using Welch method to calculate the power spectrum of EEG frequency bands, converted time-series EEG into a brain topographical map with spatial-frequency information. A 3D network with one-dimensional and two-dimensional convolutional layers was designed to effectively learn these features. Comparative experiments demonstrated that the average decoding recognition rate reached 86.89%, outperforming traditional methods and validating the effectiveness of this approach in motor imagery EEG decoding.
