Motor imagery electroencephalogram classification based on sparse spatiotemporal decomposition and channel attention.
10.7507/1001-5515.202111031
- Author:
Hongli LI
1
;
Feichao YIN
1
;
Ronghua ZHANG
2
;
Xin MA
3
;
Hongyu CHEN
1
Author Information
1. School of Control Science and Engineering, Tiangong University, Tianjin 300387, P. R. China.
2. School of Artificial Intelligence, Tiangong University, Tianjin 300387, P. R. China.
3. School of Electronics and Information Engineering, Tiangong University, Tianjin 300387, P. R. China.
- Publication Type:Journal Article
- Keywords:
Attention mechanism;
Brain-computer interface;
Deep learning;
Motor imagery;
Sparse decomposition
- MeSH:
Algorithms;
Brain-Computer Interfaces;
Electroencephalography/methods*;
Humans;
Imagery, Psychotherapy;
Imagination
- From:
Journal of Biomedical Engineering
2022;39(3):488-497
- CountryChina
- Language:Chinese
-
Abstract:
Motor imagery electroencephalogram (EEG) signals are non-stationary time series with a low signal-to-noise ratio. Therefore, the single-channel EEG analysis method is difficult to effectively describe the interaction characteristics between multi-channel signals. This paper proposed a deep learning network model based on the multi-channel attention mechanism. First, we performed time-frequency sparse decomposition on the pre-processed data, which enhanced the difference of time-frequency characteristics of EEG signals. Then we used the attention module to map the data in time and space so that the model could make full use of the data characteristics of different channels of EEG signals. Finally, the improved time-convolution network (TCN) was used for feature fusion and classification. The BCI competition IV-2a data set was used to verify the proposed algorithm. The experimental results showed that the proposed algorithm could effectively improve the classification accuracy of motor imagination EEG signals, which achieved an average accuracy of 83.03% for 9 subjects. Compared with the existing methods, the classification accuracy of EEG signals was improved. With the enhanced difference features between different motor imagery EEG data, the proposed method is important for the study of improving classifier performance.
