Distinguishable spatial-spectral feature learning neural network framework for motor imagery-based brain–computer interface. (27th August 2021)

• Record Type: Journal Article
• Authors: Liu, Chang; Jin, Jing; Xu, Ren; Li, Shurui; Zuo, Cili; Sun, Hao; Wang, Xingyu; Cichocki, Andrzej
• Is Part Of: Journal of neural engineering. Volume 18:Number 4(2021)
• Publication Date: 2021-08-27
• Subjects: brain–computer interface -- motor imagery -- convolutional neural network -- squeeze-and-excitation -- common spatial pattern; Neurosciences -- Periodicals; Biomedical engineering -- Periodicals; 612.8
• DOI: 10.1088/1741-2552/ac1d36
• Languages: English
• ISSNs: 1741-2560

Abstract

Abstract: Objective. Spatial and spectral features extracted from electroencephalogram (EEG) are critical for the classification of motor imagery (MI) tasks. As prevalently used methods, the common spatial pattern (CSP) and filter bank CSP (FBCSP) can effectively extract spatial-spectral features from MI-related EEG. To further improve the separability of the CSP features, we proposed a distinguishable spatial-spectral feature learning neural network (DSSFLNN) framework for MI-based brain–computer interfaces (BCIs) in this study. Approach. The first step of the DSSFLNN framework was to extract FBCSP features from raw EEG signals. Then two squeeze-and-excitation modules were used to re-calibrate CSP features along the band-wise axis and the class-wise axis, respectively. Next, we used a parallel convolutional neural network module to learn distinguishable spatial-spectral features. Finally, the distinguishable spatial-spectral features were fed to a fully connected layer for classification. To verify the effectiveness of the proposed framework, we compared it with the state-of-the-art methods on BCI competition IV datasets 2a and 2b. Main results. The results showed that the DSSFLNN framework can achieve a mean Cohen's kappa value of 0.7 on two datasets, which outperformed the state-of-the-art methods. Moreover, two additional experiments were conducted and they proved that the combination of band-wise feature learning and class-wise feature learning can achieve significantly better performance than only using either one of them. Significance. The proposed DSSFLNN can effectively improve the decoding performance of MI-based BCIs.