A novel classification method for EEG-based motor imagery with narrow band spatial filters and deep convolutional neural network

• Published in: Cognitive neurodynamics Vol. 16; no. 2; pp. 379 - 389
• Main Authors: Xu, Senwei, Zhu, Li, Kong, Wanzeng, Peng, Yong, Hu, Hua, Cao, Jianting
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer Netherlands 01.04.2022; Springer Nature B.V
• Subjects: Accuracy; Algorithms; Artificial Intelligence; Artificial neural networks; Biochemistry; Biomedical and Life Sciences; Biomedicine; Classification; Cognitive Psychology; Competition; Computer Science; Data collection; Datasets; EEG; Electrodes; Electroencephalography; Experiments; Filter banks; Imagery; Mental task performance; Methods; Neural networks; Neurosciences; Research Article; Spatial filtering; Virtual reality; Wavelet transforms; Motor imagery; Feature fusion; Deep Convolutional Neural Network (DCNN); Narrow band
• ISSN: 1871-4080; 1871-4099
• DOI: 10.1007/s11571-021-09721-x

The Common Spatial Pattern (CSP) algorithm is the most widely used method for decoding Electroencephalography (EEG) signals from motor imagery (MI) paradigm. However, due to the inter-subject variability, the CSP algorithm heavily relies on the selection of filter bands and extensive analytical processing time required to build an effective model, which has been a challenge in current research. In this paper, we propose a narrow filter bank CSP (NFBCSP) algorithm, which automatically determines the optimal narrow band for two-class motor imagery by band search tree, and a high-performance classification model dedicated to each subject can be obtained in a short time for online processing or further offline analysis. The optimal narrow band is combined with the CSP algorithm to extract the dynamic features in the EEG signals. For the multi-class motor imagery task, it is first transformed into multiple One-Versus-Rest (OVR) tasks and determines the corresponding optimal narrow bands. After extracting the features of each optimal narrow band separately, the Deep Convolutional Neural Network (DCNN) is used for the fusion of band features and classification of multi-class motor imagery. Finally, we verified our method using two different motor imagery datasets, the BCI-VR dataset with two classes of motor imagery and the BCI Competition IV dataset 2a with four classes of motor imagery. The experimental results show that the proposed method achieves an average classification accuracy of 86.43% for the two-class motor imagery task, and 76.87% for the four-class motor imagery task, which outperforms other recent methods.