Please wait a minute...
Journal of Integrative Neuroscience  2020, Vol. 19 Issue (2): 259-272    DOI: 10.31083/j.jin.2020.02.1269
Original Research Previous articles | Next articles
Decoding spectro-temporal representation for motor imagery recognition using ECoG-based brain-computer interfaces
Fangzhou Xu1, *(), Wenfeng Zheng2, Dongri Shan1, Qi Yuan3, Weidong Zhou4
1School of Electronic and Information Engineering (Department of Physics), Qilu University of Technology (Shandong Academy of Sciences), Jinan, Shandong Province, 250353, P. R. China
2School of Electrical Engineering and Automation, Qilu University of Technology (Shandong Academy of Sciences), Jinan, Shandong Province, 250353, P. R. China
3Shandong Province Key Laboratory of Medical Physics and Image Processing Technology, School of Physics and Electronics, Shandong Normal University, Jinan, Shandong Province, 250358, P. R. China
4School of Microelectronics, Shandong University, Jinan, Shandong Province, 250100, P. R. China
Download:  PDF(18267KB)  ( 405 ) Full text   ( 12 )
Export:  BibTeX | EndNote (RIS)      
Abstract  
One of the challenges in brain-computer interface systems is obtaining motor imagery recognition from brain activities. Brain-signal decoding robustness and system performance improvement during the motor imagery process are two of the essential issues in brain-computer interface research. In conventional approaches, ineffective decoding of features and high complexity of algorithms often lead to unsatisfactory performance. A novel method for the recognition of motor imagery tasks is developed based on employing a modified S-transforms for spectro-temporal representation to characterize the behavior of electrocorticogram activities. A classifier is trained by using a support vector machine, and an optimized wrapper approach is applied to guide selection to implement the representation selection obtained. A channel selection algorithm optimizes the wrapper approach by adding a cross-validation step, which effectively improves the classification performance. The modified S-transform can accurately capture event-related desynchronization/event-related synchronization phenomena and can effectively locate sensorimotor rhythm information. The optimized wrapper approach used in this scheme can effectively reduce the feature dimension and improve algorithm efficiency. The method is evaluated on a public electrocorticogram dataset with a recognition accuracy of 98% and an information transfer rate of 0.8586 bit/trial. To verify the effect of the channel selection, both electrocorticogram and electroencephalogram data are experimentally analyzed. Furthermore, the computational efficiency of this scheme demonstrates its potential for online brain-computer interface systems in future cognitive tasks.
Key words:  Brain-computer interface      motor imagery      signal processing      electrocorticogram      optimized wrapper approach      neural coding      evoked potentials     
Submitted:  25 December 2019      Revised:  08 May 2020      Accepted:  21 May 2020      Published:  30 June 2020     
Fund: 
61701270/National Natural Science Foundation of China
61701279/National Natural Science Foundation of China
81472159/National Natural Science Foundation of China
81871508/National Natural Science Foundation of China
61773246/National Natural Science Foundation of China
2019KJN010/Program for Youth Innovative Research Team in University of Shandong Province, China
2019TSLH0315/Key Program for Research and Development of Shandong Province, China (Key Project for Science and Technology Innovation, Department and City Cooperation)
Jinan Program for Development of Science and Technology
Jinan Program for Leaders of Science and Technology
TSHW201502038/Taishan Scholar Program of Shandong Province of China
*Corresponding Author(s):  Fangzhou Xu     E-mail:  xfz@qlu.edu.cn

Cite this article: 

Fangzhou Xu, Wenfeng Zheng, Dongri Shan, Qi Yuan, Weidong Zhou. Decoding spectro-temporal representation for motor imagery recognition using ECoG-based brain-computer interfaces. Journal of Integrative Neuroscience, 2020, 19(2): 259-272.

URL: 

https://jin.imrpress.com/EN/10.31083/j.jin.2020.02.1269     OR     https://jin.imrpress.com/EN/Y2020/V19/I2/259

[1] Yeong-Wook Kim, Juan-Xiu Cui, Sheng-Lan Jin, Sung-Ju Jee, Min-Kyun Sohn. Attentional and neurophysiologic effects of repetitive transcranial magnetic stimulation[J]. Journal of Integrative Neuroscience, 2020, 19(3): 397-404.
[2] Hao Wang, Jin Wu, Ke Fang, Lei Cai, Lai-Shan Wang, Zhen-Dong Dai. Application of robo-pigeon in ethological studies of bird flocks[J]. Journal of Integrative Neuroscience, 2020, 19(3): 443-448.
[3] Lei Zhang, Qingguo Wei. Channel selection in motor imaginary-based brain-computer interfaces: a particle swarm optimization algorithm[J]. Journal of Integrative Neuroscience, 2019, 18(2): 141-152.
[4] Lei Guo, Wei Zhang, Jialei Zhang. The effect of an exogenous alternating magnetic field on neural coding in deep spiking neural networks[J]. Journal of Integrative Neuroscience, 2018, 17(2): 97-104.
[5] Zhendong Mu, Jinhai Yin, Jianfeng Hu. Application of a brain-computer interface for person authentication using EEG responses to photo stimuli[J]. Journal of Integrative Neuroscience, 2018, 17(1): 53-60.
No Suggested Reading articles found!