Neurofeedback-based motor imagery training for brain–computer interface (BCI)

• Published in: Journal of neuroscience methods Vol. 179; no. 1; pp. 150 - 156
• Main Authors: Hwang, Han-Jeong, Kwon, Kiwoon, Im, Chang-Hwang
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 30.04.2009
• Subjects: Adult; Arm - physiology; Biofeedback, Psychology - methods; Brain - physiology; Brain–computer interface (BCI); Cortical source imaging; EEG; Electroencephalography - methods; Electromyography; Humans; Imagination - physiology; Learning - physiology; Male; Man-Machine Systems; Motor imagery; Psychomotor Performance - physiology; Real-time cortical activity monitoring; Time Factors; User-Computer Interface; Motor imagery; Real-time cortical activity monitoring; Cortical source imaging; EEG; Brain–computer interface (BCI)
• ISSN: 0165-0270; 1872-678X; 1872-678X
• DOI: 10.1016/j.jneumeth.2009.01.015

In the present study, we propose a neurofeedback-based motor imagery training system for EEG-based brain–computer interface (BCI). The proposed system can help individuals get the feel of motor imagery by presenting them with real-time brain activation maps on their cortex. Ten healthy participants took part in our experiment, half of whom were trained by the suggested training system and the others did not use any training. All participants in the trained group succeeded in performing motor imagery after a series of trials to activate their motor cortex without any physical movements of their limbs. To confirm the effect of the suggested system, we recorded EEG signals for the trained group around sensorimotor cortex while they were imagining either left or right hand movements according to our experimental design, before and after the motor imagery training. For the control group, we also recorded EEG signals twice without any training sessions. The participants’ intentions were then classified using a time–frequency analysis technique, and the results of the trained group showed significant differences in the sensorimotor rhythms between the signals recorded before and after training. Classification accuracy was also enhanced considerably in all participants after motor imagery training, compared to the accuracy before training. On the other hand, the analysis results for the control EEG data set did not show consistent increment in both the number of meaningful time–frequency combinations and the classification accuracy, demonstrating that the suggested system can be used as a tool for training motor imagery tasks in BCI applications. Further, we expect that the motor imagery training system will be useful not only for BCI applications, but for functional brain mapping studies that utilize motor imagery tasks as well.