A Minimal Set of Electrodes for Motor Imagery BCI to Control an Assistive Device in Chronic Stroke Subjects: A Multi-Session Study

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 19; no. 6; pp. 617 - 627
• Main Authors: Tam, Wing-Kin, Tong, Kai-yu, Meng, Fei, Gao, Shangkai
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.12.2011; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Adult; Aged; Algorithms; Band pass filters; Brain - physiology; Brain modeling; Brain-computer interface (BCI); Calibration; Cerebral Cortex - physiology; Channels; Chronic Disease; Data Interpretation, Statistical; Devices; Electric Stimulation; electrical stimulation; Electrodes; Electroencephalography; Female; Functional Laterality - physiology; Humans; Imagery; Imagination - physiology; Male; Middle Aged; Motors; Movement - physiology; Online Systems; Patient rehabilitation; Psychomotor Performance - physiology; Self-Help Devices; Stroke; Stroke Rehabilitation; Strokes; Support Vector Machine; support vector machine (SVM); Support vector machines; Training; User-Computer Interface
• DOI: 10.1109/TNSRE.2011.2168542
• ISSN: 1534-4320; 1558-0210

The brain-computer interface (BCI) system has been developed to assist people with motor disability. To make the system more user-friendly, it is a challenge to reduce the electrode preparation time and have a good reliability. This study aims to find a minimal set of electrodes for an individual stroke subject for motor imagery to control an assistive device using functional electrical stimulation for 20 sessions with accuracy higher than 90%. The characteristics of this minimal electrode set were evaluated with two popular algorithms: Fisher's criterion and support-vector machine recursive feature elimination (SVM-RFE). The number of calibration sessions for channel selection required for robust control of these 20 sessions was also investigated. Five chronic stroke patients were recruited for the study. Our results suggested that the number of calibration sessions for channel selection did not have a significant effect on the classification accuracy. A performance index devised in this study showed that one training day with 12 electrodes using the SVM-RFE method achieved the best balance between the number of electrodes and accuracy in the 20-session data. Generally, 8-36 channels were required to maintain accuracy higher than 90% in 20 BCI training sessions for chronic stroke patients.