EEG characteristic investigation of the sixth-finger motor imagery and optimal channel selection for classification. (24th January 2022)

• Record Type: Journal Article
• Authors: Liu, Yuan; Wang, Zhuang; Huang, Shuaifei; Wang, Wenjie; Ming, Dong
• Is Part Of: Journal of neural engineering. Volume 19:Number 1(2022)
• Publication Date: 2022-01-24
• Subjects: supernumerary robotic limbs -- brain–computer interface -- motor imagery -- wearable robotic -- EEG characteristic; Neurosciences -- Periodicals; Biomedical engineering -- Periodicals; 612.8
• DOI: 10.1088/1741-2552/ac49a6
• Languages: English
• ISSNs: 1741-2560

Abstract

Abstract: Objective. Supernumerary robotic limbs are body augmentation robotic devices by adding extra limbs or fingers to the human body different from the traditional wearable robotic devices such as prosthesis and exoskeleton. We proposed a novel motor imagery (MI)-based brain–computer interface (BCI) paradigm based on the sixth-finger which imagines controlling the extra finger movements. The goal of this work is to investigate the electromyographic (EEG) characteristics and the application potential of MI-based BCI systems based on the new imagination paradigm (the sixth finger MI). Approach. Fourteen subjects participated in the experiment involving the sixth finger MI tasks and rest state. Event-related spectral perturbation was adopted to analyze EEG spatial features and key-channel time-frequency features. Common spatial patterns were used for feature extraction and classification was implemented by support vector machine. A genetic algorithm (GA) was used to select combinations of EEG channels that maximized classification accuracy and verified EEG patterns based on the sixth finger MI. And we conducted a longitudinal 4 weeks EEG control experiment based on the new paradigm. Main results. Event-related desynchronization (ERD) was found in the supplementary motor area and primary motor area with a faint contralateral dominance. Unlike traditional MI based on the human hand, ERD was also found in frontal lobe. GA results showed that the distribution of the optimal eight-channel is similar to EEG topographical distributions, nearing parietal and frontal lobe. And the classification accuracy based on the optimal eight-channel (the highest accuracy of 80% and mean accuracy of 70%) was significantly better than that based on the random eight-channel ( p < 0.01). Significance. This work provided a new paradigm for MI-based MI system and verified its feasibility, widened the control bandwidth of the BCI system.