Abstract
The rehabilitation training based on motor imagery brain-computer interface (MI-BCI) is considered to be an effective method. We designed a new 2-class unilateral upper limb motor imagery tasks. Data from 15 healthy subjects and 10 stoke patients are collected in the study. The results of event-related desynchronization/synchronization (ERD/ERS) and power spectral density (PSD) analysis showed the significant different features on health subjects and stroke patients. The improved 2-Conv-FBCNET is used to classify Electroencephalogram (EEG) signals and the accuracy is (health: 61.0%, stroke: 59.4%). The new two types of tasks provide a new training method for MI-BCI rehabilitation training system.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
