NeuroFlex: Feasibility of EEG-Based Motor Imagery Control of a Soft Glove for Hand Rehabilitation

This study introduces NeuroFlex, a soft robotic glove controlled by brain signals to help people with hand mobility issues perform rehabilitation exercises. NeuroFlex uses a deep learning model to decode a person's intention to move from their brain activity (EEG data) and translates it into commands for the glove. The glove's design allows users to practice fist formation and grasping movements, and the results show that the system can accurately detect the intent to make a fist up to 85.3% of the time.

• 1
  The accuracy of decoding the intent of fingers making a fist from MI EEG can reach up to 85.3%, with an average AUC of 0.88.
• 2
  NeuroFlex demonstrates the feasibility of detecting and assisting the patient’s attempted movements using pure thinking through a non-intrusive brain–computer interface (BCI).
• 3
  This EEG-based soft glove aims to enhance the effectiveness and user experience of rehabilitation protocols, providing the possibility of extending therapeutic opportunities outside clinical settings.