Design of a Hand Rehabilitation System Based on EEG Signals
Main Article Content
Abstract
In order to solve the problems of poor traditional rehabilitation training and the inability to achieve neuronal reorganization and recovery in stroke patients, a hand rehabilitation system controlled by EEG signals and classified by convolutional neural network was designed. The EEG signal acquisition module adopts the DSI-24 wireless polar brain acquisition system of Boruikang, the EEG signal processing method uses dual-channel CNN processing, the hand control system adopts the arduino development board and pneumatic rehabilitation gloves, and the signal processing and control software are completed in the computer. Design an experimental paradigm of motion imagination with two commands, left-handed and right-handed. Four participants were recruited to verify the feasibility of the system. Result The CNN recognition rate of five subjects reached 82%, the validation using the BCI2b dataset reached 85%, and the accuracy of the hand rehabilitation experiment reached 80%. Conclusions The results of this experiment verify the feasibility of rehabilitation gloves and provide a new method for the treatment of stroke patients.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
Huo YaopuResearch on finger rehabilitation system based on motor imaging EEG[D]. Southeast University, 2019
Ueki S, Kawasaki H, Ito S, et al. Development of a Hand-assist Robot with Multi-Degrees-of-Freedom for Rehabilitation Therapy[J]. IEEE/ASME Transactions on Mechatronics, 2012, 17(1): 136-146.
Jo I, Lee J, Park Y, et al. Design of a Wearable Hand Exoskeleton for Exercising Flexion/Extension of the Fingers[M]//Amirabdollahian F, Burdet E, Masia L. International Conference on Rehabilitation Robotics ICORR. 2017:1615-1620.
Nycz C, Butzer T L, Lambercy O, et al. Design and Characterization af a Lightweight and Fully Portable Remote Actuation System for Use with a Hand Exoskeleton[J]. IEEE Robotics and Automation Letters, 2016, 1(2): 976-983.
Gezgin E, Chang P H, Akhan A F. Synthesis of a Watt II Six-bar Linkage in the Design of a Hand Rehabilitation Robot[J]. Mechanism and Machine Theory, 2016, 104: 177-189.
Dovat L, Lambercy O, Gassert R, et al. HandCARE: A Cable-Actuated Rehabilitation System to Train Hand Function After Stroke[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2009, 16(6): 582-591.
Pinter D, Pegritz S, Pargfrieder C, et al. Exploratory Study on the Effects of a Robotic Hand Rehabilitation Device on Changes in Grip Strength and Brain Activity after Stroke[J]. Topics in Stroke Rehabilitation, 2013, 20(4): 308-316.
Teixeira C D C,0liveira J C D．Right hand rehabilitation wiIh cyber_ force,cybe以rasp, and cybelove[c]Virtual and Augmented Reality．New York：IEEE,2015：186—189
CHEN Hongwei. Research on control system and strategy of exoskeleton hand rehabilitation robot[D]. Harbin Institute of Technology, 2013.
LI Shengqun. Research on structure and control system of finger rehabilitation robot[D]. Huazhong University of Science and Technology, 2009.
ZHANG Nan, NIU Baoshan, WANG Hongbo, et al. Design of Structure and Control System of Automated Interference Rejection Finger Rehabilitation Robot[J]. Science Technology and Engineering, 2019, 19(06): 166-173.
Li J, Wang S, Wang J, et al. Development of a Hand Exoskeleton System for Index Finger Rehabilitation[J]. Chinese Journal of Mechanical Engineering, 2012, 25(2): 223-232.
FAN Xu, DAI Ning, WANG Hongtao, et al. Research on Bending Deformation Prediction Method of Pneumatic Grid Software Actuator[J/OL]. China Mechanic 2019: 1-9.
LI Min, CHEN Jiazhou, HE Bo, et al. Movement Planning and Structural Optimization of Multi-segment Continuous Structure Hand Function Rehabilitation Exoskeleton[J]. Journal of Xi'an Jiaotong University, 2019, 53(10): 1-9.
SCHIRRMEISTER R T, SPRINGENBERG J T, FIEDERER L D J, et al. Deep learning with convolutional neural networks for EEG decoding and visualization[J]. Human Brain Mapping, 2017, 38(11): 5391-5420