Author:
Tao Yunfei,Huang Yuping,Zheng Jigui,Chen Jing,Zhang Zhaojing,Guo Yajing
Abstract
Abstract
In order to obtain the estimated value of the continuous motion of the lower limbs of the human body (abbreviated as CMLLHB) and realize the better human-machine collaborative control effect of the exoskeleton robot, a method for estimating the amount of CMLLHB based on sEMG and high-order polynomials is proposed. Extract and form 5 feature parameter matrices of 8 channels of signals, establish a high-order polynomial-based CMLLHB, and realize CMLLHB. Through experiments, the overall average error of angle estimation based on this method is 0.09±0.11rad, the root mean square error is 1.63rad, and the average correlation coefficient Weir is 0.79. Among them, the hip joint motion estimation effect is the best.
Subject
General Physics and Astronomy
Reference6 articles.
1. A Support Vector Machine Based on an Improved Particle Swarm Optimization Algorithm for SEMG Signal Pattern Recognition[J];Mingliang;Chinese Journal of Sensors and Actuators,2017
2. Study on recognition of motor pattern based on electrical signal of facial muscles of lower limbs[J];Fan;Journal of Qiqihar University(Natural Science Edition),2018
3. Real-time myoprocessors for a neural controlled powered exoskeleton arm[C];Cavallaro;IEEE Transactions on Biomedical Engineering,2006
4. A dynamic recurrent neural network for multiple muscles electromyographic mapping to elevation angles of the lower limb in human locomotion[J];Cheron;Journal of Neuroscience Methods,2003