Estimation of Continuous Joint Angles of Upper Limb Based on sEMG by Using GA-Elman Neural Network

The estimation of continuous and simultaneous multijoint angle based on surface electromyography (sEMG) signal is of considerable significance in rehabilitation practice. However, there are few studies on the continuous joint angle of multiple joints at present. In this paper, the wavelet packet energy entropy (WPEE) of the special subspace was investigated as a feature of the sEMG signal. An Elman neural network optimized by genetic algorithm (GA) was established to estimate the joint angle of shoulder and elbow. First, the accuracy of the method is verified by estimating the angle of the shoulder joint. Then, this method was used to simultaneously and continuously estimate the shoulder and elbow joint angle. Six subjects flexed and extended the upper limbs according to the intended movements of the experiment. The results show that this method can obtain a decent performance with a of 3.4717 and of 0.8283 in shoulder movement and with a of 4.1582 and of 0.8114 in continuous synchronous movement of the shoulder and elbow.

[1]  Amit M. Joshi,et al.  Improved Classification Scheme Using Fused Wavelet Packet Transform Based Features for Intelligent Myoelectric Prostheses , 2020, IEEE Transactions on Industrial Electronics.

[2]  Arit Thammano,et al.  Modified Genetic Algorithm for Flexible Job-Shop Scheduling Problems , 2012, Complex Adaptive Systems.

[3]  Caihua Xiong,et al.  Simultaneous and Continuous Estimation of Shoulder and Elbow Kinematics from Surface EMG Signals , 2017, Frontiers in neuroscience.

[4]  Abdulkadir Sengur,et al.  Flexible Analytic Wavelet Transform Based Features for Physical Action Identification Using sEMG Signals , 2020 .

[5]  Gregory S Sawicki,et al.  A neuromechanics-based powered ankle exoskeleton to assist walking post-stroke: a feasibility study , 2015, Journal of NeuroEngineering and Rehabilitation.

[6]  Yoshiyuki Sankai,et al.  Feasibility of Synergy-Based Exoskeleton Robot Control in Hemiplegia , 2018, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[7]  Jianda Han,et al.  A State-Space EMG Model for the Estimation of Continuous Joint Movements , 2015, IEEE Transactions on Industrial Electronics.

[8]  Carlo Menon,et al.  Performance of forearm FMG and sEMG for estimating elbow, forearm and wrist positions , 2017 .

[9]  Ke Huang,et al.  Information-theoretic wavelet packet subband selection for texture classification , 2006, Signal Process..

[10]  J. Dewald,et al.  Flexion synergy overshadows flexor spasticity during reaching in chronic moderate to severe hemiparetic stroke , 2017, Clinical Neurophysiology.

[11]  Xinjun Sheng,et al.  Continuous estimation of finger joint angles under different static wrist motions from surface EMG signals , 2014, Biomed. Signal Process. Control..

[12]  Chalavadi Krishna Mohan,et al.  Human action recognition using genetic algorithms and convolutional neural networks , 2016, Pattern Recognit..

[13]  S. Rose,et al.  Changes in the integrity of thalamocortical connections are associated with sensorimotor deficits in children with congenital hemiplegia , 2013, Brain Structure and Function.

[14]  Dean Zhao,et al.  A novel optimized GA–Elman neural network algorithm , 2017, Neural Computing and Applications.

[15]  Sung Hoon Kim,et al.  Robotic-Assisted Shoulder Rehabilitation Therapy Effectively Improved Poststroke Hemiplegic Shoulder Pain: A Randomized Controlled Trial. , 2019, Archives of physical medicine and rehabilitation.

[16]  Andrzej Rybarczyk,et al.  Multisensor data fusion using Elman neural networks , 2018, Appl. Math. Comput..

[17]  J. Langenderfer,et al.  Effect of hammer mass on upper extremity joint moments. , 2017, Applied ergonomics.

[18]  Ning Zhang,et al.  The design of a hemiplegic upper limb rehabilitation training system based on surface EMG signals , 2018 .

[19]  Xianmin Zhang,et al.  Estimation of Handgrip Force from SEMG Based on Wavelet Scale Selection , 2018, Sensors.

[20]  Yong Zhang,et al.  Classification of EEG Signals Based on Autoregressive Model and Wavelet Packet Decomposition , 2017, Neural Processing Letters.

[21]  Jianda Han,et al.  Continuous Estimation of Human Multi-Joint Angles From sEMG Using a State-Space Model. , 2017, IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[22]  Xiangyang Zhu,et al.  Divide-and-conquer muscle synergies: A new feature space decomposition approach for simultaneous multifunction myoelectric control , 2018, Biomed. Signal Process. Control..

[23]  Nahid Norouzi-Gheidari,et al.  Electromyogram-Related Neuromuscular Electrical Stimulation for Restoring Wrist and Hand Movement in Poststroke Hemiplegia: A Systematic Review and Meta-Analysis , 2019, Neurorehabilitation and neural repair.

[24]  Ying Cheng,et al.  Motor Function Evaluation of Hemiplegic Upper-Extremities Using Data Fusion from Wearable Inertial and Surface EMG Sensors , 2017, Sensors.

[25]  S. Scalvini,et al.  Feasibility and efficacy of a robotic device for hand rehabilitation in hemiplegic stroke patients: a randomized pilot controlled study , 2017, Clinical rehabilitation.

[26]  Yong Wang,et al.  Continuous estimation of joint angle from electromyography using multiple time-delayed features and random forests , 2018, Biomed. Signal Process. Control..

[27]  Yupeng Ren,et al.  EMG-Based Continuous and Simultaneous Estimation of Arm Kinematics in Able-Bodied Individuals and Stroke Survivors , 2017, Front. Neurosci..