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

Abstract

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 RMSE of 3.4717 and R2 of 0.8283 in shoulder movement and with a RMSE of 4.1582 and R2 of 0.8114 in continuous synchronous movement of the shoulder and elbow.

Continuous Motion Intention Prediction Using sEMG for Upper-Limb Rehabilitation: A Systematic Review of Model-Based and Model-Free Approaches

“…Studies [173] and [174] utilized TD features and BPNN for predictions, with [174] introducing an AE before BPNN input to extract advanced features through unsupervised learning. As for studies [175] and [176] based on RNN, [175] employed TFD features for prediction with GA-optimized ElmanNN, while [176] utilized time-delayed TD features with RFNN to enhance robustness to movement speed variations. However, although GA-ElmanNN outperformed both ElmanNN and GA-BPNN, GA increased computational cost for real-time prediction.…”

Continuous Estimation of Upper Limb Joint Angle Based on Stacked Denoising Autoencoder

“…Ma et al [1] designed the SCA-LSTM network that extracts the different-mode feature information of the sEMG using a short connected autoencoder (SCA) and inputs it into an LSTM network to estimate the shoulder-elbow joint angles. Wang et al [2] utilized the genetic algorithm (GA) to optimize the parameters in an Elman neural network to extract the sEMG special subspace's wavelet packet energy entropy was used as the input of GA-Elman for simultaneous estimation of shoulder and elbow joint angles. Ma et al [3] constructed a Bi-LSTM model that can extract sEMG's bidirectional information to simultaneously estimate the shoulder-elbow joint angles.…”

Continuous Estimation of Human Upper Limb Joint Angles by Using PSO-LSTM Model

“…Zhang et al [26] proposed an m-order non-linear model is aim to establish the mapping between the sEMG signal and the human leg joint angle, and to estimate the human leg joint angle by Back Propagation neural network (BP). Wang et al [27] proposed to use the wavelet packet energy entropy of special subspaces as a feature of sEMG signals to estimate shoulder and elbow joint angles using a genetic an Elman neural network optimized by a genetic algorithm. Ma et al [28] proposed a short connected autoencoder long short-term memory (SCA-LSTM) model that uses kinematic information extracted from the sEMG to estimate continuous arm motion.…”