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
Hemiplegia is a motor dysfunction caused by nerve damage [
Surface electromyography (sEMG) signals can reflect neuromuscular activity to a certain extent, and its collection process is convenient and harmless to the human body. It can adapt to the particularity of the physiological condition of hemiplegic patients. Therefore, it becomes one of the most vital signals that can directly reflect the intended movement of the human body. It is used as a tool to indicate the body’s paralysis of the arm all the time [
Many researchers use forces, torques, and angles estimated from SEMG signals to predict movement, thus driving the upper limb movement of the rehabilitation device [
There are still some difficulties in synchronous motion intention recognition of shoulder and elbow joints. The movement of the shoulder and elbow is more extensive. And in the extensive movement of the upper limb, there are many changes in the shoulder and elbow. Therefore, it is more meaningful to estimate the degree of freedom of shoulder joint and elbow joint continuously at the same time.
In this study, we studied the feature method of wavelet packet energy entropy for specific subspaces to alleviate the redundancy problem of adjacent subspaces. For proportional control of shoulder and wrist movements, GA-Elman is used to improve prediction accuracy. The sEMG signals and upper limb movements are recorded during various dynamic processes. In the continuous movement of the shoulder, the feature method and proportional control strategy are discussed and verified to improve the prediction accuracy. The reliability of using this method is discussed in shoulder and elbow synchronous continuous motion.
Six healthy subjects (three males and three females, age 22–28, height 160–180 cm, weight 48–70 kg) were enrolled in this study. They are right-handers. All the subjects read and signed an informed consent form approved by an institutional review board. Before the experiment, everyone was asked to practice as expected to adapt to the equipment until they felt comfortable. In this experiment, Trigno Wireless System (Delsys Inc, Natick, MA, USA) was used to record sEMG signals at a sampling frequency of 1600 Hz. The real angle measurement of shoulder and elbow joints is based on the Codamotion System (Charnwood Dynamics Ltd, UK), which is an active optical motion capture system introduced. The frequency of the acquisition angle is 200 Hz. The average subsampling processing method was used to make the frequency the same. Before collecting sEMG, the muscle surface of volunteers was wiped with alcohol. And the sensors were attached according to the standard manual. We selected eight muscle channels, which in order are biceps brachii, triceps brachii, deltoid (anterior), pectoralis major, deltoid (middle), brachioradialis, trapezius, and teres minor muscle. The sEMG sensors were placed over eight muscles and the markers of Codamotion were set over shoulders and elbows, as shown in Figure
Sensors and markers placement.
During the experiment, the subject sat quietly in the chair. The subject’s right arm hanged naturally and the right hand relaxed. All movements started from where their arm fell naturally and returned to this position after the action was completed. The initial state is shown in Figure
Movement description. (a) The initial state of the subject. The arms are naturally lowered vertically. (b) The subject touched his right shoulder. (c, d) Subjects lifted the right arm as much as possible in different directions.
The experimental movement is shown in Figure
The raw signal was denoised using a wavelet transform. Wavelet packet transform has good signal decomposition ability. Therefore, a sEMG feature extraction method was studied based on that. Wavelet packet transform decomposes the low-frequency part and the high-frequency part of the subspace at the same time, which has better time-frequency localization analysis ability than the wavelet transform [
Six-layer wavelet packet decomposition is performed on eight-channel sEMG signals, and db4 wavelet was chosen as the wavelet base. The raw sEMG signal is very weak, and its energy is mainly distributed in the frequency range of 10–500 Hz [
There is a different degree of information redundancy between adjacent subspaces [
The subspace of wavelet packet decomposition (red is the subspace selected as Feature A;
The raw signal and the signal after wavelet packet decomposition.
The general Elman NN has four layers: the input layer, the implicit layer, the bearing layer, and the output layer. The block diagram of Elman NN is shown in Figure
The block diagram of Elman NN.
BP algorithm is easy to fall into local minima [
The flowchart of optimizing Elman neural network with GA is shown in Figure
Flowchart of GA-Elman algorithm.
GA-Elman can be regarded as an adaptive system without manual intervention [
All assessments were based on data from 6 healthy subjects. K-fold validation (
In this paper, average root mean square error (
The GA-Elman network of upper limb shoulder movement was established for each subject. The comparison of the estimated shoulder joint angles and the actual shoulder joint angles of one subject by using GA-Elman with Feature A and Feature B is shown in Figure
Comparison of the estimated shoulder joint angles and the actual shoulder joint angles by using GA-Elman with (a) Feature A and (b) Feature B.
As can be seen from Figure
The average estimation performance index.
Subject A | Subject B | Subject C | Subject D | Subject E | Subject F | |||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
F.A | F.B | F.A | F.B | F.A | F.B | F.A | F.B | F.A | F.B | F.A | F.B | |
RMSE | 3.24 | 4.23 | 2.95 | 5.35 | 3.57 | 3.92 | 3.06 | 3.20 | 3.96 | 3.98 | 4.05 | 3.98 |
0.81 | 0.78 | 0.81 | 0.79 | 0.83 | 0.77 | 0.87 | 0.80 | 0.82 | 0.79 | 0.83 | 0.81 |
Taking one subject as an example, Figure
Estimated result using different NN. (a) GA-Elman NN. (b) Elman NN. (c) GA-BP NN.
The
It can be seen from Figure
Network training error curve. (a) GA-Elman NN. (b) Elman NN. (c) GA-BP NN.
Fitness curve. (a) GA-Elman NN. (b) GA-BP NN.
The error continuously decreases until the target network training error is reached during the training process. Figures
As can be seen from Figure
The above conclusions show that GA-Elman is superior in both the prediction process and the prediction results. Figures
The average
The average
It is shown in Figures
The GA-Elman with Feature A estimates the continuous angle of the shoulder and elbow joints simultaneously and compares with the GA-BP and Elman neural networks. Table
GA-Elman | GA-BP | Elman | |||
---|---|---|---|---|---|
Subject A | Shoulder | 4.1417 | 7.3099 | 10.2045 | |
0.7833 | 0.5918 | 0.4514 | |||
Elbow | 5.1253 | 8.3085 | 9.3042 | ||
0.8222 | 0.5041 | 0.6763 | |||
Subject B | Shoulder | 3.0728 | 6.3099 | 10.1078 | |
0.8142 | 0.7015 | 0.5912 | |||
Elbow | 7.1421 | 4.8686 | 8.5155 | ||
0.7723 | 0.8203 | 0.6565 | |||
Subject C | Shoulder | 6.1708 | 10.1952 | 8.1873 | |
0.7841 | 0.5480 | 0.6521 | |||
Elbow | 1.1358 | 7.2054 | 9.2116 | ||
0.8556 | 0.7489 | 0.4302 | |||
Subject D | Shoulder | 3.1324 | 6.1982 | 6.1745 | |
0.8764 | 0.6102 | 0.6975 | |||
Elbow | 3.0988 | 10.2543 | 10.1865 | ||
0.7874 | 0.4972 | 0.6153 | |||
Subject E | Shoulder | 4.1053 | 9.2633 | 9.1954 | |
0.7954 | 0.6645 | 0.6253 | |||
Elbow | 5.1623 | 8.2845 | 10.2064 | ||
0.8133 | 0.6572 | 0.5382 | |||
Subject F | Shoulder | 3.2588 | 8.0483 | 8.4527 | |
0.8253 | 0.7235 | 0.6348 | |||
Elbow | 4.3527 | 7.6523 | 7.2594 | ||
0.8075 | 0.7838 | 0.6972 |
As can be seen from Table
So far, the reliability of the joint continuous motion estimation framework based on SEMG signals has been proved. The framework we introduced shows three comparative advantages. First, the selection of a specific subspace in wavelet packet transform not only extracts signals that match the motion, but also achieves dimensionality reduction, which greatly reduces the number of features. Redundant sEMG signals make it difficult to predict movement. The introduction of wavelet packet energy entropy in non-adjacent spaces can alleviate this problem. Compared with the original wavelet packet energy entropy, this method is more accurate in motion estimation. But it did not increase the difficulty of calculation. Secondly, GA-Elman was established to deal with the regression problem of continuous motion. Finally, the feasibility of estimating single joint and multijoint movements was verified in a large number of upper limb movements. Compared with Elman and GA-BP NN, the average
In this paper, aiming at the rehabilitation training of patients with hemiplegia, the Elman neural network optimized by GA is proposed to predict the shoulder and elbow joint angle. The WPEE of the specific subspace is used to represent the sEMG as the input of the neural network. The results show that the method in this paper is effective for estimating the shoulder and elbow joint angle of the upper limb. In comparative experiments, it showed the best performance. However, the comparison of Tables
The data used to support the findings of this study are available from the corresponding author upon request.
The authors declare that they have no conflicts of interest.
This work was supported by the National Natural Science Foundation of China (Nos. 61971169 and U1909209), National Natural Science Major Foundation of Research Instrumentation of China (Grant no. 61427808), and Zhejiang Provincial Natural Science Foundation of China (Grant no. LZ17F030002).