Abstract

Continuous joint angle estimation based on a surface electromyography (sEMG) signal can be used to improve the man-machine coordination performance of the exoskeleton. In this study, we proposed a time-advanced feature and utilized long short-term memory (LSTM) with a root mean square (RMS) feature and its time-advanced feature (RMSTAF; collectively referred to as RRTAF) of sEMG to estimate the knee joint angle. To evaluate the effect of joint angle estimation, we used root mean square error (RMSE) and cross-correlation coefficient ρ between the estimated angle and actual angle. We also compared three methods (i.e., LSTM using RMS, BPNN (back propagation neural network) using RRTAF, and BPNN using RMS) with LSTM using RRTAF to highlight its good performance. Five healthy subjects participated in the experiment and their eight muscle (i.e., rectus femoris (RF), biceps femoris (BF), semitendinosus (ST), gracilis (GC), semimembranosus (SM), sartorius (SR), medial gastrocnemius (MG), and tibialis anterior (TA)) sEMG signals were taken as algorithm inputs. Moreover, the knee joint angles were used as target values. The experimental results showed that, compared with LSTM using RMS, BPNN using RRTAF, and BPNN using RMS, the average RMSE values of LSTM using RRTAF were respectively reduced by 8.57%, 46.62%, and 68.69%, whereas the average ρ values were respectively increased by 0.31%, 4.15%, and 18.35%. The results demonstrated that LSTM using RRTAF, which contained the time-advanced feature, had better performance for estimating the knee joint motion.

Highlights

  • In recent years, the exoskeleton robot has attracted the attention of researchers from all over the world due to its broad application prospects in the fields of power assistance, disability assistance, and rehabilitation [1,2,3,4,5]

  • The root mean square (RMS) feature extraction and its time-advanced feature (RMSTAF) formulas are shown in Formulas (3) and (4), where emg(i) represents the preprocessed sample sequence, N represents the width of the sliding window, and is set at 20

  • We verified whether RMS feature application and its time-advanced feature (RMSTAF) could effectively improve knee joint angle prediction accuracy

Read more

Summary

Introduction

The exoskeleton robot has attracted the attention of researchers from all over the world due to its broad application prospects in the fields of power assistance, disability assistance, and rehabilitation [1,2,3,4,5]. Zhang et al [20] built an angle prediction model using a back propagation (BP) neural network with the RMS feature of sEMG to describe the relationship between the human leg joint angle and relevant muscle (sEMG) signals. Fei Wang et al [23] used a general regression neural network adjusted with a general algorithm (GA-GRNN) and sEMG RMS feature to predict the knee joint angle. Utilized a radial basis function neural network (RBF) as the joint angle model and extracted the liner profile-curve of sEMG as the input feature to estimate the human joint angle or angular velocity. The previous results are limited for the following reasons Some of these studies did not consider that sEMG was generated earlier than the related muscle contraction, so various features adopted in some of the above methods could not readily reflect the real joint angle information.

Data Acquisition
This capture system integrated
Position namesnames of the subjects’
Feature Extraction of sEMG and Time-Advanced Feature Signals
Long Short-Term Memory Neural Network for Angle Estimation
Choice
BP Neural Network Algorithms n y y network
Evaluation Criteria of Angle Prediction Effect
Results
Discussion
Conclusions

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.