Prediction of lower limb joint angle using sEMG based on GA-GRNN

Wang, Fei; Yin, Tenglong; Lei, Chengshuai; Zhang, Yuanke; Wang, Yifan; Liu, Jian

doi:10.1109/cyber.2015.7288236

Cited by 15 publications

(15 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Mapping EMG measurements to joint positions is a common approach for a regression-based EMG control scheme for exoskeleton control [ 37 , 38 , 39 , 40 , 41 ]. Lee and Lee (2005) estimated knee angles from EMG measurements using a combination of a radial basis function neural network and a multilayer neural network [ 41 ].…”

Section: Introductionmentioning

confidence: 99%

EMG and Joint Angle-Based Machine Learning to Predict Future Joint Angles at the Knee

Coker

Chen

Schall

et al. 2021

Sensors

View full text Add to dashboard Cite

Electromyography (EMG) is commonly used to measure electrical activity of the skeletal muscles. As exoskeleton technology advances, these signals may be used to predict human intent for control purposes. This study used an artificial neural network trained and tested with knee flexion angles and knee muscle EMG signals to predict knee flexion angles during gait at 50, 100, 150, and 200 ms into the future. The hypothesis of this study was that the algorithm’s prediction accuracy would only be affected by time into the future, not subject, gender or side, and that as time into the future increased, the prediction accuracy would decrease. A secondary hypothesis was that as the number of algorithm training trials increased, the prediction accuracy of the artificial neural network (ANN) would increase. The results of this study indicate that only time into the future affected the accuracy of knee flexion angle prediction (p < 0.001), whereby greater time resulted in reduced accuracy (0.68 to 4.62 degrees root mean square error (RMSE) from 50 to 200 ms). Additionally, increased number of training trials resulted in increased angle prediction accuracy.

show abstract

Section: Introductionmentioning

confidence: 99%

EMG and Joint Angle-Based Machine Learning to Predict Future Joint Angles at the Knee

Coker

Chen

Schall

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…In recent years, more and more researchers have used machine learning methods (the other kind of angle estimation methods) to estimate the joint motion angle based on sEMG. For example, support vector machines (SVM) [18], random forests (RF) [19], and other artificial neural network (ANN) algorithms [20][21][22][23] are often utilized to predict joint angles. SVM can be used for classification and regression.…”

Section: Introductionmentioning

confidence: 99%

“…Six able bodied subjects and two people with C5 tetraplegia participated in the experiment. 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. Shengxin Wang et al [24] 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.…”

Section: Introductionmentioning

confidence: 99%

Continuous Estimation of Knee Joint Angle Based on Surface Electromyography Using a Long Short-Term Memory Neural Network and Time-Advanced Feature

Liu

Song

et al. 2020

Sensors

View full text Add to dashboard Cite

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.

show abstract

“…Esta técnica evita el periodo de adaptación y aprendizaje de los controles de la prótesis por parte del usuario. La técnica permite identificar la intención de movimiento del usuario, logrando con ello un control más directo y natural [9][10][11][12][13][14]. En [9] se presenta un algoritmo de control activo-reactivo que permite estimar el torque articular a través de EMG; los autores reportan trayectorias de marcha similares a una marcha estándar, sin embargo, las pruebas no fueron realizadas por personas con amputación.…”

Section: Introductionunclassified

“…En consecuencia, cuando una persona sufre amputación se pierden los patrones de movimiento que habían sido establecidos durante su vida; por lo que ahora, encontrar dichos patrones se convierte en el principal problema. Los algoritmos que utilizan redes neuronales y EMG para estimar ángulo de prótesis transfemorales son presentados en [10,11]. Sin embargo, debido al costo computacional los algoritmos sólo son implementados en línea.…”

Section: Introductionunclassified

Algorithm to estimate the knee angle in normal gait: trajectory generation approach to intelligent transfemoral prosthesis

Martínez-Solis

Ramírez-Betancour

Olmos-López

et al.

View full text Add to dashboard Cite

This paper presents an algorithm to estimate the knee angle from hip angle and gait parameters. This algorithm uses a single sensor on the thigh to achieve the estimation. Hip-knee natural correlations were employed in order to analyze the gait flexion-extension movements in two stages: 1) when the foot is not in full contact with the floor (swing phase and heel contact); 2) when the whole sole makes contact with the ground (stance phase). The estimation is developed in real-time for gait movements and speed fluctuations do not distort the angle estimated. In addition, the simple linear regression was used to approximate the estimated angle to actual knee angle. The experimental results obtained from the gait studies, showed an acceptable knee angle approximation; the mean error estimation was 8.25∘. The major goal of this work was the development of an algorithm that can solve the problem of human body-intelligent transfemoral prosthesis coordination, even if there are gait speed fluctuations.

show abstract

Prediction of lower limb joint angle using sEMG based on GA-GRNN

Cited by 15 publications

References 3 publications

EMG and Joint Angle-Based Machine Learning to Predict Future Joint Angles at the Knee

EMG and Joint Angle-Based Machine Learning to Predict Future Joint Angles at the Knee

Continuous Estimation of Knee Joint Angle Based on Surface Electromyography Using a Long Short-Term Memory Neural Network and Time-Advanced Feature

Algorithm to estimate the knee angle in normal gait: trajectory generation approach to intelligent transfemoral prosthesis

Contact Info

Product

Resources

About