Knee Joint Angle Prediction Based on Muscle Synergy Theory and Generalized Regression Neural Network

Liu, Quan; Ma, Liangyun; Ai, Qing; Chen, Kun; Meng, Wei

doi:10.1109/aim.2018.8452230

Cited by 15 publications

(11 citation statements)

References 13 publications

(17 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Siddiqi et al [44] used SVM to predict thumb angle of bending motion and adopted "piecewise-discretization" method for continuous angle prediction. Liu et al [45] used a generalized neural network (GNN) to estimate the joint angle of the lower limb knee joint during continuous movement. Xin et al [46] used sEMG to predict the joint angle of wrist flexion and extension movement through a time-delay recurrent neural network (TDRNN).…”

Section: A Via Physiological Signalsmentioning

confidence: 99%

Machine Learning in Robot-Assisted Upper Limb Rehabilitation: A Focused Review

Liu

Meng³

et al. 2023

IEEE Trans. Cogn. Dev. Syst.

Self Cite

View full text Add to dashboard Cite

Robot-assisted rehabilitation, which can provide repetitive, intensive and high-precision physics training, has a positive influence on motor function recovery of stroke patients. Current robots need to be more intelligent and more reliable in clinical practice. Machine learning algorithms (MLAs) are able to learn from data and predict future unknown conditions, which is of benefit to improve the effectiveness of robot-assisted rehabilitation. In this paper, we conduct a focused review on machine learning-based methods for robot-assisted upper limb rehabilitation. Firstly, the current status of upper rehabilitation robots is presented. Then, we outline and analyze the designs and applications of MLAs for upper limb movement intention recognition, human-robot interaction control and quantitative assessment of motor function. Meanwhile, we discuss the future directions of MLAs-based robotic rehabilitation. This review article provides a summary of MLAs for robotic upper limb rehabilitation and contributes to the design and development of future advanced intelligent medical devices.

show abstract

Section: A Via Physiological Signalsmentioning

confidence: 99%

Machine Learning in Robot-Assisted Upper Limb Rehabilitation: A Focused Review

Liu

Meng³

et al. 2023

IEEE Trans. Cogn. Dev. Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Neural networks are a type of machine learning algorithms that are trained to find the underlying relation between input and output variables. Several studies used neural networks for the prediction of knee flexion angles or torques in able-bodied subjects ( Liu et al, 2018 ; Huang et al, 2019 ; Saranya et al, 2019 ; Wang G. et al, 2019 ; Deng et al, 2020 ; Gautam et al, 2020 ). Huang et al (2019) proposed a deep-recurrent neural network for prediction of knee joint angles in real-time.…”

Section: Introductionmentioning

confidence: 99%

Multi-Day EMG-Based Knee Joint Torque Estimation Using Hybrid Neuromusculoskeletal Modelling and Convolutional Neural Networks

et al. 2022

View full text Add to dashboard Cite

Proportional control using surface electromyography (EMG) enables more intuitive control of a transfemoral prosthesis. However, EMG is a noisy signal which can vary over time, giving rise to the question what approach for knee torque estimation is most suitable for multi-day control. In this study we compared three different modelling frameworks to estimate knee torque in non-weight-bearing situations. The first model contained a convolutional neural network (CNN) which mapped EMG to knee torque directly. The second used a neuromusculoskeletal model (NMS) which used EMG, muscle tendon unit lengths and moment arms to compute knee torque. The third model (Hybrid) used a CNN to map EMG to specific muscle activation, which was used together with NMS components to compute knee torque. Multi-day measurements were conducted on ten able-bodied participants who performed non-weight bearing activities. CNN had the best performance in general and on each day (Normalized Root Mean Squared Error (NRMSE) 9.2 ± 4.4%). The Hybrid model (NRMSE 12.4 ± 3.4%) was able to outperform NMS (NRMSE 14.3 ± 4.2%). The NMS model showed no significant difference between measurement days. The CNN model and Hybrid models had significant performance differences between the first day and all other days. CNNs are suited for multi-day torque estimation in terms of error rate, outperforming the other two model types. NMS was the only model type which was robust over all days. This study investigated the behavior of three model types over multiple days, giving insight in the most suited modelling approach for multi-day torque estimation to be used in prosthetic control.

show abstract

“…The sEMG and joint angle regression model is established through deep belief networks and back propagation (BP) neural networks [ 18 ]. To further improve the prediction effect, sEMG, joint angles, and plantar pressure signals [ 19 , 20 ] are introduced into the generalized regression neural network for training and prediction. Similarly, sEMG and A-mode ultrasound [ 21 ] have been combined and introduced to build a vector machine regression model.…”

Section: Introductionmentioning

confidence: 99%

Study on the Control Method of Knee Joint Human–Exoskeleton Interactive System

Wang

Yang

Ding

et al. 2022

Sensors

View full text Add to dashboard Cite

The advantages of exoskeletons based on the Bowden cable include being lightweight and flexible, thus being convenient in assisting humans. However, the performance of an exoskeleton is limited by the structure and human–exoskeleton interaction, which is analyzed from the established mathematical model of the human–exoskeleton system. In order to improve the auxiliary accuracy, corresponding control methods are proposed. The disturbance observer is designed to compensate for disturbances and parameter perturbations in the inner loop. The human–exoskeleton interaction feedforward model is integrated into the admittance control, which overcomes the limitation of the force loading caused by the friction of the Bowden cable and the change in stiffness of the human–exoskeleton interaction. Furthermore, an angle prediction method using the encoder as the signal source is designed to reduce the disturbance of the force loading caused by human motion. Finally, the effectiveness of the design method proposed in this paper is verified through experiments.

show abstract

Knee Joint Angle Prediction Based on Muscle Synergy Theory and Generalized Regression Neural Network

Cited by 15 publications

References 13 publications

Machine Learning in Robot-Assisted Upper Limb Rehabilitation: A Focused Review

Machine Learning in Robot-Assisted Upper Limb Rehabilitation: A Focused Review

Multi-Day EMG-Based Knee Joint Torque Estimation Using Hybrid Neuromusculoskeletal Modelling and Convolutional Neural Networks

Study on the Control Method of Knee Joint Human–Exoskeleton Interactive System

Contact Info

Product

Resources

About