Prediction of Human Dynamic Ankle Moment Based on Surface Electromyography Signals

Zhu, Aibin; Shen, H.; Shen, Zhitao; Liu, Ying; Mao, Han; Zhang, Xiaodong; Cao, Guang-Zhong

doi:10.1109/urai.2019.8768692

Cited by 2 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As detailed in Table 5, five studies included in this paper predicted lower-limb kinematic and kinetic data by using muscle activity and joint(s) angle as input to the prediction system [39][40][41][42][43]. All studies involved healthy subjects (N = 51, 28 males; 23 females; mean age 30 years, mean height 170 cm, and weight ranging between 60 kg and 80 kg).…”

Section: Lower-limb Kinematic and Kinetic Prediction With Emg And Add...mentioning

confidence: 99%

“…All participants were instructed to walk overground without assistance or exoskeleton use. Two studies requested participants to walk at their natural speed [42,43], two studies [40,41] requested gait at natural speed and at different speeds. One study [39] controlled participants' speed during the experimental protocol.…”

Section: Lower-limb Kinematic and Kinetic Prediction With Emg And Add...mentioning

confidence: 99%

“…Conclusions about which muscles were relevant for each type of output prediction cannot be drawn currently, due to the low number of papers. Two papers predicted ankle torque [39,40], two papers predicted joint moments [42,43]; Hahn et al [42] predicted hip, knee, and ankle moments and Zhu et al [43] predicted only knee moment. Chong et al [41] predicted knee and hip angle.…”

Section: Lower-limb Kinematic and Kinetic Prediction With Emg And Add...mentioning

confidence: 99%

“…Chong et al [41] predicted knee and hip angle. Prediction tools again varied, although all could be classified as neural networks; two papers used an artificial neural network (ANN) [40,42], one employed restricted Boltzmann machine (RBM) [41], one combined CNN and LSTM [39], and the final one [43] implemented an Elman neural network. The mechanisms evaluating the performance of the prediction tools were again heterogeneous, limiting direct comparison between studies.…”

Section: Lower-limb Kinematic and Kinetic Prediction With Emg And Add...mentioning

confidence: 99%

“…Two papers [39,42] used EMG, angular velocity, and anthropometrics as input to calculate joint moments. Two papers [40,43] used EMG and angle joints as input to calculate torque and moment joints. One paper [41] used EMG, acceleration, and force sensing resistors (FSRs) as an input to calculate joint angles, where the prediction system is seen to perform better than in the previous studies [39,40,42,43], as can be shown in Table 5.…”

Section: Lower-limb Kinematic and Kinetic Prediction With Emg And Add...mentioning

confidence: 99%

See 4 more Smart Citations

Prediction of Gait Kinematics and Kinetics: A Systematic Review of EMG and EEG Signal Use and Their Contribution to Prediction Accuracy

Amrani El Yaakoubi,

McDonald,

Lennon

2023

Bioengineering

View full text Add to dashboard Cite

Human-machine interfaces hold promise in enhancing rehabilitation by predicting and responding to subjects’ movement intent. In gait rehabilitation, neural network architectures utilize lower-limb muscle and brain activity to predict continuous kinematics and kinetics during stepping and walking. This systematic review, spanning five databases, assessed 16 papers meeting inclusion criteria. Studies predicted lower-limb kinematics and kinetics using electroencephalograms (EEGs), electromyograms (EMGs), or a combination with kinematic data and anthropological parameters. Long short-term memory (LSTM) and convolutional neural network (CNN) tools demonstrated highest accuracies. EEG focused on joint angles, while EMG predicted moments and torque joints. Useful EEG electrode locations included C3, C4, Cz, P3, F4, and F8. Vastus Lateralis, Rectus Femoris, and Gastrocnemius were the most commonly accessed muscles for kinematic and kinetic prediction using EMGs. No studies combining EEGs and EMGs to predict lower-limb kinematics and kinetics during stepping or walking were found, suggesting a potential avenue for future development in this technology.

show abstract

Section: Lower-limb Kinematic and Kinetic Prediction With Emg And Add...mentioning

confidence: 99%

Section: Lower-limb Kinematic and Kinetic Prediction With Emg And Add...mentioning

confidence: 99%

Section: Lower-limb Kinematic and Kinetic Prediction With Emg And Add...mentioning

confidence: 99%

Section: Lower-limb Kinematic and Kinetic Prediction With Emg And Add...mentioning

confidence: 99%

Section: Lower-limb Kinematic and Kinetic Prediction With Emg And Add...mentioning

confidence: 99%

See 3 more Smart Citations

Prediction of Gait Kinematics and Kinetics: A Systematic Review of EMG and EEG Signal Use and Their Contribution to Prediction Accuracy

Amrani El Yaakoubi,

McDonald,

Lennon

2023

Bioengineering

View full text Add to dashboard Cite

show abstract

Transferable Deep Learning Models for Accurate Ankle Joint Moment Estimation during Gait Using Electromyography

Ali,

Owaki,

Hayashibe

2024

Applied Sciences

View full text Add to dashboard Cite

The joint moment is a key measurement in locomotion analysis. Transferable prediction across different subjects is advantageous for calibration-free, practical clinical applications. However, even for similar gait motions, intersubject variance presents a significant challenge in maintaining reliable prediction performance. The optimal deep learning models for ankle moment prediction during dynamic gait motions remain underexplored for both intrasubject and intersubject usage. This study evaluates the feasibility of different deep-learning models for estimating ankle moments using sEMG data to find an optimal intrasubject model against the inverse dynamic approach. We verified and compared the performance of 1302 intrasubject models per subject on 597 steps from seven subjects using various architectures and feature sets. The best-performing intrasubject models were recurrent convolutional neural networks trained using signal energy features. They were then transferred to realize intersubject ankle moment estimation.

show abstract

Prediction of Human Dynamic Ankle Moment Based on Surface Electromyography Signals

Cited by 2 publications

References 9 publications

Prediction of Gait Kinematics and Kinetics: A Systematic Review of EMG and EEG Signal Use and Their Contribution to Prediction Accuracy

Prediction of Gait Kinematics and Kinetics: A Systematic Review of EMG and EEG Signal Use and Their Contribution to Prediction Accuracy

Transferable Deep Learning Models for Accurate Ankle Joint Moment Estimation during Gait Using Electromyography

Contact Info

Product

Resources

About