Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Systematic analysis of success of lower limb muscle combinations in the prediction of ankle biomechanics during stair descent: Guiding input selection in sEMG-based prosthetic control.

Gait & posture·2026
Same author

Prediction of ankle kinematics and kinetics in stair ascent motion using surface EMG feature inputs of lower extremity muscle combinations.

Journal of biomechanics·2026
Same author

Synergistic muscle activation impacts muscle spindles projecting to the mouse trigeminal mesencephalic nucleus.

Journal of neurophysiology·2025
Same author

Contactless measurement of muscle fiber conduction velocity-a novel approach using optically pumped magnetometers.

Journal of neural engineering·2025
Same author

Neurochallenges in smart cities: state-of-the-art, perspectives, and research directions.

Frontiers in neuroscience·2025
Same author

Biochemical, biomechanical and imaging biomarkers of ischemic stroke: Time for integrative thinking.

The European journal of neuroscience·2024

Related Experiment Video

Updated: Jul 23, 2025

Engineering Platform and Experimental Protocol for Design and Evaluation of a Neurally-controlled Powered Transfemoral Prosthesis
11:16

Engineering Platform and Experimental Protocol for Design and Evaluation of a Neurally-controlled Powered Transfemoral Prosthesis

Published on: July 22, 2014

16.3K

The use of nonnormalized surface EMG and feature inputs for LSTM-based powered ankle prosthesis control algorithm

Ahmet Doğukan Keleş1,2, Ramazan Tarık Türksoy1,3, Can A Yucesoy1

  • 1Institute of Biomedical Engineering, Boğaziçi University, Istanbul, Türkiye.

Frontiers in Neuroscience
|July 19, 2023
PubMed
Summary

This study developed new control algorithms for powered ankle prostheses using nonnormalized surface electromyogram (sEMG) data. The findings enable more practical and economical prosthetic control for amputees.

Keywords:
feature extractionlong short-term memory neural networklower limb amputationpowered ankle prosthesissurface electromyogram (sEMG)

More Related Videos

A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study
06:58

A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study

Published on: November 6, 2015

9.5K
A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation
11:06

A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation

Published on: April 12, 2016

10.5K

Related Experiment Videos

Last Updated: Jul 23, 2025

Engineering Platform and Experimental Protocol for Design and Evaluation of a Neurally-controlled Powered Transfemoral Prosthesis
11:16

Engineering Platform and Experimental Protocol for Design and Evaluation of a Neurally-controlled Powered Transfemoral Prosthesis

Published on: July 22, 2014

16.3K
A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study
06:58

A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study

Published on: November 6, 2015

9.5K
A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation
11:06

A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation

Published on: April 12, 2016

10.5K

Area of Science:

  • Biomedical Engineering
  • Rehabilitation Engineering
  • Neuroprosthetics

Background:

  • Powered ankle prostheses require advanced control algorithms for natural ambulation.
  • Current algorithms face limitations in sensor integration and autonomous adaptation.
  • Surface electromyogram (sEMG) offers a promising, economical, and practical solution for prosthetic control.

Purpose of the Study:

  • To develop and assess algorithms predicting sagittal ankle position and moment using nonnormalized sEMG.
  • To identify optimal muscle and feature combinations for economic and practical prosthetic control.
  • To establish the feasibility of using nonnormalized sEMG data in real-time prosthetic control.

Main Methods:

  • Utilized a long-short-term memory (LSTM) neural network architecture with eight lower extremity muscles' sEMG data.
  • Extracted five features (IEMG, MAV, WAMP, RMS, WL) from nonnormalized sEMG amplitudes.
  • Ranked muscle and feature combinations using Pearson's correlation coefficient and root-mean-square error.

Main Results:

  • The combination of integrated EMG (IEMG) and waveform length (WL) demonstrated the best feature performance.
  • Medial gastrocnemius (MG), rectus femoris (RF), and vastus medialis (VM) showed the highest predictive success for position and moment.
  • Peroneus longus (PL) and gluteus maximus (GMax)+VM were identified as economical and practical variations, respectively.

Conclusions:

  • Nonnormalized sEMG data can be effectively used for developing control algorithms in powered ankle prostheses.
  • The study provides a systematic approach to selecting sEMG sensors for practical and economical prosthetic applications.
  • This research paves the way for more autonomous and natural-feeling prosthetic ambulation.