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

Engineering Supramolecular Metal-Organic Frameworks for Stable and Efficient Perovskite Quantum Dots by Defect Passivation and Heterostructure Construction.

ACS nano·2026
Same author

CDK1 Phosphorylates KAT8 at Ser348 to Stabilize the MSL Complex and Promote H4K16 Acetylation in Non-Small Cell Lung Cancer.

Cells·2026
Same author

GSTM1 upregulation contributes to ursolic acid-alleviated hepatic steatosis and liver injury in chronic alcohol-fed mice.

The Journal of nutritional biochemistry·2026
Same author

Early laboratory-based differentiation of severe influenza pneumonia and influenza-associated encephalopathy in children using a multi-model, stability-aware machine-learning workflow: a single-center retrospective cohort study.

BMC infectious diseases·2026
Same author

Physiological and metabolic orchestration during biphasic low-salinity adaptation in the mud crab (Scylla paramamosain): Insights into osmoregulation, lipid remodeling, and energy metabolism.

Comparative biochemistry and physiology. Part A, Molecular & integrative physiology·2026
Same author

Construction and Application of a Tactile Somatosensory Comfort Model for Scrubbing Tasks.

Biomimetics (Basel, Switzerland)·2026
Same journal

Autonomous Microrobots for Spatiotemporally Active Therapeutic Delivery and Controlled Release.

Cyborg and bionic systems (Washington, D.C.)·2026
Same journal

Optoelectronic Tweezers for Single-Cell Research: Principles, Applications, and Prospects‌.

Cyborg and bionic systems (Washington, D.C.)·2026
Same journal

Enhancing Shape Sensing of Slender Medical Continuum Robot Using Carbon Nanotube Piezoresistive Fiber Bandage.

Cyborg and bionic systems (Washington, D.C.)·2026
Same journal

Frequency-Specific Transcranial Photobiomodulation Elicits Complementary Glial Mechanisms for Neurovascular Protection and Amyloid Clearance in Alzheimer Disease.

Cyborg and bionic systems (Washington, D.C.)·2026
Same journal

Text Sequence Stimulation for High-Speed and Comfortable SSVEP-BCI.

Cyborg and bionic systems (Washington, D.C.)·2026
Same journal

Micro/Nanorobotic Systems for Imaging-Guided Closed-Loop Thrombus Recanalization.

Cyborg and bionic systems (Washington, D.C.)·2026
See all related articles

Related Experiment Video

Updated: May 9, 2025

Motor Dual-Tasks for Gait Analysis and Evaluation in Post-Stroke Patients
05:23

Motor Dual-Tasks for Gait Analysis and Evaluation in Post-Stroke Patients

Published on: March 11, 2021

2.3K

Lateral Walking Gait Recognition and Hip Angle Prediction Using a Dual-Task Learning Framework.

Mingxiang Luo1, Meng Yin1, Jinke Li1

  • 1Guangdong Provincial Key Lab of Robotics and Intelligent System, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.

Cyborg and Bionic Systems (Washington, D.C.)
|May 2, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces the "Twin Brother" model for accurate lateral walking gait recognition and hip angle prediction using electromyography (EMG) signals. The model significantly improves exoskeleton control by achieving high accuracy in classifying gait stages and estimating joint angles.

More Related Videos

Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task
11:18

Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task

Published on: June 1, 2015

10.6K
In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy
07:43

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy

Published on: July 2, 2021

2.9K

Related Experiment Videos

Last Updated: May 9, 2025

Motor Dual-Tasks for Gait Analysis and Evaluation in Post-Stroke Patients
05:23

Motor Dual-Tasks for Gait Analysis and Evaluation in Post-Stroke Patients

Published on: March 11, 2021

2.3K
Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task
11:18

Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task

Published on: June 1, 2015

10.6K
In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy
07:43

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy

Published on: July 2, 2021

2.9K

Area of Science:

  • Biomechanics and Biomedical Engineering
  • Machine Learning in Healthcare
  • Rehabilitation Robotics

Background:

  • Lateral walking enhances hip abductor strength, crucial for mobility.
  • Accurate gait recognition and hip joint angle prediction are vital for controlling assistive devices like exoskeletons.
  • Electromyography (EMG) signals offer a promising avenue for real-time biomechanical analysis.

Purpose of the Study:

  • To develop and validate a novel dual-task learning framework, the "Twin Brother" model.
  • To accurately classify lateral walking gait stages and estimate continuous hip joint angles from EMG signals.
  • To enhance the control capabilities of exoskeletons for improved rehabilitation and assistance.

Main Methods:

  • A dual-task learning framework fusing Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Neural Networks (NNs), and an attention mechanism was employed.
  • Electromyography (EMG) signals from six muscles of ten subjects during lateral walking were collected and analyzed.
  • The model was evaluated against traditional machine learning methods, including CNN-LSTM, CNN, LSTM, Support Vector Machine (SVM), NN, and K-Nearest Neighbors (KNN).

Main Results:

  • The "Twin Brother" model achieved a high gait recognition accuracy of 98.81% ± 0.14%.
  • Excellent hip angle prediction accuracy was demonstrated with Root Mean Square Errors (RMSE) of 0.9183° ± 0.024° (left) and 1.0511° ± 0.027° (right), and R² values of 0.9853 ± 0.006 and 0.9808 ± 0.008, respectively.
  • The model outperformed all comparative methods in both gait recognition and hip angle estimation tasks.

Conclusions:

  • The proposed "Twin Brother" model offers a robust and accurate solution for real-time lateral walking gait recognition and hip joint angle prediction.
  • This advancement holds significant potential for improving the precision and effectiveness of exoskeleton control systems.
  • The findings pave the way for more sophisticated human-robot interaction in rehabilitation and assistive technologies.