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

Multichannel Optimization Strategy for Functional Electrical Stimulation in Grasp Gesture Restoration: A Pilot Study.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026
Same author

Cold-induced CaCYP links protein degradation and antioxidant defense via CabHLH-79 in Capsicum annuum.

Plant science : an international journal of experimental plant biology·2026
Same author

Cross-domain few-shot learning: A new perspective on overcoming bottlenecks in clinical artificial intelligence tumor diagnosis.

Chinese journal of cancer research = Chung-kuo yen cheng yen chiu·2026
Same author

Transparent cellulose films: Preparation, functionalization, and applications in food packaging.

Carbohydrate polymers·2026
Same author

Skin-inspired cellulose-based hydrogel design with hydrophobic-conductive synergy for enhanced electrochemical nanoplastic removal.

Carbohydrate polymers·2026
Same author

Bimodal iontronic skins powered by edge intelligence for real-time collaborative interaction.

National science review·2026

Related Experiment Video

Updated: Dec 30, 2025

Using a Split-belt Treadmill to Evaluate Generalization of Human Locomotor Adaptation
08:04

Using a Split-belt Treadmill to Evaluate Generalization of Human Locomotor Adaptation

Published on: August 23, 2017

8.6K

Unsupervised Cross-Subject Adaptation for Predicting Human Locomotion Intent.

Kuangen Zhang, Jing Wang, Clarence W de Silva

    IEEE Transactions on Neural Systems and Rehabilitation Engineering : a Publication of the IEEE Engineering in Medicine and Biology Society
    |January 17, 2020
    PubMed
    Summary

    This study introduces an unsupervised method to predict human locomotion intent without labeling data. This approach significantly reduces the burden on subjects and researchers, improving wearable robot control.

    More Related Videos

    Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior
    10:52

    Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior

    Published on: April 13, 2016

    9.1K
    Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine
    07:05

    Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

    Published on: October 27, 2016

    9.5K

    Related Experiment Videos

    Last Updated: Dec 30, 2025

    Using a Split-belt Treadmill to Evaluate Generalization of Human Locomotor Adaptation
    08:04

    Using a Split-belt Treadmill to Evaluate Generalization of Human Locomotor Adaptation

    Published on: August 23, 2017

    8.6K
    Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior
    10:52

    Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior

    Published on: April 13, 2016

    9.1K
    Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine
    07:05

    Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

    Published on: October 27, 2016

    9.5K

    Area of Science:

    • Robotics
    • Human-Computer Interaction
    • Machine Learning

    Background:

    • Predicting human locomotion intent is crucial for advanced wearable robot control and mobility assistance.
    • Traditional methods require extensive data labeling and subject-specific training, posing significant practical challenges.

    Purpose of the Study:

    • To develop an unsupervised cross-subject adaptation method for predicting human locomotion intent, reducing data labeling requirements.
    • To enhance user-independence in locomotion intent prediction for wearable robotic applications.

    Main Methods:

    • An unsupervised cross-subject adaptation technique was employed, utilizing source subject labeled data and target subject unlabeled data.
    • Two classifiers were designed to maximize classification discrepancy, coupled with a feature generator to align source and target subject features.
    • A neural network was trained using this adaptation method for locomotion intent prediction.

    Main Results:

    • The method achieved high classification accuracy (averaging 93.60% and 94.59%) on two public datasets in a leave-one-subject-out validation.
    • Demonstrated significant user-independence for locomotion intent classification without requiring target subject data labeling.

    Conclusions:

    • The unsupervised cross-subject adaptation method effectively predicts human locomotion intent with high accuracy and user-independence.
    • Future work will explore the application of this method for subjects with disabilities and for direct wearable robot control.