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

Bridging Perspectives: Guiding the Selection of Patient-Centered Outcomes in Rehabilitation Learning Health Systems.

Archives of physical medicine and rehabilitation·2026
Same author

Defining and Measuring Delays in Postacute Care: Toward a Standardized Definition of Rehabilitation Access.

Medical care·2026
Same author

Automated cell properties toolbox from 3D bioprinted hydrogel scaffolds via deep learning and optical coherence tomography.

Biomedical optics express·2026
Same author

Evaluation of multiple generative large language models on neurology board-style questions.

Frontiers in digital health·2026
Same author

Linking data to determine risk for 30-day readmissions in dementia.

The American journal of managed care·2026
Same author

Trends in Discharge to Institutional Post-Acute Care After Total Joint Arthroplasty in the United States and Canada.

Journal of the American Geriatrics Society·2025
Same journal

Optimizing Sensor and Data Selection on Lower Limbs via Deep Learning for Real-Time Human Activity Recognition.

IEEE transactions on human-machine systems·2026
Same journal

Bimanual Manipulation of Steady-Hand Eye Robots with Adaptive Sclera Force Control: Cooperative vs. Teleoperation Strategies.

IEEE transactions on human-machine systems·2026
Same journal

Palpation Characteristics of an Instrumented Virtual Cricothyroidotomy Simulator.

IEEE transactions on human-machine systems·2025
Same journal

A Single-Camera Method for Estimating Lift Asymmetry Angles Using Deep Learning Computer Vision Algorithms.

IEEE transactions on human-machine systems·2025
Same journal

User-Centered and Analytic-Based Approaches to Generate Usable Gestures for Individuals With Quadriplegia.

IEEE transactions on human-machine systems·2024
Same journal

SonoMyoNet: A Convolutional Neural Network for Predicting Isometric Force from Highly Sparse Ultrasound Images.

IEEE transactions on human-machine systems·2024
See all related articles

Related Experiment Video

Updated: Jun 28, 2025

A Rehabilitation Program of Exoskeleton-assisted Body Weight-Supported Treadmill Training with Non-immersive Virtual Reality for Stroke Patients
05:54

A Rehabilitation Program of Exoskeleton-assisted Body Weight-Supported Treadmill Training with Non-immersive Virtual Reality for Stroke Patients

Published on: May 16, 2025

160

Single-Belt Versus Split-Belt: Intelligent Treadmill Control via Microphase Gait Capture for Poststroke

Shengting Cao1, Mansoo Ko2, Chih-Ying Li2

  • 1Electrical and Computer Engineering, University of Alabama, Tuscaloosa, AL 35487 USA.

IEEE Transactions on Human-Machine Systems
|April 11, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces an AI system, "Splicer," that transforms a standard treadmill into a split-belt system for stroke rehabilitation. It enables cost-effective gait training by adjusting belt speed based on real-time gait phase detection.

Keywords:
Deep learninginter- and intragait classificationrehabilitationself-supervised learningsingle-beltsplit-belt treadmills

More Related Videos

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

10.4K
Use of a Foot-Induced Digitally Controlled Resistance Device for Functional Magnetic Resonance Imaging Evaluation in Patients with Foot Paresis
08:58

Use of a Foot-Induced Digitally Controlled Resistance Device for Functional Magnetic Resonance Imaging Evaluation in Patients with Foot Paresis

Published on: July 7, 2023

291

Related Experiment Videos

Last Updated: Jun 28, 2025

A Rehabilitation Program of Exoskeleton-assisted Body Weight-Supported Treadmill Training with Non-immersive Virtual Reality for Stroke Patients
05:54

A Rehabilitation Program of Exoskeleton-assisted Body Weight-Supported Treadmill Training with Non-immersive Virtual Reality for Stroke Patients

Published on: May 16, 2025

160
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

10.4K
Use of a Foot-Induced Digitally Controlled Resistance Device for Functional Magnetic Resonance Imaging Evaluation in Patients with Foot Paresis
08:58

Use of a Foot-Induced Digitally Controlled Resistance Device for Functional Magnetic Resonance Imaging Evaluation in Patients with Foot Paresis

Published on: July 7, 2023

291

Area of Science:

  • Biomedical Engineering
  • Rehabilitation Technology
  • Artificial Intelligence in Medicine

Background:

  • Stroke is a leading cause of long-term disability, necessitating effective rehabilitation strategies for hemiparesis.
  • Split-belt treadmills improve gait recovery but are prohibitively expensive for many clinics.
  • Current rehabilitation methods often lack cost-effective solutions for coordinated leg movement in hemiparetic patients.

Purpose of the Study:

  • To develop an AI-based system to simulate split-belt treadmill functionality on a single-belt treadmill.
  • To enable real-time, adaptive gait adjustments for improved post-stroke rehabilitation.
  • To provide a cost-effective alternative to expensive split-belt treadmills.

Main Methods:

  • Designed an AI system utilizing a low-cost RGB camera for gait pattern capture.
  • Implemented a novel microgait classification pipeline with self-supervised learning for real-time gait phase detection.
  • Employed a ResNet-LSTM module for temporal information processing and a real-time filtering algorithm for smooth treadmill control.

Main Results:

  • The developed system accurately detects gait microphases with reduced human annotation requirements compared to traditional classifiers.
  • The AI system, named "Splicer," effectively mimics split-belt treadmill functionality, adjusting foot speeds and promoting paretic side symmetry.
  • Testing with healthy individuals and stroke patients demonstrated comparable performance to actual split-belt systems.

Conclusions:

  • The AI-powered "Splicer" system offers a cost-effective solution for stroke rehabilitation by simulating split-belt treadmill benefits.
  • This technology has the potential to significantly improve accessibility to advanced gait training for hemiparetic patients.
  • The system's accuracy and reduced reliance on manual annotation represent a significant advancement in AI-driven rehabilitation tools.