Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

The leg-swing interface: a novel approach to seated VR locomotion with balanced immersion and physical load.

Scientific reports·2026

Same author

Patient-independent hybrid generative-discriminative modeling for seizure detection in long-term scalp EEG.

Scientific reports·2026

Same author

Target delivery of brain-derived neurotrophic factor using magnetic stimulation in subacute stroke.

Biomedicine & pharmacotherapy = Biomedecine & pharmacotherapie·2026

Same author

Vision-Based Artificial Intelligence for Adaptive Peen Forming: Sensing Architectures, Learning Models, and Closed-Loop Smart Manufacturing.

Sensors (Basel, Switzerland)·2026

Same author

DKK1 Suppresses Hippo Signaling via PIP<sub>3</sub>-OGT-LRP6 <i>O</i>-GlcNAcylation in Hepatocellular Carcinoma.

Cancer communications (London, England)·2026

Same author

The nuclear cap-binding complex safeguards stress-resistant protein synthesis and proliferation of stem cells.

Science advances·2026

Same journal

Ultrasound-Informed State Estimation of Wrist Tremor Dynamics via Koopman Operator for Personalized Sensory Peripheral Nerve Stimulation.

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

Same journal

Motion Intention Recognition and DDPG-Based Adaptive Impedance Control for a Robotic Upper-Limb Exoskeleton.

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

Same journal

CNN-Based Modelling Reveals Temporal Brain Dynamics of Auditory Intensity Processing.

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

Same journal

Pathology-Informed Augmentation Improves Cross-Cohort IMU-to-vGRF Estimation Between Healthy Adults and Adults With Osteoarthritis.

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

Same journal

Effects of task-driven head orientations on gait and balance during walking in virtual reality.

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

Same journal

Wearable sensor-based Mild Cognitive Impairment Identification: A Multi-Domain Gait Analysis Approach with Association Rule Mining.

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

See all related articles

Search research articles

Related Experiment Video

Updated: Aug 3, 2025

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

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

Published on: April 12, 2016

A Machine Learning-Based Initial Difficulty Level Adjustment Method for Balance Exercise on a Trunk Rehabilitation

Hosu Lee, Yunho Choi, Amre Eizad

IEEE Transactions on Neural Systems and Rehabilitation Engineering : a Publication of the IEEE Engineering in Medicine and Biology Society

|April 8, 2023

Summary

This summary is machine-generated.

A machine learning method automatically adjusts trunk rehabilitation robot difficulty for patients with balance issues. This approach enhances exercise personalization and improves patient outcomes in rehabilitation settings.

More Related Videos

A Vibrotactile Feedback Device for Seated Balance Assessment and Training

A Vibrotactile Feedback Device for Seated Balance Assessment and Training

Published on: January 20, 2019

Author Spotlight: Enhancing Post-Stroke Upper Limb Rehabilitation with Robotic Technologies for Improved Motor Recovery and Functional Outcomes

Author Spotlight: Enhancing Post-Stroke Upper Limb Rehabilitation with Robotic Technologies for Improved Motor Recovery and Functional Outcomes

Published on: September 6, 2024

Related Experiment Videos

Last Updated: Aug 3, 2025

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

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

Published on: April 12, 2016

A Vibrotactile Feedback Device for Seated Balance Assessment and Training

A Vibrotactile Feedback Device for Seated Balance Assessment and Training

Published on: January 20, 2019

Author Spotlight: Enhancing Post-Stroke Upper Limb Rehabilitation with Robotic Technologies for Improved Motor Recovery and Functional Outcomes

Author Spotlight: Enhancing Post-Stroke Upper Limb Rehabilitation with Robotic Technologies for Improved Motor Recovery and Functional Outcomes

Published on: September 6, 2024

Area of Science:

Rehabilitation Engineering
Robotics in Medicine
Machine Learning Applications

Background:

Trunk rehabilitation exercises improve seated balance and gait in patients with neurological conditions like stroke.
Current methods lack automated systems for adjusting exercise difficulty on trunk rehabilitation robots (TRRs).
Personalized difficulty adjustment is crucial for optimizing patient recovery and engagement.

Purpose of the Study:

To develop and validate a machine learning (ML)-based method for automatically determining exercise difficulty on a TRR.
To predict the optimal virtual damping gain (Dvirtual) for TRR's unstable training mode based on patient data.
To assess the efficacy of the ML-driven difficulty adjustment in real-world training scenarios.

Main Methods:

A machine learning model was trained using data from 37 healthy adults, incorporating demographic information, balancing ability, and training sequence.
The model predicted the virtual damping gain (Dvirtual) to control exercise difficulty.
Model performance was validated using leave-one-out cross-validation and tested on 25 separate healthy adults.

Main Results:

The ML model achieved 80.90% average accuracy (R2 score) in predicting desired difficulty levels, quantified by Mean Velocity Displacement (MVD).
Statistical analysis showed no significant difference between ground truth and predicted difficulty levels across Hard, Medium, and Easy modes.
Predicted Dvirtual significantly reduced performance variability (standard deviation) by up to 41.39% and influenced balance performance metrics like Planar Deviation (PD).

Conclusions:

The proposed ML-based method effectively and automatically adjusts TRR exercise difficulty.
This approach has significant potential for personalizing rehabilitation for individuals with diverse balancing abilities.
Automated difficulty adjustment can enhance the efficiency and effectiveness of trunk rehabilitation.