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

Motion-Informed, Patient-Specific Femoral Localization for MPFL Reconstruction Using 4D-CT and Constrained Optimization.

Diagnostics (Basel, Switzerland)·2026
Same author

Spatiotemporal Dynamics Modeling of Brain Activity for Human-Robot Cognitive Interaction: A Distributed-Lumped Parameter System Framework.

IEEE transactions on neural networks and learning systems·2025
Same author

The attitudes and acceptance of functional assistive robots among older adults with disabilities: a mixed-methods study.

Innovation in aging·2025
Same author

A Dynamic Evaluation-Denoising Network for Motion Artifacts Removal from Single-Channel EEG.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

Optimal H<sub>∞</sub> tracking control of nonlinear systems with zero-equilibrium-free via novel adaptive critic designs.

Neural networks : the official journal of the International Neural Network Society·2023
Same author

Trajectory Modulation for Impact Reducing of Lower-Limb Exoskeletons.

Micromachines·2022

Related Experiment Video

Updated: Sep 23, 2025

The Muscle Cuff Regenerative Peripheral Nerve Interface for the Amplification of Intact Peripheral Nerve Signals
07:30

The Muscle Cuff Regenerative Peripheral Nerve Interface for the Amplification of Intact Peripheral Nerve Signals

Published on: January 13, 2022

2.2K

Multimodal Human-Exoskeleton Interface for Lower Limb Movement Prediction Through a Dense Co-Attention Symmetric

Kecheng Shi1, Fengjun Mu2, Rui Huang1

  • 1School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China.

Frontiers in Neuroscience
|May 13, 2022
PubMed
Summary

This study introduces a novel multimodal approach for predicting lower limb movements in hemiplegic patients using electroencephalogram (EEG) and surface electromyography (sEMG) signals. The proposed Dense con-attention mechanism-based Multimodal Enhance Fusion Network (DMEFNet) significantly improves prediction accuracy.

Keywords:
dense con-attention mechanismhemiplegia rehabilitation traininghuman-exoskeleton interfacelower limb movement predictionmultimodal

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

10.5K
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

9.6K

Related Experiment Videos

Last Updated: Sep 23, 2025

The Muscle Cuff Regenerative Peripheral Nerve Interface for the Amplification of Intact Peripheral Nerve Signals
07:30

The Muscle Cuff Regenerative Peripheral Nerve Interface for the Amplification of Intact Peripheral Nerve Signals

Published on: January 13, 2022

2.2K
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
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

9.6K

Area of Science:

  • Biomedical Engineering
  • Neuroscience
  • Rehabilitation Technology

Background:

  • Accurate lower limb movement prediction is crucial for human-exoskeleton interfaces in hemiplegia rehabilitation.
  • Single-modal biological signals like electroencephalogram (EEG) are unreliable for movement prediction.
  • Existing multimodal approaches combining EEG and surface electromyography (sEMG) overlook deep feature fusion and signal interconnections.

Purpose of the Study:

  • To propose a novel multimodal human-exoskeleton interface for enhanced lower limb movement prediction in patients with hemiplegia.
  • To address the limitations of current single-modal and multimodal interfaces by focusing on deep feature fusion between EEG and sEMG signals.
  • To introduce the Dense con-attention mechanism-based Multimodal Enhance Fusion Network (DMEFNet) for improved prediction accuracy.

Main Methods:

  • Development of the Dense con-attention mechanism-based Multimodal Enhance Fusion Network (DMEFNet).
  • Integration of electroencephalogram (EEG) and surface electromyography (sEMG) signals within the network.
  • Design of a data acquisition experiment and an incomplete asynchronous data collection paradigm to validate the model.
  • Utilizing con-attention structure to extract common attention between sEMG and EEG signal features.

Main Results:

  • The proposed DMEFNet demonstrated effective lower limb movement prediction in hemiplegic patients.
  • Achieved high prediction accuracy within-subject (82.96%) and cross-subject (88.44%) scenarios.
  • The con-attention mechanism successfully captured inter-modal attention between sEMG and EEG signals, enhancing feature fusion.
  • Validated the model's performance through a specifically designed experimental setup.

Conclusions:

  • DMEFNet offers a significant advancement in multimodal human-exoskeleton interfaces for hemiplegia rehabilitation.
  • The fusion of EEG and sEMG signals with a dense con-attention mechanism improves movement prediction accuracy.
  • This approach holds promise for more effective and personalized rehabilitation training for patients with hemiplegia.