Search research articles

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

EEG-RCPNet: a cross-subject cognitive impairment detection model based on limited-channel eeg signals.

Medical & biological engineering & computing·2026

Same author

SMMTM: Motor imagery EEG decoding algorithm using a hybrid multi-branch separable convolutional self-attention temporal convolutional network.

PloS one·2025

Same author

First true blood pressure measurement with micropulse detection of arterial opening achieved.

Scientific reports·2025

Same author

Preventing troublesome variability in clinical blood pressure measurement.

Journal of human hypertension·2024

Same author

Assessment of arteriosclerosis based on lognormal fitting.

Physiological measurement·2024

Same author

Enhancing Patient Selection in Sepsis Clinical Trials Design Through an AI Enrichment Strategy: Algorithm Development and Validation.

Journal of medical Internet research·2024

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

Search research articles

Related Experiment Video

Updated: Oct 18, 2025

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

Action Recognition of Lower Limbs Based on Surface Electromyography Weighted Feature Method.

Jiashuai Wang¹, Dianguo Cao¹, Jinqiang Wang¹

¹School of Engineering, Qufu Normal University, Rizhao 276826, China.

Sensors (Basel, Switzerland)

|September 28, 2021

Summary

This study introduces a novel weighted feature method and an improved genetic algorithm-support vector machine (IGA-SVM) to enhance lower limb action recognition using surface electromyography (sEMG). The proposed approach achieves a high average recognition rate of 94.75%.

Keywords:

action recognition championship and sorting surface electromyography weighted feature method

More Related Videos

Standing Neurophysiological Assessment of Lower Extremity Muscles Post-Stroke

Standing Neurophysiological Assessment of Lower Extremity Muscles Post-Stroke

Published on: July 26, 2021

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

Related Experiment Videos

Last Updated: Oct 18, 2025

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

Standing Neurophysiological Assessment of Lower Extremity Muscles Post-Stroke

Standing Neurophysiological Assessment of Lower Extremity Muscles Post-Stroke

Published on: July 26, 2021

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

Area of Science:

Biomedical Engineering
Rehabilitation Technology
Human-Computer Interaction

Background:

Surface electromyography (sEMG) is crucial for non-invasive lower limb action recognition.
Traditional feature extraction methods often suffer from high redundancy and low discrimination.
Genetic algorithms (GAs) can be prone to local optima in optimization tasks.

Purpose of the Study:

To enhance the recognition accuracy of lower limb actions using sEMG data.
To address the limitations of feature redundancy and discrimination in sEMG analysis.
To improve the robustness of genetic algorithms in machine learning applications.

Main Methods:

A weighted feature method was developed, leveraging muscle-action correlations to improve feature selection.
An improved genetic algorithm (IGA) was integrated with a support vector machine (SVM), employing a championship sorting method to avoid local optima.
The proposed IGA-SVM model was applied to recognize six distinct lower limb actions.

Main Results:

The weighted feature method effectively reduced redundancy and improved feature discrimination.
The championship sorting method in the IGA prevented premature convergence to suboptimal solutions.
The combined IGA-SVM model achieved an average recognition rate of 94.75% for lower limb actions.

Conclusions:

The proposed weighted feature method and IGA-SVM offer a promising solution for accurate lower limb action recognition.
This approach demonstrates significant potential for applications in areas like prosthetics, exoskeletons, and human-robot interaction.
Further research can explore the scalability and adaptability of this method to more complex actions and diverse populations.