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

A Contrastive Representation Learning Method for Event Classification in Φ-OTDR Systems.

Sensors (Basel, Switzerland)·2025

Same author

Formononetin Alleviates the Inflammatory Response Induced by Carotid Balloon Injury in Rats via the PP2A/MAPK Axis.

Immunological investigations·2025

Same author

Phenolic Components and Biological Activity of Pomegranate.

Chemistry & biodiversity·2024

Same author

Multifractal Characteristics Analysis of Spatial State of Prefecture-Level Cities in China.

Applied spatial analysis and policy·2023

Same author

ABCB-mediated shootward auxin transport feeds into the root clock.

EMBO reports·2023

Same author

Derivation of the toxicological threshold of silicon element in the extractables and leachables from the pharmaceutical packaging and process components.

Toxicology and industrial health·2022

Search research articles

Related Experiment Video

Updated: Jan 16, 2026

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

High-Accuracy Lower-Limb Intent Recognition: A KPCA-ISSA-SVM Approach with sEMG-IMU Sensor Fusion.

Kaiyang Yin¹, Pengchao Hao¹, Huanli Zhao¹

¹School of Electrical and Mechanical Engineering, Pingdingshan University, Pingdingshan 467000, China.

Biomimetics (Basel, Switzerland)

|September 26, 2025

Summary

This study introduces a novel framework using Kernel Principal Component Analysis (KPCA) and an Improved Sparrow Search Algorithm (ISSA) to optimize Support Vector Machines (SVM) for human locomotion intent recognition from physiological signals.

Keywords:

KPCA-ISSA-SVM human–machine rehabilitation devices locomotion intention recognition machine learning nonlinear dimensionality reduction sEMG-IMU fusion

More Related Videos

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Author Spotlight: Assessing Brain Activity in Robotic-Assisted Lower Limb Rehabilitation Using fNIRS

Author Spotlight: Assessing Brain Activity in Robotic-Assisted Lower Limb Rehabilitation Using fNIRS

Published on: June 7, 2024

Related Experiment Videos

Last Updated: Jan 16, 2026

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

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Author Spotlight: Assessing Brain Activity in Robotic-Assisted Lower Limb Rehabilitation Using fNIRS

Author Spotlight: Assessing Brain Activity in Robotic-Assisted Lower Limb Rehabilitation Using fNIRS

Published on: June 7, 2024

Area of Science:

Biomedical Engineering
Rehabilitation Technology
Human-Machine Interface

Background:

Decoding human locomotion intention from physiological signals is crucial for advanced rehabilitation devices.
Conventional methods struggle with the nonlinear dynamics of biological data, limiting accuracy.
Accurate intent recognition is key for intuitive control of exoskeletons and prosthetics.

Purpose of the Study:

To develop a novel and accurate framework for lower-limb motion intent recognition.
To address the limitations of conventional methods in capturing complex biological data dynamics.
To enhance the performance of human-machine systems for rehabilitation applications.

Main Methods:

Integrated Kernel Principal Component Analysis (KPCA) for nonlinear dimensionality reduction.
Employed an Improved Sparrow Search Algorithm (ISSA) for optimizing Support Vector Machine (SVM) hyperparameters.
Utilized synchronized surface electromyography (sEMG) and inertial measurement unit (IMU) data for feature extraction.

Main Results:

The proposed KPCA-ISSA-SVM framework achieved 95.35% offline and 93.3% online recognition accuracy.
Demonstrated superior performance compared to conventional PCA-SVM (91.85%) and standalone SVM (89.76%).
Effectively handled nonlinear coupling characteristics of sEMG-IMU data and complex motion patterns.

Conclusions:

The KPCA-ISSA-SVM architecture offers a robust and significantly more accurate solution for intention perception.
This framework advances the development of more intuitive and effective rehabilitation technologies.
The study highlights the potential of advanced machine learning techniques for decoding complex physiological signals.