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

Circulating exosomes convey the cognitive benefits of Tai Chi: The role of miR-625-5p in prefrontal remodeling and therapeutic potential.

Neural regeneration research·2026
Same author

Electroacupuncture Improves the Learning and Memory by Modulating Hippocampal Glucose Metabolism through IGF1/IGF1R Signaling in Alzheimer's Disease.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Electroacupuncture improves spatial learning and memory functions in triple-transgenic Alzheimer's disease model mice by enhancing glutamatergic synapse plasticity in the entorhinal cortex-hippocampal CA1 circuit.

Neural regeneration research·2026
Same author

Tai Chi Chuan Auxiliary Training Systems in Health and Rehabilitation: Scoping Review.

Journal of medical Internet research·2025
Same author

Muscle-Derived Small Extracellular Vesicles Mediate Exercise-Induced Cognitive Protection in Chronic Cerebral Hypoperfusion.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2025
Same author

Clinical practice guidelines and expert consensus statements on rehabilitation for patients with COVID-19: a systematic review.

BMJ open·2024
Same journal

Effects of Telerehabilitation Based on Motion Recognition Technology on Exercise Endurance of Patients With Non-Small Cell Lung Cancer After Surgery: Single-Center, Prospective, Open-Label, Randomized Controlled Trial.

JMIR mHealth and uHealth·2026
Same journal

Feasibility and Acceptability of mPallCare<i>,</i> a Digital Health Intervention for People Living With Advanced Cancer in a Refugee Settlement in Uganda: Mixed Methods Study.

JMIR mHealth and uHealth·2026
Same journal

Feasibility and Preliminary Efficacy of a "Sit Less" Program Leveraging Fitbit Tracking and Tailored Text Messages in Cardiometabolic Disease: Findings from Two Parallel Randomized Controlled Trials in Coronary Artery Disease and Type 2 Diabetes.

JMIR mHealth and uHealth·2026
Same journal

Long-Term Effectiveness of Unguided Internet-Based Cognitive Behavioral Therapy on Major Depressive Disorder in Chinese Adults: Randomized Controlled Trial With a 12-Month Follow-Up.

JMIR mHealth and uHealth·2026
Same journal

Gait Analysis for Identifying Normal Cognition, Subjective Cognitive Decline, and Mild Cognitive Impairment in Parkinson Disease: Diagnostic Study.

JMIR mHealth and uHealth·2026
Same journal

Enhancing Cognitive Functions of Older Adults With Software Robot: Longitudinal Exploratory Field Study.

JMIR mHealth and uHealth·2026
See all related articles

Related Experiment Video

Updated: Oct 21, 2025

Author Spotlight: Enhancing Upper Limb Rehabilitation in Stroke Patients Through Advanced Robotic and Neuromodulation Technologies
05:28

Author Spotlight: Enhancing Upper Limb Rehabilitation in Stroke Patients Through Advanced Robotic and Neuromodulation Technologies

Published on: October 11, 2024

780

Upper-Limb Motion Recognition Based on Hybrid Feature Selection: Algorithm Development and Validation.

Qiaoqin Li1, Yongguo Liu1, Jiajing Zhu1

  • 1Knowledge and Data Engineering Laboratory of Chinese Medicine, School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China.

JMIR Mhealth and Uhealth
|September 2, 2021
PubMed
Summary
This summary is machine-generated.

This study introduces FESCOM, a hybrid feature selection method for upper-limb exercise recognition, significantly reducing computation time while maintaining high accuracy. The approach enhances motion recognition in rehabilitation systems using wearable sensors.

Keywords:
feature selectioninertial measurement unitmachine learningmotion recognitionrehabilitation exercises

More Related Videos

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.9K
Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
08:15

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

Published on: March 28, 2025

854

Related Experiment Videos

Last Updated: Oct 21, 2025

Author Spotlight: Enhancing Upper Limb Rehabilitation in Stroke Patients Through Advanced Robotic and Neuromodulation Technologies
05:28

Author Spotlight: Enhancing Upper Limb Rehabilitation in Stroke Patients Through Advanced Robotic and Neuromodulation Technologies

Published on: October 11, 2024

780
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.9K
Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
08:15

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

Published on: March 28, 2025

854

Area of Science:

  • Biomechanics and Rehabilitation Engineering
  • Machine Learning and Signal Processing
  • Wearable Sensor Technology

Background:

  • Automatic exercise recognition is crucial for rehabilitation systems, especially for unsequented exercises.
  • Current motion recognition relies on feature engineering and machine learning, facing challenges with high-dimensional data.
  • Existing feature selection methods (filter and wrapper) have limitations in performance and computational cost.

Purpose of the Study:

  • To develop an improved feature selection method for upper-limb exercise motion recognition.
  • To enhance the performance and efficiency of motion recognition systems.

Main Methods:

  • A hybrid feature selection method (FESCOM) combining filter and wrapper approaches was proposed.
  • Data from 5 upper-limb exercises by 21 participants using an inertial measurement unit (IMU) were collected.
  • FESCOM utilized filter-based candidate selection followed by wrapper-based refinement using kNN, NB, and RF classifiers.

Main Results:

  • FESCOM achieved low classification error rates: 1.7% (kNN), 8.9% (NB), and 7.4% (RF).
  • Feature selection time was significantly reduced: 13s (kNN), 71s (NB), 541s (RF) per iteration.
  • FESCOM demonstrated superior recognition performance compared to traditional wrapper methods, especially with kNN and NB.

Conclusions:

  • The FESCOM method effectively improves upper-limb motion recognition accuracy and efficiency.
  • It offers a computationally efficient alternative to traditional feature selection methods.
  • The approach is adaptable for broader applications in motion recognition with diverse datasets.