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 Experiment Video

Updated: Sep 26, 2025

Using Virtual Reality to Transfer Motor Skill Knowledge from One Hand to Another
05:12

Using Virtual Reality to Transfer Motor Skill Knowledge from One Hand to Another

Published on: September 18, 2017

546.9K

Application of Unsupervised Transfer Technique Based on Deep Learning Model in Physical Training.

Quanbin Zhao1, Hanqi Wang1

  • 1Department of Leisure Sports Teaching and Research Office, Shenyang Sport University, Shenyang 110102, Liaoning, China.

Computational Intelligence and Neuroscience
|April 25, 2022
PubMed
Summary

This study introduces a deep learning model for standardizing physical training actions, improving accuracy by 1.69% compared to traditional methods. The findings offer theoretical support for correcting training errors.

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

FPR2 deficiency alleviates LPS-induced depressive-like behaviors in mice by suppressing the microglial CSF1/NLRP3 inflammasome pathway.

Journal of neuroinflammation·2026
Same author

Total Synthesis of Marine Natural Product Sunshinamide via Macrolactonization.

Archiv der Pharmazie·2026
Same author

Efficacy and Safety of Ciprofol Versus Propofol for Anesthesia in Older Patients: A Systematic Review and Meta-Analysis of Randomized Controlled Trials.

Drugs & aging·2026
Same author

Ductile and scalable 3 GPa steel via a hierarchical microstructural architecture.

Nature communications·2026
Same author

Discovery of CZL-149: A Novel, Highly Potent, and Orally Bioavailable Dual Inhibitor Targeting BET and p300/CBP Bromodomains with Strong Antitumor Efficacy.

Journal of medicinal chemistry·2026
Same author

The efficacy and safety of four different PD-1 checkpoint inhibitors in advanced non-small cell lung cancer: a real-world retrospective study.

Frontiers in oncology·2026

Area of Science:

  • Sports Science
  • Biomechanical Analysis
  • Artificial Intelligence in Sports

Background:

  • Standardization and scientific accuracy of physical training actions are crucial for effectiveness and injury prevention.
  • Existing methods for analyzing and correcting training actions often lack precision and adaptability.

Purpose of the Study:

  • To develop and evaluate a deep learning model for the standardization and scientization of physical training actions.
  • To analyze the importance of action standardization in physical training.
  • To improve the discrimination accuracy of physical training actions.

Main Methods:

  • Utilized a stacked denoising autoencoder (SDAE) combined with a BiLSTM deep network model (SDAL-DNM).
  • Implemented an unsupervised transfer model based on the SDAL-DNM deep learning architecture.

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K

Related Experiment Videos

Last Updated: Sep 26, 2025

Using Virtual Reality to Transfer Motor Skill Knowledge from One Hand to Another
05:12

Using Virtual Reality to Transfer Motor Skill Knowledge from One Hand to Another

Published on: September 18, 2017

546.9K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K
  • Collected and analyzed movement data from five physical training actions to assess trainer performance and identify action differences.

    • Main Results:

    • The proposed SDAL-DNM model demonstrated an average decline of 1.69% before and after unsupervised learning.
    • The unsupervised transfer model showed superior performance compared to the extreme learning machine (ELM), which had an average decline of 5.5%.
    • The model effectively distinguished between different trainers' actions, enabling continuous adaptation.

    Conclusions:

    • The unsupervised transfer model significantly enhances the discrimination accuracy of physical training actions.
    • This research provides a theoretical foundation for effectively correcting errors in physical training execution.
    • The developed deep learning approach offers a promising tool for optimizing physical training standardization.