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

MRASM: A multiscale residual attention spatiotemporal model for breast tumor prediction.

Magnetic resonance imaging·2025
Same author

Soil moisture and ecosystem vegetation health effects on drought severity.

Journal of advanced research·2025
Same author

Integrating Network Pharmacology and Experimental Validation to Elucidate the Mechanisms of Tang Shen Ping Decoction in Diabetic Kidney Disease.

ACS omega·2025
Same author

A missense mutation in <i>Muc2</i> promotes gut microbiome- and metabolome-dependent colitis-associated tumorigenesis.

bioRxiv : the preprint server for biology·2025
Same author

Personalized ultraviolet A1 phototherapy strategies for steroid-refractory hand-foot eczema: A prospective study.

Journal of the American Academy of Dermatology·2025
Same author

Efficient estimation of plant species diversity in desert regions using UAV-based quadrats and advanced machine learning techniques.

Journal of environmental management·2025

Related Experiment Video

Updated: Sep 20, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.2K

Applying Deep Learning-Based Human Motion Recognition System in Sports Competition.

Liangliang Zhang1

  • 1Academy of Sports and Leisure, Xi'an Physical Education University, Xi'an, China.

Frontiers in Neurorobotics
|June 7, 2022
PubMed
Summary

A new deep learning algorithm improves human motion recognition (HMR) for sports, outperforming traditional methods on large datasets and subtle movements. This kernel extreme learning machine approach enhances accuracy and efficiency in sports analysis.

Keywords:
convolutional neural networkdata setdeep learninghuman motion recognitionrecognition ratesports

More Related Videos

Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography
04:06

Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography

Published on: January 12, 2024

719
An Inertial Measurement Unit Based Method to Estimate Hip and Knee Joint Kinematics in Team Sport Athletes on the Field
06:52

An Inertial Measurement Unit Based Method to Estimate Hip and Knee Joint Kinematics in Team Sport Athletes on the Field

Published on: May 26, 2020

8.1K

Related Experiment Videos

Last Updated: Sep 20, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.2K
Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography
04:06

Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography

Published on: January 12, 2024

719
An Inertial Measurement Unit Based Method to Estimate Hip and Knee Joint Kinematics in Team Sport Athletes on the Field
06:52

An Inertial Measurement Unit Based Method to Estimate Hip and Knee Joint Kinematics in Team Sport Athletes on the Field

Published on: May 26, 2020

8.1K

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Sports Science

Background:

  • Traditional human motion recognition (HMR) systems struggle with large datasets and recognizing subtle micromotions.
  • Deep learning (DL) offers potential for HMR improvement, particularly in sports contexts.
  • Existing DL methods like CNN and C3D have limitations in complex motion analysis.

Purpose of the Study:

  • To develop an improved HMR algorithm for sports competition using deep learning.
  • To address the performance limitations of traditional HMR systems on large-scale data and micromotions.
  • To propose a novel HMR algorithm based on kernel extreme learning machine (KELM) with multidimensional feature fusion (MFF).

Main Methods:

  • Proposed a novel HMR algorithm integrating kernel extreme learning machine (KELM) with multidimensional feature fusion (MFF).
  • Conducted simulation experiments to evaluate the KELM-MFF-based HMR algorithm's performance against other leading methods.
  • Compared recognition rates across different algorithms, including SVM-MFF, CNN-T, IDT, C3D, and CNN.

Main Results:

  • The KELM-MFF-based HMR algorithm demonstrated superior recognition rates compared to SVM-MFF, CNN-T, IDT, C3D, and CNN.
  • Achieved high recognition rates of 92.4% (early fusion) and 92.1% (late fusion), surpassing SVM-MFF (91.8% and 90.5%).
  • The algorithm exhibited efficient training (30s) and testing (15s) times, with color dimension features outperforming time dimension features by up to 24%.

Conclusions:

  • The proposed KELM-MFF-based HMR algorithm effectively handles large-scale datasets and accurately recognizes micromotions in sports.
  • This DL-based approach offers a significant advancement for HMR in sports competition analysis.
  • The research provides valuable insights into applying extreme learning machine algorithms for enhanced sports performance monitoring.