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

Physical activity and health-related quality of life in Korean postmenopausal women with and without chronic diseases: a population-based study using the KNHANES 2016-2020 database.

Menopause (New York, N.Y.)·2026

Same author

Prediction Model for Low Bone Mineral Density in Cancer Survivors and Age-Matched Controls Using a Causal Bayesian Network: A Nationwide Population-Based Study in Korea.

Clinical Medicine Insights. Oncology·2026

Same author

Association of Multiple-trait Polygenic Risk Score with Obesity and Cardiometabolic Diseases in Korean Population.

Genomics, proteomics & bioinformatics·2025

Same author

Effects of NSAIDs on Early CKD Development: A 10-Year Population-Based Study Using the Korean Senior Cohort.

Drugs & aging·2025

Same author

Associations of dietary patterns and lower urinary tract symptoms (LUTS) in Korean adults.

Nutrition research and practice·2025

Same author

Anthropometric Changes in Female Participants Enrolled in a Combined Aerobic and Resistance Training Program for Longer than 1 Year: A Cohort Study.

Journal of obesity & metabolic syndrome·2024

Search research articles

Related Experiment Video

Updated: Jun 15, 2025

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Published on: September 8, 2023

Recognition of Forward Head Posture Through 3D Human Pose Estimation With a Graph Convolutional Network: Development

Haedeun Lee¹, Bumjo Oh^2,3, Seung-Chan Kim¹

¹Machine Learning Systems Laboratory, School of Sports Science, Sungkyunkwan University, Suwon, Gyunggi-do, Republic of Korea.

JMIR Formative Research

|August 26, 2024

Summary

Forward head posture (FHP) can cause pain and fatigue. A new system uses 3D pose estimation and graph convolutional networks (GCN) to detect FHP from 2D images, enabling posture correction.

Keywords:

algorithms deep learning forward head posture graph graph convolutional networks graph neural network human pose estimation injury prediction machine learning neural network neural networks pose postural posture posture correction upper

More Related Videos

Author Spotlight: Automated Deep Brain Stimulation for Parkinson's Disease - Exploring the Possibilities and Challenges of Home Monitoring

Author Spotlight: Automated Deep Brain Stimulation for Parkinson's Disease - Exploring the Possibilities and Challenges of Home Monitoring

Published on: July 14, 2023

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

Related Experiment Videos

Last Updated: Jun 15, 2025

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Published on: September 8, 2023

Author Spotlight: Automated Deep Brain Stimulation for Parkinson's Disease - Exploring the Possibilities and Challenges of Home Monitoring

Author Spotlight: Automated Deep Brain Stimulation for Parkinson's Disease - Exploring the Possibilities and Challenges of Home Monitoring

Published on: July 14, 2023

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

Area of Science:

Biomedical Engineering
Computer Vision
Human-Computer Interaction

Background:

Prolonged improper posture, particularly forward head posture (FHP), is linked to headaches, fatigue, and respiratory issues.
Sedentary lifestyles exacerbate FHP due to extended static posture maintenance.
Current FHP diagnosis relies on impractical clinical methods, necessitating real-time, accessible assessment tools.

Purpose of the Study:

To develop an accessible and efficient system for real-time detection of forward head posture (FHP).
To enable continuous posture assessment and provide corrective feedback for public health benefits.
To overcome limitations of existing pose estimation models in measuring the craniovertebral angle for FHP diagnosis.

Main Methods:

Sequential estimation of 2D and 3D human key points using Detectron2D and VideoPose3D algorithms.
Utilized a graph convolutional network (GCN) to analyze the spatial configuration of upper body key points in 3D.
Trained the GCN to implicitly learn FHP indicators from 3D anatomical key point data.

Main Results:

The GCN model achieved 78.27% test accuracy using upper body key points.
GCN demonstrated superior balanced performance (F1-score macro: 77.54%) compared to a baseline feedforward neural network (75.88%).
GCN exhibited better generalization and balanced precision/recall for FHP detection across diverse postures.

Conclusions:

A GCN-based network can learn FHP-related features from 2D images via 3D pose estimation for posture correction systems.
The developed system shows potential for practical application in posture monitoring and correction.
Future work will address system limitations and explore further advancements in FHP detection.