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: Jul 9, 2026

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Non-Contact Fall Detection System Using 4D Imaging Radar for Elderly Safety Based on a CNN Model.

Sejong Ahn1, Museong Choi2, Jongjin Lee2

  • 1Department of Computer Engineering, Tech University of Korea, Siheung 15073, Republic of Korea.

Sensors (Basel, Switzerland)
|September 19, 2025
PubMed
Summary

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

8-λ LAN-WDM TOSA for 800-Gb/s links with simplified, non-hermetic packaging.

Optics express·2026
Same author

Ensemble-Based Source Attribution of Fine Particulate Matter over South Korea during the ASIA-AQ/SIJAQ Campaign.

Environmental science & technology·2026
Same author

Measuring Network Sizes in the Context of Respondent Driven Sampling: Evidence from Two Independent Surveys.

Survey research methods·2026
Same author

Pre-incision structures reveal principles of DNA nucleotide excision repair.

Nature·2026
Same author

Doping-Enabled Symmetry Control in BaCoO<sub>3</sub> for Enhanced Oxygen Reduction Reaction.

Small (Weinheim an der Bergstrasse, Germany)·2025
Same author

Solvent Polarity Independent Symmetry-Breaking Charge Separation in a Slip-Stacked Covalent Terrylene Monoimide Dimer.

Journal of the American Chemical Society·2025

This study introduces a non-contact fall detection system using 4D imaging radar and AI. It accurately identifies falls and postures, offering a privacy-preserving alternative to wearable devices.

Area of Science:

  • Gerontology
  • Biomedical Engineering
  • Computer Science

Background:

  • Global population aging leads to more elderly individuals living alone.
  • Increased fall accidents among the elderly cause severe injuries, reduced quality of life, and higher medical costs.
  • Current fall detection methods, like wearables and cameras, have limitations such as discomfort and privacy concerns.

Purpose of the Study:

  • To develop a non-contact fall detection system using 4D imaging radar and artificial intelligence (AI).
  • To provide real-time monitoring, visualization, and immediate alerts for falls.
  • To address the limitations of existing fall detection technologies.

Main Methods:

  • Integration of 4D imaging radar sensors with AI technology for fall detection.
Keywords:
4D imaging radar sensorCNNelderly safetyfall detectionpoint cloud

More Related Videos

Using Motion Capture Technology in the Instrumented Timed Up and Go Test to Detect the Risk of Falling in Aged Adults
05:26

Using Motion Capture Technology in the Instrumented Timed Up and Go Test to Detect the Risk of Falling in Aged Adults

Published on: October 25, 2024

Related Experiment Videos

Last Updated: Jul 9, 2026

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Using Motion Capture Technology in the Instrumented Timed Up and Go Test to Detect the Risk of Falling in Aged Adults
05:26

Using Motion Capture Technology in the Instrumented Timed Up and Go Test to Detect the Risk of Falling in Aged Adults

Published on: October 25, 2024

  • Utilizing radar-generated Point Cloud data (spatial coordinates, velocity, Doppler power, time) for body position and movement analysis.
  • Employing a Convolutional Neural Network (CNN) model for posture classification (standing, sitting, lying) and fall detection, with data pre-processing using zero padding and k-means clustering.

    • Main Results:

    • The system achieved 98.66% accuracy in posture classification.
    • The system demonstrated 95% accuracy in fall detection.
    • The proposed system effectively detects falls without requiring wearable devices or cameras, thus preserving privacy.

    Conclusions:

    • The developed non-contact fall detection system is effective and accurate.
    • This technology offers a viable, privacy-conscious solution for elderly fall monitoring.
    • Future research could explore multi-sensor integration for enhanced indoor monitoring applications.