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

Assessing the reliability and validity of a standardized rubric for staff evaluation of all-ceramic crown preparations at preclinical setting.

BMC medical education·2026
Same author

Joint UAV trajectory and offloading optimization with robust secrecy for intelligent mining.

Scientific reports·2026
Same author

Anterior loop of the mental nerve: a cone-beam computed tomography analysis of its prevalence and surgical implications in implant dentistry.

Folia morphologica·2026
Same author

Long-term relief of CRPS-associated limb dystonia with ketamine infusion.

BMJ case reports·2026
Same author

Harnessing multi-modal deep learning for multi-drone navigation-based trajectory prediction system.

Scientific reports·2026
Same author

Laser-Based Interventions for Preventing and Managing Osteoradionecrosis of the Jaw After Head and Neck Radiotherapy: A Systematic Review.

Cureus·2026

Related Experiment Video

Updated: Jan 9, 2026

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

5.2K

Artificial Intelligence-based fine-tuning model for fall activity recognition in disabled persons within an IoT

Abdulrahman Alzahrani1,2, Reham Al-Dayil3, Amirah Ghanim Alghanim4

  • 1Department of Computer Science and Engineering, College of Computer Science and Engineering, University of Hafr Al Batin, Hafar Al Batin, Saudi Arabia. aalzahrani@uhb.edu.sa.

Scientific Reports
|December 1, 2025
PubMed
Summary

This study introduces a new system for detecting falls in disabled individuals using Artificial Intelligence (AI) and the Internet of Things (IoT). The Temporal Convolutional Network-Based Fall Activity Recognition System for Disabled Persons (TCN-FARSDP) achieved 99.48% accuracy.

Keywords:
Disabled personsFall activity recognitionFusion modelsInternet of thingsTemporal convolutional network

More Related Videos

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

9.3K
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

11.1K

Related Experiment Videos

Last Updated: Jan 9, 2026

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

5.2K
Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

9.3K
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

11.1K

Area of Science:

  • Computer Science, Artificial Intelligence
  • Biomedical Engineering
  • Healthcare Technology

Background:

  • Remote monitoring and fall detection are critical in telemedicine for disabled individuals.
  • Existing fall detection methods struggle with accuracy due to complex human movements.
  • Internet of Things (IoT) and Artificial Intelligence (AI) are increasingly used in healthcare for automated condition detection.

Purpose of the Study:

  • To present a novel Temporal Convolutional Network-Based Fall Activity Recognition System for Disabled Persons (TCN-FARSDP).
  • To enhance the safety and well-being of disabled individuals through accurate fall incident detection.
  • To develop a system deployable within an IoT environment for continuous monitoring.

Main Methods:

  • Image pre-processing using Gaussian filtering (GF) for noise reduction and clarity enhancement.
  • Fusion of feature extraction models including NASNetMobile, DenseNet121, and MobileNetV3Large.
  • Fall activity detection using a Temporal Convolutional Network (TCN) classifier, fine-tuned with Adamax optimizer.

Main Results:

  • The TCN-FARSDP system demonstrated a high accuracy of 99.48% in fall detection.
  • The proposed method outperformed existing techniques in experimental validation on an FD dataset.
  • The Adamax fine-tuning improved model convergence and stability.

Conclusions:

  • The TCN-FARSDP system offers a highly accurate and reliable solution for fall detection in disabled persons.
  • The integration of deep learning techniques within an IoT framework significantly advances remote healthcare monitoring.
  • This system holds significant potential for improving safety and enabling timely intervention for disabled individuals.