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

Search research articles

Related Experiment Video

Updated: Jun 27, 2026

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

A Lightweight Temporal Convolutional Network for Contactless SPPB-Aligned Functional Fall-Risk Stratification in

Kai-Chih Lin¹, Rong-Jong Wai¹, Hung-Yu Chang Chien²

¹Department of Electronic and Computer Engineering, National Taiwan University of Science and Technology, Taipei 106, Taiwan.

Sensors (Basel, Switzerland)

|June 26, 2026

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

AI-Assisted Dynamic Postural Control Screening to Improve Functional Mobility in Older Adult Populations: Quasi-Experimental Study.

JMIR aging·2025

Same author

Are Older Adults without a Healthy Diet Less Physically Active and More Sedentary?

Nutrients·2019

See all related articles

This summary is machine-generated.

This study introduces a lightweight, contactless AI system for assessing fall risk in older adults using video. The Temporal Convolutional Artificial Intelligence Fall-Risk Network (TCAI-FallNet) shows promise for functional mobility stratification.

Area of Science:

Gerontology
Biomedical Engineering
Computer Science

Background:

Falls in older adults represent a significant public health challenge.
Existing methods for fall risk assessment lack scalability and interpretability.
Need for accessible, objective tools for functional fall-risk stratification.

Purpose of the Study:

To develop and evaluate a lightweight, contactless framework for fall-risk stratification.
To align functional fall-risk assessment with the Short Physical Performance Battery (SPPB) using monocular RGB video.
To introduce the Temporal Convolutional Artificial Intelligence Fall-Risk Network (TCAI-FallNet) for this purpose.

Main Methods:

Utilized monocular RGB video from 688 community-dwelling older adults performing SPPB-aligned tasks.

Keywords:

contactless sensing edge AI explainable artificial intelligence fall-risk assessment functional risk stratification human pose estimation monocular RGB video skeletal biomechanics temporal convolutional network

More Related Videos

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

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: Jun 27, 2026

Design and Analysis for Fall Detection System Simplification

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

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

Extracted and normalized 2D keypoints using BlazePose to create temporal skeletal trajectories.

Fused biomechanical descriptors with TCAI-FallNet embeddings for risk prediction.

Main Results:

TCAI-FallNet achieved a macro-averaged area under the curve (AUC) of 0.91.
The model demonstrated an overall accuracy of 81.3% in functional fall-risk stratification.
The trained model is lightweight (<3 MB) with low inference latency (<20 ms).

Conclusions:

TCAI-FallNet offers a promising contactless solution for SPPB-aligned functional mobility risk stratification.
The framework's lightweight nature and efficiency support potential clinical deployment.
Further validation with prospective fall-event data is required.