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: Jul 17, 2026

Multimodal Imaging and Spectroscopy Fiber-bundle Microendoscopy Platform for Non-invasive, In Vivo Tissue Analysis

Multimodal Imaging and Spectroscopy Fiber-bundle Microendoscopy Platform for Non-invasive, In Vivo Tissue Analysis

Published on: October 17, 2016

Dynamic multimode fiber specklegram sensor with automated training data generation for bed-exit prediction.

Md Nazmul Islam Sarkar^1,2, Linh Viet Nguyen^1,2, Adam D Kilpatrick^3,4

¹Future Industries Institute, Adelaide University, Mawson Lakes, SA 5095, Australia.

Biomedical Optics Express

|July 16, 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

Single-fiber probes for combined sensing and imaging in biological tissue: recent developments and prospects.

Biomedical optics express·2024

Same author

Microsphere-Enabled Micropillar Array for Whispering Gallery Mode Virus Detection.

ACS applied materials & interfaces·2024

Same author

Surface Functionalised Optical Fibre for Detection of Hydrogen Sulphide.

Biosensors·2023

Same author

Mitigating stimulated Brillouin scattering in multimode fibers with focused output via wavefront shaping.

Nature communications·2023

Same author

Label-free DNA quantification using isothermal amplification on an exposed core optical fiber microfluidic platform.

The Analyst·2023

Same author

Ultra-high-resolution greyscale fluorescence images <i>via</i> UV-exposure of thin flexible phosphor films.

Nanoscale·2023

This study introduces a novel predictive bed-exit detection system using fiber optic sensors and deep learning. It accurately forecasts patient bed exits, enhancing safety through proactive fall prevention in healthcare settings.

Area of Science:

Biomedical Engineering
Artificial Intelligence in Healthcare
Sensor Technology

Background:

Existing bed-exit systems are reactive, limiting their effectiveness for fall prevention.
There is a need for predictive patient monitoring to enhance safety in healthcare settings.
Patient privacy is a key concern in developing monitoring technologies.

Purpose of the Study:

To develop and validate a proof-of-concept system for predictive bed-exit detection.
To combine dynamic multimode fiber specklegram sensing with deep learning for accurate predictions.
To achieve bed-exit prediction while preserving patient privacy.

Main Methods:

Integration of a multimode optical fiber into a hospital mattress to monitor patient movement via speckle pattern variations.

More Related Videos

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Related Experiment Videos

Last Updated: Jul 17, 2026

Multimodal Imaging and Spectroscopy Fiber-bundle Microendoscopy Platform for Non-invasive, In Vivo Tissue Analysis

Multimodal Imaging and Spectroscopy Fiber-bundle Microendoscopy Platform for Non-invasive, In Vivo Tissue Analysis

Published on: October 17, 2016

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Automated data labeling using zero-mean normalized cross-correlation for bed entry/exit event identification.

Application of principal component analysis for dimensionality reduction and training a convolutional neural network for temporal pattern recognition.

Main Results:

The system successfully predicts bed-exit events up to 30 seconds in advance with ±1 second accuracy.
Demonstrated ability to detect subtle pre-exit patterns imperceptible to conventional sensors.
The supervised learning framework allows continuous adaptation to patient behavior and environmental changes.

Conclusions:

The developed system offers a significant advancement in intelligent patient monitoring.
Predictive intervention strategies, enabled by this technology, can substantially enhance patient safety.
This approach addresses limitations of current healthcare monitoring by providing proactive fall prevention capabilities.