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

A Dual-FBG Sensor with Machine Learning for Microstrain-Temperature Decoupling Under Cyanoacrylate Bonding Toward Catheter Applications.

Micromachines·2026
Same author

A Deep Learning Framework for Enhancing High-Frequency Optical Fiber Vibration Sensing from Low-Sampling-Rate FBG Interrogators.

Sensors (Basel, Switzerland)·2025
Same author

Abundant dynamics of group velocity locked vector solitons from Er-doped fiber laser based on GO/PVA film.

Nanophotonics (Berlin, Germany)·2024
Same author

One Raman DTS Interrogator Channel Supports a Dual Separate Path to Realize Spatial Duplexing.

Sensors (Basel, Switzerland)·2024
Same author

Enhancing Multichannel Fiber Optic Sensing Systems with IFFT-DNN for Remote Water Level Monitoring.

Sensors (Basel, Switzerland)·2024
Same author

Reinforcement learning-based adaptive beam alignment in a photodiode-integrated array antenna module.

Optics letters·2024

Related Experiment Video

Updated: Jan 16, 2026

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy
07:13

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Published on: February 25, 2021

4.4K

Spectral Demodulation of Mixed-Linewidth FBG Sensor Networks Using Cloud-Based Deep Learning for Land Monitoring.

Michael Augustine Arockiyadoss1, Cheng-Kai Yao1, Pei-Chung Liu1

  • 1Department of Electro-Optical Engineering, National Taipei University of Technology, Taipei 10608, Taiwan.

Sensors (Basel, Switzerland)
|September 27, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a Transformer neural network to resolve spectral overlap in Fiber Bragg Grating (FBG) sensing systems. The novel approach enhances sensor density and network scalability for diverse monitoring applications.

Keywords:
agriculturedeep learningfiber Bragg gratingland monitoringmaritime sensingoptical sensorssensor networksspectral analysisurban infrastructure

More Related Videos

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring
08:16

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 2025

488
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 16, 2026

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy
07:13

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Published on: February 25, 2021

4.4K
Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring
08:16

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 2025

488
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:

  • Optoelectronics and Photonics
  • Artificial Intelligence in Sensing
  • Signal Processing for Optical Networks

Background:

  • Fiber Bragg Grating (FBG) sensing systems struggle with spectral overlap, limiting sensor density and network scalability.
  • Existing methods face challenges in resolving overlapping signatures, especially under bidirectional drift conditions.
  • High-density FBG networks are crucial for applications like land monitoring and infrastructure surveillance.

Purpose of the Study:

  • To develop a novel Transformer-based neural network architecture for resolving spectral overlap in FBG sensor arrays.
  • To enhance demodulation accuracy and sensing capacity by combining dual-linewidth configurations with reflection and transmission mode fusion.
  • To enable scalable deployment and near-real-time inference for large-scale FBG sensing networks using cloud computing.

Main Methods:

  • Implementation of a Transformer neural network architecture for spectral signature resolution.
  • Integration of dual-linewidth FBG configurations and fusion of reflection/transmission modes.
  • Utilizing cloud computing for scalable deployment and real-time inference capabilities.
  • Incorporation of self-healing functionality for dynamic mode switching during fiber breaks.

Main Results:

  • Effective resolution of spectral overlap in both uniform and mixed-linewidth FBG sensor arrays under bidirectional drift.
  • Demonstrated exceptional demodulation performance even under severe spectral overlap conditions.
  • Achieved enhanced resilience against spectral congestion and supported self-healing functionality.
  • Validated performance across twelve diverse drift scenarios, outperforming conventional peak-finding algorithms.

Conclusions:

  • The proposed Transformer-based approach establishes a new paradigm for high-density, distributed FBG sensing.
  • This breakthrough significantly enhances the scalability and accuracy of FBG sensing systems.
  • The technology is applicable to critical monitoring tasks including land, soil, groundwater, maritime surveillance, and smart agriculture.