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 Novel Residual Dual Attention Multiscale Network for Vibration-Based Damage Recognition in Floating Wind Turbine Structural Health Monitoring.

Sensors (Basel, Switzerland)·2026
Same author

Dual-stream learning with inverted transformer and BiGRU for rolling bearing remaining useful life prediction.

Scientific reports·2026
Same author

Post-marketing safety evaluation of mirogabalin using the JADER database.

Frontiers in pharmacology·2026
Same author

fNIRS as a Biomarker for Preoperative Assessment: Correlating Brain Activity with Clinical Evaluation for Lumbar Disc Herniation.

Bioengineering (Basel, Switzerland)·2026
Same author

Correction: Platelet-rich plasma combined with multimodal therapy for diabetic foot ulcer with tophi: a case report.

Frontiers in clinical diabetes and healthcare·2026
Same author

Robust cross-domain blast furnace tuyere leak detection via few-shot guided simulation-to-real adaptation.

Scientific reports·2026

Related Experiment Video

Updated: Jun 21, 2025

Manufacturing Simple and Inexpensive Soil Surface Temperature and Gravimetric Water Content Sensors
08:49

Manufacturing Simple and Inexpensive Soil Surface Temperature and Gravimetric Water Content Sensors

Published on: December 21, 2019

9.3K

Tiny-Machine-Learning-Based Supply Canal Surface Condition Monitoring.

Chengjie Huang1, Xinjuan Sun1, Yuxuan Zhang2

  • 1School of Electronic Engineering, North China University of Water Resources and Electric Power, Jinshui East Road No. 136, Zhengzhou 450046, China.

Sensors (Basel, Switzerland)
|July 13, 2024
PubMed
Summary

This study introduces a lightweight convolutional neural network (CNN) for early structural damage detection in water supply canals. Deployed as a TinyML application on a microcontroller, it enables efficient, real-time infrastructure monitoring.

Keywords:
convolutional neural networks (CNNs)damage classificationembedded systemsstructural health monitoring (SHM)tiny machine learning (TinyML)water supply canals

More Related Videos

Continuous Instream Monitoring of Nutrients and Sediment in Agricultural Watersheds
12:50

Continuous Instream Monitoring of Nutrients and Sediment in Agricultural Watersheds

Published on: September 26, 2017

11.2K
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.0K

Related Experiment Videos

Last Updated: Jun 21, 2025

Manufacturing Simple and Inexpensive Soil Surface Temperature and Gravimetric Water Content Sensors
08:49

Manufacturing Simple and Inexpensive Soil Surface Temperature and Gravimetric Water Content Sensors

Published on: December 21, 2019

9.3K
Continuous Instream Monitoring of Nutrients and Sediment in Agricultural Watersheds
12:50

Continuous Instream Monitoring of Nutrients and Sediment in Agricultural Watersheds

Published on: September 26, 2017

11.2K
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.0K

Area of Science:

  • Civil Engineering
  • Artificial Intelligence
  • Embedded Systems

Background:

  • Ensuring the safe operation of China's South-to-North Water Diversion Project infrastructure is critical.
  • Current structural health monitoring systems for hydraulic infrastructure often rely on resource-intensive desktop applications.
  • There is a need for efficient, low-power solutions for real-time monitoring of water supply canals.

Purpose of the Study:

  • To develop and deploy a lightweight convolutional neural network (CNN) model for early detection of structural damage in water supply canals.
  • To implement this model as a Tiny Machine Learning (TinyML) application on a low-power microcontroller unit (MCU).
  • To evaluate the model's performance, energy efficiency, and feasibility for resource-constrained devices.

Main Methods:

  • Collected and utilized images of supply canal damage as input for the CNN model.
  • Employed data augmentation techniques to enhance the training dataset.
  • Deployed a lightweight CNN model (7.57 KB) as a TinyML application on an MCU for real-time inference.

Main Results:

  • The deployed TinyML model achieved high accuracy (94.17 ± 1.67%) and precision (94.47 ± 1.46%).
  • The model demonstrated superior performance and energy efficiency compared to other common CNN models.
  • Each inference consumed minimal energy (5610.18 μJ), enabling nearly 11 years of continuous operation on a button cell battery.

Conclusions:

  • Real-time monitoring of supply canal surface conditions on low-power, resource-constrained devices is feasible.
  • The developed TinyML application offers a practical solution for enhancing the security of hydraulic infrastructure.
  • This research paves the way for more efficient and accessible structural health monitoring systems.