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

Magnetoelectric-powered electrocatalysis for rapid wireless tooth whitening.

Journal of materials chemistry. B·2026
Same author

Fusion sensing for urban resilience.

Innovation (Cambridge (Mass.))·2026
Same author

From generalization to precision: A large domain-specific pretrained model for specialized medical tasks.

Cell reports. Medicine·2026
Same author

Automated diagnosis of keratitis from low-quality slit-lamp images using an improved generative adversarial network.

NPJ digital medicine·2026
Same author

Mechanisms and clinical challenges of ICB-mediated remodeling of the tumor microenvironment in nasopharyngeal carcinoma.

Oral oncology·2026
Same author

Transforming global water cycle observations via synergistic AI and remote sensing.

Science advances·2026

Related Experiment Video

Updated: Dec 13, 2025

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

1.9K

Recognition of Crop Diseases Based on Depthwise Separable Convolution in Edge Computing.

Musong Gu1,2,3, Kuan-Ching Li4, Zhongwen Li1

  • 1College of Information Science and Technology, Chengdu University, Chengdu 610106, China.

Sensors (Basel, Switzerland)
|July 26, 2020
PubMed
Summary

A new depthwise separable convolutional neural network (DSCNN) model enables efficient crop disease recognition on edge devices. This approach significantly reduces computation time and parameters for real-time monitoring in agriculture.

Keywords:
Visual Geometry Group (VGG) network modeldepthwise separable convolution neural networkrecognition of crop diseases

More Related Videos

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images
11:49

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

9.7K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.2K

Related Experiment Videos

Last Updated: Dec 13, 2025

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

1.9K
Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images
11:49

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

9.7K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.2K

Area of Science:

  • Agricultural Science
  • Computer Vision
  • Machine Learning

Background:

  • Traditional crop disease recognition relies on cloud-based analysis, which is time-consuming, costly, and hinders timely monitoring.
  • Edge computing offers potential for on-site analysis, but resource limitations of edge devices challenge the deployment of deep learning models.

Purpose of the Study:

  • To develop an efficient crop disease recognition model suitable for edge computing environments.
  • To address the limitations of traditional methods and resource constraints of edge devices in agricultural pattern recognition.

Main Methods:

  • Proposed a novel recognition model based on depthwise separable convolutional neural network (DSCNN).
  • DSCNN features a significant reduction in parameters and computational load, optimizing it for edge deployment.
  • Compared simulation results with established convolutional neural network (CNN) models like LeNet and VGGNet.

Main Results:

  • The proposed DSCNN model achieved high recognition accuracy for crop diseases.
  • Demonstrated substantial reductions in recognition time: 80.9% compared to LeNet and 94.4% compared to VGGNet.
  • The model's efficiency makes it well-suited for resource-constrained edge devices.

Conclusions:

  • The DSCNN model offers a viable solution for real-time crop disease monitoring using edge computing.
  • Its fast recognition speed and high accuracy enable timely diagnosis and treatment, improving agricultural practices.
  • Facilitates remote embedded equipment deployment for efficient agricultural disease management.