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

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

Bridging the Gap from "Paper" to "Patient": An Overview and Quality Assessment of PET/CT-Based Radiomics for Prostate Cancer Using the Updated RQS 2.0.

Academic radiology·2026

Same author

Noninvasive detection and prognostic stratification of biliary tract cancer using cell-free DNA fragmentomics: a model development and validation study.

Molecular biomedicine·2026

Same author

A machine learning framework combining cfDNA fragmentomics and serum biomarkers for early ovarian cancer detection.

Cell communication and signaling : CCS·2026

Same author

Integrative fragmentomic and mutational signature profile of plasma cfDNA for early lung cancer detection.

NPJ precision oncology·2026

Same author

Radiomics for differentiating ruptured intracranial aneurysms: overview, methodological quality evaluation using METRICS and RQS, and feature transportability validation using independent multi-center dataset.

European radiology·2026

Same author

Seasonal variations in outcomes following spontaneous intracerebral hemorrhage: a case control study.

BMC neurology·2026

Same journal

Machine-learning-assisted comparative analysis of rice growth and yield formation in field and plant factory systems.

Frontiers in plant science·2026

Same journal

TomatoweedDet: a real-field multi-class weed detection dataset and YOLO benchmark for tomato production systems.

Frontiers in plant science·2026

Same journal

Genomic advances in orphan and underutilized Brassicaceae crops and their wild relatives.

Frontiers in plant science·2026

Same journal

Delayed sowing limits grain number per spike in wheat by restricting young spike differentiation through reduced photothermal resources.

Frontiers in plant science·2026

Same journal

Deterministic assembly and centralized networks define the <i>Pinus massoniana</i> rhizosphere mycobiota.

Frontiers in plant science·2026

Same journal

Cover cropping enhances fruit quality in protected citrus cultivation by modulating rhizosphere microbiome and iron availability.

Frontiers in plant science·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Aug 15, 2025

Screening Cotton Genotypes for Reniform Nematode Resistance

Screening Cotton Genotypes for Reniform Nematode Resistance

Published on: May 2, 2019

Cotton disease identification method based on pruning.

Dongqin Zhu¹, Quan Feng¹, Jianhua Zhang^2,3

¹School of Mechanical and Electrical Engineering, Gansu Agricultural University, Lanzhou, China.

Frontiers in Plant Science

|January 2, 2023

Summary

This summary is machine-generated.

This study compresses deep convolutional neural networks (DCNN) for efficient cotton disease recognition on smart devices. Transfer learning after compression significantly improves accuracy and reduces model size, enabling a practical mobile application.

Keywords:

compact model convolutional neural network cotton diseases pruning transfer learning

More Related Videos

Specific and Accurate Detection of the Citrus Greening Pathogen Candidatus liberibacter spp. Using Conventional PCR on Citrus Leaf Tissue Samples

Specific and Accurate Detection of the Citrus Greening Pathogen Candidatus liberibacter spp. Using Conventional PCR on Citrus Leaf Tissue Samples

Published on: June 29, 2018

Evaluating Dryocosmus Kuriphilus-induced Damage on Castanea Sativa

Evaluating Dryocosmus Kuriphilus-induced Damage on Castanea Sativa

Published on: August 30, 2018

Related Experiment Videos

Last Updated: Aug 15, 2025

Screening Cotton Genotypes for Reniform Nematode Resistance

Screening Cotton Genotypes for Reniform Nematode Resistance

Published on: May 2, 2019

Specific and Accurate Detection of the Citrus Greening Pathogen Candidatus liberibacter spp. Using Conventional PCR on Citrus Leaf Tissue Samples

Specific and Accurate Detection of the Citrus Greening Pathogen Candidatus liberibacter spp. Using Conventional PCR on Citrus Leaf Tissue Samples

Published on: June 29, 2018

Evaluating Dryocosmus Kuriphilus-induced Damage on Castanea Sativa

Evaluating Dryocosmus Kuriphilus-induced Damage on Castanea Sativa

Published on: August 30, 2018

Area of Science:

Agricultural Science
Computer Science
Machine Learning

Background:

Deep convolutional neural networks (DCNNs) excel at plant disease recognition but are too large for mobile devices.
Deploying DCNNs on resource-limited smart devices requires significant model compression.

Purpose of the Study:

To develop a compressed DCNN model for cotton disease identification on mobile devices.
To evaluate the effectiveness of pruning algorithms and transfer learning strategies for model compression.

Main Methods:

Model compression using a pruning algorithm based on the γ coefficient in Batch Normalization layers.
Comparison of two transfer learning strategies: compression after transfer learning vs. transfer learning after compression.
Evaluation of VGG16, ResNet164, and DenseNet40 models on a cotton disease dataset.

Main Results:

Transfer learning after compression generally outperformed compression after transfer learning.
Compressed DenseNet40 achieved 97.23% accuracy with only 0.26M parameters at 80% compression.
The best model (DenseNet40-80%-T) achieved 97.23% accuracy, 2.2 MB size, and 87ms identification time on an Android app.

Conclusions:

Model compression using pruning and transfer learning is effective for deploying DCNNs on smart devices.
The optimized DenseNet40 model offers high accuracy and efficiency for mobile cotton disease recognition.
A functional Android application demonstrates the practical utility of the compressed model.