Related Experiment Video
Updated: Jul 29, 2026
04:17
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
Published on: May 10, 2024
748
An improved pear disease classification approach using cycle generative adversarial network
Khulud Alshammari1, Reem Alshammari2, Alanoud Alshammari3
1Faculty of Computers & Information Technology, University of Tabuk, Tabuk, Saudi Arabia. 421009996@stu.ut.edu.sa.
Scientific Reports
|March 21, 2024
Summary
Plant disease detection is improved using Cycle Generative Adversarial Network (CycleGAN). This machine learning approach enhances classification accuracy, crucial for agriculture and food security.
Area of Science:
- Agricultural Science
- Computer Science
Background:
- Agriculture is vital for global food security and economic stability.
- Plant diseases cause significant yield and economic losses.
- Manual plant disease identification is inaccurate and time-consuming.
Purpose of the Study:
- To address limitations in Convolutional Neural Network (CNN) model training due to insufficient data for plant disease classification.
- To enhance the accuracy of plant disease detection and classification using advanced machine learning techniques.
Main Methods:
- Designed a Cycle Generative Adversarial Network (CycleGAN) to augment limited agricultural datasets.
- Implemented CycleGAN architecture to improve CNN model performance for plant disease classification.
Main Results:
- CycleGAN effectively addressed over-fitting and limited dataset size issues.
- The developed approach demonstrated an average enhancement of 7% in plant disease classification accuracy.
Conclusions:
- CycleGAN is a viable method for improving plant disease classification accuracy.
- This advancement supports more reliable agricultural monitoring and disease management.
