International Journal of Computer Theory and Engineering

Editor-In-Chief: Prof. Mehmet Sahinoglu
Frequency: Quarterly
ISSN: 1793-8201 (Print), 2972-4511 (Online)
Publisher:IACSIT Press
OPEN ACCESS
4.1
CiteScore

⚠️ Important Security Notice: Beware of Fraudulent Emails Impersonating IJCTE Officials
IJCTE 2025 Vol.17(3): 126-133
DOI: 10.7763/IJCTE.2025.V17.1375

Deployment of a Deep Learning Model for the Automated Diagnosis of Thai Rubber Leaf Diseases via the LINE Platform

Puriwat Lertkrai, Benjamin Chanakot, and Nattapong Kaewboonma*
Faculty of Management Technology, Rajamangala University of Technology Srivijaya, Nakhon Si Thammarat, Thailand
Email: puriwat.l@rmutsv.ac.th (P.L.); benjamin.c@rmutsv.ac.th (B.C.); nattapong.k@rmutsv.ac.th (N.K.)
*Corresponding author

Manuscript received December 24, 2024; revised February 19, 2025; accepted April 9, 2025; published July 9, 2025

Abstract—This research presents an approach for real-time detection of rubber leaf diseases using the YOLOv8 deep learning model, integrated with the LINE messaging platform. The system enables users to submit rubber leaf images via LINE, where they are processed by an Artificial Intelligence (AI)—powered backend hosted on Heroku, utilizing Docker and Flask for scalability and efficiency. The YOLOv8 model was trained on a dataset comprising three classes: Healthy, New Disease, and Powdery Mildew. It achieved an overall mAP50 of 57.9% and an mAP50-95 of 42.8%, demonstrating strong performance in detecting healthy leaves (mAP50: 98.3%) but lower accuracy in identifying Powdery Mildew (mAP50: 22.4%), likely due to significant class imbalance. User testing involved 50 beta testers who submitted 500 images through the chatbot, yielding a detection accuracy of 72.4%, a misclassification rate of 5.4%, and an average response time of 2.5 seconds. Key performance metrics included a macro-average precision of 78.2%, recall of 73.0%, and an F1 score of 75.5%. User feedback highlighted satisfaction with the system’s ease of use and response speed, though improvements were suggested in handling misclassifications and providing treatment recommendations. These results indicate that the system offers a robust and scalable solution for rubber leaf disease detection, with potential for further optimization.

Keywords—image data processing, image data diagnosis, image detection, deep learning, rubber leaf disease

[PDF]

Cite: Puriwat Lertkrai, Benjamin Chanakot, and Nattapong Kaewboonma, "Deployment of a Deep Learning Model for the Automated Diagnosis of Thai Rubber Leaf Diseases via the LINE Platform," International Journal of Computer Theory and Engineering, vol. 17, no. 3, pp. 126-133, 2025.

Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).

Article Metrics in Dimensions

Menu