A Deep Learning Framework for Automated Silkworm Disease Identification and Farmer Assistance Using YOLOv8

Arpitha S; Supreetha Gowda HD

doi:10.71097/IJTAS.v17.i6.1353

A Deep Learning Framework for Automated Silkworm Disease Identification and Farmer Assistance Using YOLOv8

Author(s)	Ms. Arpitha S, Dr. Supreetha Gowda HD
Country	India
Abstract	Sericulture continues to face significant productivity losses due to delayed or inconsistent detection of silkworm diseases under conventional, manual-inspection-based rearing practices. This paper presents an end-to-end deep learning framework that automates the identification of major silkworm diseases—Grasserie, Flacherie, Pebrine, and Muscardine—alongside the healthy condition, using the YOLOv8 object-detection architecture. The proposed pipeline integrates image acquisition, a standardized preprocessing stage (resizing, normalization, denoising and augmentation), YOLOv8-based detection and classification, confidence-score estimation, bounding-box visualization, automated report generation, and persistent storage of prediction history, all delivered through a browser-based interface that requires no specialized technical skill from the end user. The model was evaluated using an 80:10:10 train–validation–test split together with a 5-fold cross-validation protocol to obtain an unbiased estimate of generalization performance. The system achieved an average cross-validated accuracy of 95.7% and an overall validation accuracy of 97.3%, with precision, recall and F1-score values exceeding 95% across all five disease categories, and a mean inference time of 1.6 seconds per image on a CPU-only Intel Core i7 platform. Comparative evaluation against CNN-based, transfer-learning, and traditional machine-learning baselines shows that the proposed system not only matches or exceeds reported accuracy levels but also uniquely combines detection with a deployable, farmer-facing assistance workflow. The results indicate that the framework is a practical and scalable candidate for real-time disease surveillance in sericulture operations.
Keywords	Silkworm disease detection; YOLOv8; deep learning; sericulture; object detection; computer vision; image classification; farmer assistance system
Field	Computer Applications
Published In	Volume 17, Issue 6, June 2026
Published On	2026-06-30
DOI	https://doi.org/10.71097/IJTAS.v17.i6.1353
Short DOI	https://doi.org/hb9bqk

View / Download PDF File

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJTAS DOI prefix is
10.71097/IJTAS

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 15 Isu 12 Cover Page Vol 15 Isu 11 Cover Page Vol 15 Isu 10

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJTAS Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	Message on WhatsApp	+91-9687-182-185	editor@ijtas.com

International Journal of Technology and Applied Science

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

A Deep Learning Framework for Automated Silkworm Disease Identification and Farmer Assistance Using YOLOv8

Share this