A PREDICTIVE MODEL FOR EARLY DETECTION AND SPREAD OF CROP DISEASE USING A CONVOLUTIONAL NEURAL NETWORK ALGORITHM

ALUM, BOB OKWUDILI (2025) A PREDICTIVE MODEL FOR EARLY DETECTION AND SPREAD OF CROP DISEASE USING A CONVOLUTIONAL NEURAL NETWORK ALGORITHM. Other thesis, GODFREY OKOYE UNIVERSITY, ENUGU.

[img] Text
bob101.docx
Download (4MB)

Abstract

This study presents the development of a deep learning-based predictive model for the early detection of tomato crop diseases. The model is designed as a decision-support tool for smallholder farmers, and it utilizes a Convolutional Neural Network (CNN), which was enhanced with transfer learning (VGG16) to effectively analyze and classify diseases from tomato leaf images. Image data augmentation techniques were employed to improve the detection accuracy of the proposed model under diverse conditions, and the training dataset was compiled from active farms in the Sub-Saharan region of Africa and reputable online sources like the PlantVillage dataset, enabling the system to combine localized and standardized data. The system includes a user-friendly Graphical User Interface (GUI) to ensure easy accessibility and usability for farmers with limited tech skills. The system addresses common issues in traditional disease management, such as misdiagnosis and excessive pesticide use, by providing timely and precise disease identification, which has led to reduced input costs, decreased chemical usage, and improved crop yields for farmers. Evaluation results from the test dataset show an accuracy of 94%, precision of 94%, recall of 93%, and an F1 score of 93%, underscoring the model's effectiveness in enhancing agricultural disease detection and supporting sustainable farming.

Item Type: Thesis (Other)
Subjects: Q Science > QA Mathematics > QA76 Computer software
Divisions: Faculty of Natural and Applied Sciences
Depositing User: Uchenna Eneogwe
Date Deposited: 16 Jun 2026 09:11
Last Modified: 16 Jun 2026 09:11
URI: http://eprints.gouni.edu.ng/id/eprint/5820

Actions (login required)

View Item View Item
GOUNI Repository is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.