The Implementation of Machine Learning for Disease Detection in Tomato Plants using Convolutional Neural Networks - Implementation Study

Aug 2, 2026

Upload by Sage

Tomato plant diseases can severely damage farmers’ productivity through issues such as begomovirus, blight, and spider mites. Machine learning is evaluated as a practical approach to reduce financial losses by improving automated disease detection. The study applies Convolutional Neural Networks (CNN) using a Kaggle dataset of 4,800 labeled images and a real-time dataset of 450 images from Kadudampit, Sukabumi. Performance is assessed with accuracy using confusion matrices across separate and combined training datasets, yielding 97% (public), 94% (public+real-time), and 80% (real-time).

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages13

Reading Time33 min

AccessFree to download

Introduction

Method

Experiment Setup

Results and Discussion

Conclusion

|
E-ISSN : 2988-585X (Online) | Journal of Elektronik Sistem InformasI
(JESII)
Volume 2 No 2 Desember 2024
DOI : 10.31848/jesii.xxxx.xxxx | | --- | --- | The Implementation of Machine Learning for Disease Detection in Tomato Plants using Convolutional Neural Networks Faisal Aziz1, Nana Suryana2 1,2Department of Information System, Univ. Kebangsaan Republik Indonesia, Indonesia Article Info ABSTRACT | Article history:
Received Dec 16, 24 Revised Dec 30, 24 Accepted Dec 31, 24 | Diseases in tomato plants can be highly detrimental to tomato farmers, with common afflictions such as begomovirus, blight, and spider mites posing significant challenges. The implementation of machine learning offers a promising solution to address these issues and mitigate the financial losses caused by such diseases. This study aims to evaluate the effectiveness of machine learning in detecting plant diseases using Convolutional Neural Networks (CNN) . The data used in this implementation was obtained from public datasets available on Kaggle and realtime data collected directly from tomato farms in Kadudampit, Sukabumi Regency. The Kaggle dataset contains 4,800 images categorized into three classes: begomovirus, blight, and spider mites. Meanwhile, the real-time dataset comprises 450 images, also divided into the same three classes. The performance of the machine learning model was tested using different datasets, with accuracy measured through a confusion matrix. The results showed that the machine learning model trained on the public dataset achieved the highest accuracy of 97% . The model trained on a combination of the public and real-time datasets achieved an accuracy of 94%, while the model trained solely on the realtime dataset achieved an accuracy of 80% . A machine learning model is considered effective if its accuracy exceeds 75% . Therefore, based on the three tests conducted, it can be concluded that the machine learning models demonstrated a good level of accuracy in detecting diseases in tomato plants. | | --- | --- | | Keywords:
Convolutional Neural Network Machine Learning
Tomato Plant Diseases | | Corresponding Author: Faisal Aziz, Information System Department, Faculty of Computer Science and Information Systems, Univ. Kebangsaan Republik Indonesia. Jln. Terusan Halimun No.37 (Pelajar Pejuang 45) Bandung, Jawa Barat, Indonesia. 40614 Email: [faisalaziz@gmail.com](faisalaziz@gmail.com) 1. INTRODUCTION With the advancement of technology, particularly in the field of Artificial Intelligence (AI), various machine learning methods have been developed to address a wide range of issues in agriculture. One prominent method is Convolutional Neural Network (CNN) . CNN, a type of deep learning, is known for its effectiveness in image analysis and pattern recognition. In the context of plant disease detection, CNN holds great potential for identifying disease symptoms on plant leaves through images with high accuracy [1] . This study focuses on tomato plants, specifically their leaves. Leaves are among the most responsive parts of a plant in showing early symptoms of disease. These symptoms may include discoloration, the appearance of spots, or deformation of the leaf structure. Early identification of these symptoms is crucial to ensure timely and appropriate intervention before the disease spreads and infects the entire plant. This research employs machine learning technology, with Convolutional Neural Network (CNN) as the primary method. CNN excel at visual data analysis such as image classification and object detection, making them a key tool for visual pattern-based decision making, especially in the medical, surveillance, and autonomous vehicle fields [2] . In this study, CNN is utilized to analyze tomato leaf images to automatically detect diseases. The main challenge of this research lies in implementing a CNN model capable of detecting diseases in tomato plants with high accuracy. This

FAQs

What diseases are targeted in the tomato plant detection task?

The study focuses on begomovirus, blight, and spider mites as the three detection classes.

How are the training datasets obtained and divided?

One dataset comes from Kaggle with 4,800 images split into three classes, and a second real-time dataset contains 450 images collected directly from tomato farms in Kadudampit, Sukabumi.

How is model performance evaluated and what accuracies are achieved?

Performance is measured using accuracy derived from a confusion matrix. Models trained on the public dataset reach 97% accuracy, on the combined dataset 94%, and on the real-time dataset 80%.

Aug 2, 2026

Upload by Sage