IoT-Based Smart Farming System with Convolutional Neural Networks for Real-Time Plant Disease Detection

Authors

  • Dr. Sajjad Ahmed Department of Computer Science, The University of Larkano, (TUL), Larkana, Sindh, Pakistan
  • Muhammad Ali Bijarani Department of Electrical Engineering, Quaid-e-Awam University of Engineering, Science and Technology (QUEST) Nawabshah, Pakistan
  • Imran Khan Keerio Department of Computer Science, Sindh Madressatul Islam University, Karachi, Pakistan
  • Anjum Usman Department of Computer Science, Shaheed Benazir Bhutto University, Sakrand Road, Nawabshah, Sindh, Pakistan
  • Muhammad Juman Jhatial Department of Computer Science, Shah Abdul Latif University, Khairpur Mir’s, Sindh, Pakistan

DOI:

https://doi.org/10.54692/lgurjcsit.v10i1.195

Keywords:

IoT, Smart Farming, Plant Disease Detection, CNN, Deep Learning, Image Classification, Real-Time Monitoring

Abstract

Agriculture plays an important role in food security and early detection of plant diseases is essential to minimize crop loss and boost production. The aim of this study is to design an Internet of Things (IoT) smart farming system that uses a Convolutional Neural Network (CNN) to detect plant diseases in real-time. The designed system uses IoT sensor to capture images of leaves, which are then transmitted via a wireless network to a cloud server for processing and classification. A CNN is built to classify the health status of the plant into three categories: healthy leaf, early diseased leaf and severe diseased leaf. The proposed system achieves high accuracy (92.4%), precision (91.8%), recall (90.6%) and F1-score (91.2%) on average. It also provides disease symptoms and suggestions of preventive measures on a web page. IoT and deep learning technologies enable real-time monitoring, diagnosis and decision support to farmers. It offers a reliable and scalable smart farming solution.

Downloads

Published

08-06-2026

Issue

Section

Articles