IoT-Based Crop Disease Detection and Management System Using Machine Learning Algorithms

• Published in: 2024 International Conference on Science Technology Engineering and Management (ICSTEM) pp. 1 - 5
• Main Authors: Manoharan, Geetha, Ali, S Dada Noor Hayath, Sathe, Manoj, Karthik, A, Nagpal, Amandeep, Sidana, Ajay
• Format: Conference Proceeding
• Language: English
• Published: IEEE 26.04.2024
• Subjects: Agricultural monitoring; Crop disease detection; Crops; Data analytics; Internet of Things; IoT (Internet of Things); Machine learning algorithms; Precision farming; Sensor networks; Supervised learning; Support vector machines; Temperature measurement; Temperature sensors
• DOI: 10.1109/ICSTEM61137.2024.10561056

As a result of the rapid development of Internet of Things (IoT) technology and the growing desire for more effective agricultural methods, there is a growing interest in the development of intelligent solutions for the identification and management of crop diseases. The purpose of this study is to describe an Internet of Things-based system that makes use of machine learning algorithms for early disease diagnosis and efficient disease management in agricultural production. The proposed system is comprised of a network of Internet of Things devices that are installed in agricultural fields. These devices include sensors that monitor environmental parameters such as temperature, humidity, and soil moisture, as well as cameras that take pictures of crops. The information that is gathered by these devices from the field is continuously transmitted to a centralized server for processing and analysis. To analyze the data that has been gathered and identify the presence of illnesses in crops based on image analysis and environmental factors, machine learning algorithms are utilized. Convolutional neural networks (CNNs) and support vector machines (SVMs) are two examples of the types of learning techniques that are utilized for effective illness classification and detection. Other techniques include unsupervised learning and supervised learning.