Rice disease identification through leaf image and IoT based smart rice field monitoring system

Islam, Md Nahidul and Ahmed, Fahim and Ahammed, Md Tanvir and Rashid, Mamunur and Bari, Bifta Sama (2022) Rice disease identification through leaf image and IoT based smart rice field monitoring system. In: Lecture Notes in Electrical Engineering. Innovative Manufacturing, Mechatronics and Materials Forum, iM3F 2021 , 20 September 2021 , Gambang. pp. 529-539., 900. ISSN 1876-1100 ISBN 978-981192094-3 (Published)

[img] Pdf
Rice disease identification through leaf image.pdf
Restricted to Repository staff only

Download (320kB) | Request a copy
[img]
Preview
Pdf
Rice disease identification through leaf image and IoT based smart rice field monitoring system_ABS.pdf

Download (48kB) | Preview

Abstract

Rice disease identification in early-stage, proper medication in case of disease affection and managing irrigation at the appropriate time is the most consequential phenomena to increase the production level of the rice. In this paper, a novel technique to diagnose the rice diseases and smart medication prescription system have been proposed. Furthermore, the internet of things (IoT) based smart rice field monitoring system has also been proposed. To identify rice diseases, the leaf image dataset (consists of healthy and three different diseases) has been analyzed through the convolutional neural network (CNN). The obtained rice disease diagnosis accuracy of the proposed system was 98.7%. In a real-time system, the leaf image data has been collected remotely using Raspberry Pi and the data has been sent to a server to be tested by a trained CNN model. Some sensors including soil moisture sensor, pressure sensor, humidity sensor, and temperature sensor have been implanted in the targeted field which aims to record the current scenario of the rice field and send the sensors data to the server. On a web page, proper medications have been displayed if any rice disease identified. Moreover, the user may monitor his field remotely which facilitates irrigation in opportune time.

Item Type: Conference or Workshop Item (Lecture)
Additional Information: Indexed by Scopus
Uncontrolled Keywords: Convolutional Neural Networks (CNN); Deep learning; Image processing; IoT; Leaf disease detection
Subjects: T Technology > T Technology (General)
T Technology > TA Engineering (General). Civil engineering (General)
T Technology > TK Electrical engineering. Electronics Nuclear engineering
Faculty/Division: Institute of Postgraduate Studies
Faculty of Electrical and Electronic Engineering Technology
Depositing User: Mr Muhamad Firdaus Janih@Jaini
Date Deposited: 30 Oct 2024 04:27
Last Modified: 30 Oct 2024 04:27
URI: http://umpir.ump.edu.my/id/eprint/42293
Download Statistic: View Download Statistics

Actions (login required)

View Item View Item