Expert system for smart farming for diagnosis of sugarcane diseases using machine learning

Atheeswaran, Athiraja; K. V., Raghavender; Chaganti, B. N. Lakshmi; Maram, Ashok; Herencsár, Norbert

Expert system for smart farming for diagnosis of sugarcane diseases using machine learning

Date

2023-07-03

Authors

Atheeswaran, Athiraja

K. V., Raghavender

Chaganti, B. N. Lakshmi

Maram, Ashok

Herencsár, Norbert

ORCID

0000-0002-9504-2275

Publisher

PERGAMON-ELSEVIER SCIENCE LTD

Altmetrics

Abstract

Agriculture is one of the oldest occupations in the world and continues to exist today. In some form or another, the world's population depends on agriculture for its needs. The major loss in sugarcane production in India is due to pests, plant disease, malnutrition, and nutrient deficiency in plants. To identify these diseases, farmers go to local farmers, experts, agricultural people, and fellow neighbors to identify the problem caused. In some cases, their information may be adequate, but in others it is not. These people cannot solve all the problems caused by their crops can be solved by these people; there is a need to accurately predict the correct disease and provide the proper treatment at the right time. This can only be done by applying machine learning-based Internet of Things solutions in real time. This article proposes a method for a smart farming system to address the needs of farmers producing sugarcane in India by applying intelligent solutions that use image processing and soft computing. Four sugarcane diseases are investigated, such as Eyespot, Leaf Scald, Yellow Leaf, and Pokkah Boeng, and three characteristics such as color, shape, and texture. Images were used for training data in Artificial Neural Network (ANN), Neuro-Fuzzy, and Case-Based Reasoning (CBR) algorithms, and the performance of the feature extraction technique was evaluated in terms of sensitivity, specificity, F1 score, and accuracy.

Keywords

ANN, CBR, Feature extraction, Fuzzy logic, Median filtering, Neuro-fuzzy, Smart farming

Citation

COMPUTERS & ELECTRICAL ENGINEERING. 2023, vol. 109,Part A, issue July 2023, p. 1-14.
https://www.sciencedirect.com/science/article/pii/S0045790623001635

Document type

Peer-reviewed

Document version

Accepted version

Date of access to the full text

2025-05-16

Language of document

en

Document licence

Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
http://creativecommons.org/licenses/by-nc-nd/4.0/