Methods for Detecting and Classifying Rice Plant Diseases using Machine Learning Technique

Abstract

Rice is the main source of energy for more than half of the world's population. In order to reduce agricultural loss in the paddy field, this work concentrated on creating a prediction model. First, illnesses of rice plants and their pictures were taken. Next, a massive dataset was encountered using a big data framework. In order to produce the reduced data with significant features that are utilized as the input to the classification model, the feature extraction procedure is applied to the data first, followed by feature selection. A rough set theory-based feature selection method is employed for the feature selection task after features based on color, shape, position, and texture are retrieved from the photos of sick rice plants for the rice disease datasets. In order to create an effective illness prediction model, ensemble classification techniques have been applied to the classification problem within a map-reduce framework. The effectiveness of the suggested model is demonstrated by the outcomes on the gathered disease data.