DIAGNOSIS CLASSIFICATION OF SOYBEAN DISEASE USING MACHINE LEARNING TECHNIQUES

Abstract

The prevention of disease transmission in plants is largely dependent on early detection of pathogen infection. Plant diseases can be identified using machine learning techniques before they fully manifest their symptoms. The more problems have been solved, the more reliable systems have been built. This system developed the agricultural field. Machine learning is a new area of study for agricultural analysis. Machine learning is a new area of study for agricultural analysis. The use of machine learning techniques in the sector of agriculture is the main topic of this study. Different machine learning techniques are in use, such as k-Nearest Neighbors (k-NN), J48 Decision Trees, Nave Bayes and Decision Table for very recent applications of data mining techniques in the agriculture field. This thesis properly classifies the problem of soybean diseases. For this purpose, different types of machine learning techniques were evaluated on soybean disease data sets. This thesis discusses the development of an expert system to diagnose soybean disease using machine learning techniques. This system implemented the K-folds cross validation method by using K value changes.