Implementation of Naïve Bayes Method with Certainty Factor for Disease and Pest Diagnosis on Onion Plants

Abstract

Shallots can be regarded as non-substituted, which is a plant that is used as a food seasoning and herbal medicine. Every year, the demand for shallots is increasing. But along with the ever-increasing demand, it is inversely proportional to the lack of availability. The cause of this is the lack of knowledge about shallot cultivation, including pest and disease disturbances. The purpose of this research is to help farmers diagnose early diseases and pests that attack shallot plants. With the presence of these pests and diseases, a system that contains knowledge from an expert is needed to diagnose early symptoms experienced by plants. In this study, the authors created an expert system for the diagnosis of diseases and pests on shallot plants. Researchers used the Naïve Bayes method as a classification method for each selected symptom. Then the Certainty Factor as a method of determining the value of confidence in the diagnosis results in the first method. In this study, it produced an accuracy rate of 97%.