Application of Bayes’ Theorem in an Expert System for Diagnosing Mangosteen Diseases and Pests

Abstract

Mangosteen is one of the typical fruits of Southeast Asia and Indonesia's flagship fruit with promising export prospects. However, the poor quality of the mangosteen fruit, which is caused by diseases and pest attacks, is an obstacle in increasing export targets. Disease and pest attacks can be immediately overcome if farmers can identify the types of pests and diseases quickly based on the symptoms that appear on the mangosteen plant. The lack of knowledge of farmers in identifying the symptoms that appear and the limited number of experts lead to the late process of handling pests and diseases of the mangosteen plant. Therefore, this study aimed to build an expert system for diagnosing mangosteen diseases and pests using Bayes’ theorem. The knowledge base contained data of 5 diseases, 5 pests, and 42 symptoms. The inference engine utilized the Bayes’ theorem to produce a probability value of a disease or pest attacking the mangosteen plant based on the symptoms that arise. This study yielded an accuracy value of 94% based on 50 test data. This expert system can help farmers in identifying the diseases and pests that attack mangosteen plants quickly as well as finding solutions to the problem.