Expert System For Diagnosing Diseases In Honey Guava Plants Using The Certainty Factor Method

Abstract

The rapid development of information technology has encouraged the use of artificial intelligence as a means of supporting decision-making, one of which is through the application of expert systems. Honey guava plants are a superior variety that is widely cultivated. In cultivation practices, the emergence of various diseases is one of the main obstacles, so that effective, fast, and precise handling measures are needed. The development of an expert system in this study was carried out as a solution to help identify diseases that attack honey guava plants through a certainty factor approach. The system's knowledge base is compiled from expert information and scientific references that cover 9 types of diseases and 32 related symptoms. The diagnosis process is carried out by analyzing the combination of symptoms selected by the user, then the system calculates the confidence level using expert weighting values ​​to produce the probability of the disease being detected. Based on the test results, the system output shows a level of accuracy that is in line with manual calculations and expert validation, so this system is considered capable of supporting the process of early disease diagnosis in honey guava plants.