Sistem Pakar Diagnosis Penyakit Tanaman Padi Menggunakan Forward Chaining dan Dempster Shafer

Abstract

Rice (Oryza sativa) is one of the main commodities in Indonesia. One of the inhibitors of rice crop production is disease. Rice plant diseases can be caused by pathogens, host plants or bad environment. The process of diagnosing rice diseases requires expertise, knowledge and experience. This study aims to build an expert system that can diagnose 13 types of rice plant diseases from 43 symptoms based on the knowledge of 3 experts with forward chaining reasoning methods and mobile-based dempster shafer calculation methods. The testing technique used is black box testing, theoretical calculation testing, system accuracy testing and MOS (Mean Opinion Score) testing. The black box test results state that the expert system has 100% compatibility in terms of functionality. The theoretical calculation test results state that the expert system calculations are in accordance with the results of manual calculations. System accuracy testing results from 30 test cases get an accuracy of 81.11%. The results of MOS testing conducted on 30 respondents produced MOS of 4.2 from a scale of 5 categorized into a good system.