Sistem Pakar Diagnosa Hama Dan Penyakit Pada Tanaman Buah Naga Menggunakan Metode Forward Chaining dan Certainty Factor

Aprialsyah, Muhammad Syahril (2026) Sistem Pakar Diagnosa Hama Dan Penyakit Pada Tanaman Buah Naga Menggunakan Metode Forward Chaining dan Certainty Factor. Skripsi thesis, Universitas Islam Negeri Imam Bonjol Padang.

	Text (Cover - Daftar Isi) Cover - Daftar Isi.pdf - Published Version Download (1MB)
	Text (BAB I) BAB I.pdf - Published Version Download (493kB)
	Text (BAB III) BAB III.pdf - Published Version Download (529kB)
	Text (BAB V - Daftar Pustaka) BAB V - Daftar Pustaka.pdf - Published Version Download (359kB)
	Text (Full Text) SKRIPSI FULL TEXT.pdf - Published Version Restricted to Repository staff only Download (5MB)

Abstract

Dragon fruit (Hylocereus spp.) production in West Sumatra Province has fluctuated, with pest and disease infestations being one of the main contributing factors. Farmers commonly diagnose these problems based on personal experience without a structured guide, increasing the risk of misidentification due to similar symptoms among different pests and diseases. This study aims to develop an expert system for diagnosing pests and diseases of dragon fruit plants using the Forward Chaining and Certainty Factor (CF) methods, and to evaluate its level of agreement with agricultural expert diagnoses.This study employed the Research and Development (R&D) method with the Waterfall development model, comprising requirement analysis, system design, implementation, and testing. The system's knowledge base consisted of 13 diagnostic objects, comprising 7 pest types (H01–H07) and 6 disease types (P01–P06), along with 76 symptoms (G01–G76), which were compiled through literature review and interviews and subsequently validated by an expert from the West Sumatra Center for Agricultural Research and Modernization (BRMP). The system was implemented as a web application using React.js and Supabase.The Forward Chaining method was used as the inference mechanism to determine diagnoses based on user-selected symptoms, while the Certainty Factor method combined user confidence (CF User) and expert confidence (CF Expert) to calculate the diagnosis confidence percentage. System testing included Black Box Testing and accuracy testing using 10 expert-validated test cases. The test results showed that all 10 test cases (10 out of 10) matched the expert's diagnosis, with system CF values ranging from 98.08% to 100.00%, yielding an overall system accuracy of 100%. These results indicate that the developed system is capable of producing diagnoses consistent with expert assessments across all tested cases, and is therefore feasible for use as a fast, systematic, and reliable preliminary diagnostic tool for dragon fruit pests and diseases.

Actions (login required)

View Item