Sistem Pakar Diagnosis Penyakit Sapi Menggunakan Metode Forward Chaining dan Certainty Factor dengan Parameter Optimasi Tingkat Keparahan Gejala

Cattle diseases are one of the factors that reduce livestock productivity and cause economic losses for farmers if they are not detected at an early stage. Limited access to veterinary services and farmers' lack of knowledge regarding disease symptoms often hinder the initial diagnosis process. This study aims to develop a web-based expert system to support the early detection of diseases in beef cattle using the Forward Chaining and Certainty Factor methods. The Forward Chaining method is employed to perform rule-based inference based on the symptoms selected by users to identify potential diseases, while the Certainty Factor method is used to calculate the confidence level of the diagnosis by combining expert certainty values with the severity level of symptoms provided by farmers. The system was developed using the Laravel framework with React, Inertia.js, and MySQL as the database management system. The knowledge base was acquired through knowledge elicitation with a veterinarian and consists of 10 cattle diseases, 33 symptoms, and 10 diagnostic rules. Functional testing was conducted using the Black Box Testing method, while diagnostic validation was performed by comparing the system's results with expert diagnoses using 30 simulated test scenarios representing each disease. The Black Box Testing results indicate that all system functions operated according to the specified requirements. Furthermore, the validation results demonstrate that the system produced diagnoses consistent with the expert's assessment for all simulated test cases, resulting in an accuracy rate of 100%. Therefore, the developed expert system is capable of assisting farmers in performing early detection of cattle diseases efficiently while providing supporting information as an initial basis for decision-making before further examination by a veterinarian.