Sistem Pakar Berbasis Web Untuk Diagnosis Penyakit Mulut Dan Kuku Pada Sapi Menggunakan Metode Forward Chaining

Aditya, Livindra Dwi (2026) Sistem Pakar Berbasis Web Untuk Diagnosis Penyakit Mulut Dan Kuku Pada Sapi Menggunakan Metode Forward Chaining. Undergraduate thesis, Politeknik Negeri Jember.

	Text (Abstract) Abstract.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (234kB)
	Text (Bab 1 Pendahuluan) Bab 1 Pendahuluan.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (243kB)
	Text (Daftar Pustaka) Daftar Pustaka.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (200kB)
	Text (Laporan Lengkap) Laporan Lengkap.pdf - Submitted Version Restricted to Registered users only Download (4MB) | Request a copy

Abstract

Foot and Mouth Disease (FMD) is a contagious disease in cloven-hoofed livestock that can reduce productivity and cause economic losses in the livestock sector. Limited farmer knowledge in recognizing early symptoms of FMD and the limited number of veterinary experts often result in delayed diagnosis. This study aims to develop a web-based expert system for diagnosing Foot and Mouth Disease in cattle using the Forward Chaining method integrated with image processing and the K-Nearest Neighbor (KNN) algorithm. The system was developed using the waterfall method, which consists of requirement analysis, design, implementation, testing, and maintenance stages. The data used include symptom data, diagnostic rules, and a dataset of 1.400 cattle images obtained from Kaggle. The image preprocessing stage includes resizing images to 256×256 pixels and applying Otsu thresholding, followed by RGB and HSV color feature extraction, GLCM texture feature extraction, and feature normalization before classification using KNN. The expert system applies IF-THEN rules based on the Forward Chaining method to determine disease diagnosis according to the symptoms selected by the user. The confusion matrix evaluation showed that the K-Nearest Neighbor method achieved an accuracy of 96,44%. These results indicate that the system was able to classify healthy and infected cattle images effectively. Black Box Testing showed that all system functions operated properly, while usability testing using the System Usability Scale (SUS) indicated that the system was easy to use by users. The developed system is expected to assist farmers in performing early detection of FMD more quickly, effectively, and conveniently through a web-based platform.

Actions (login required)

View Item