Ikhwan, Muhammad (2025) Klasifikasi Penyakit pada Kambing Berdasarkan Gejala Menggunakan Algoritma Random Forest. Other thesis, Universitas Islam Riau.

Text skripsi_203510389_watermark.pdf - Submitted Version Restricted to Registered users only Download (5MB) | Request a copy

Abstract

Goat farming is one of the key sectors in the rural economy. However, limited knowledge among farmers regarding goat diseases and the lack of medical personnel in the field often lead to delays in diagnosis and treatment. This study aims to design and develop a disease classification system for goats based on clinical symptoms using the Random Forest algorithm. The Random Forest method was chosen for its ability to produce accurate classifications, resistance to overfitting, and its capability to handle large and complex datasets. The data used was obtained from the Department of Livestock, Fisheries, and Marine Affairs of Siak Regency, totaling 634 records comprising 28 symptom features and 13 types of diseases. The system development process includes data collection, preprocessing, data splitting (train-test split), model training, evaluation using a confusion matrix, and implementation of a web-based system using Python and the Flask framework. The evaluation results indicate that the system can accurately and automatically identify goat diseases based on the symptoms entered by the user. The highest accuracy was achieved with a 70% training and 30% testing data split, yielding an accuracy of 88%, precision of 90%, recall of 91%, and an F1-score of 90%. This system is expected to assist medical personnel and farmers in accelerating the diagnosis process and reducing the risk of disease misclassification.

Actions (login required)

View Item