<![CDATA[Monkeypox is an infectious disease that spreads rapidly and requires an accurate early detection system. This study aims to develop a monkeypox disease classification model by overcoming data imbalance problems. The method used is Extreme Gradient Boosting (XGBoost) combined with Synthetic Minority Over-sampling Technique (SMOTE). Model evaluation using Confusion Matrix with 69% accuracy, precision of 0.69, recall of 0.93, and F1-score of 0.79. In addition, the Area Under Curve - Receiver Operating Characteristic (AUC-ROC) value reached 0.68. This study shows that the combination of SMOTE and XGBoost can overcome data imbalance and improve minority class detection, thus contributing to the development of a more accurate and efficient infectious disease early detection system.]]>
Copyrights © 2025
