Implementasi Support Vector Machine untuk Klasifikasi Kasus Monkeypox: Pendekatan Oversampling dan Undersampling untuk Mengatasi Ketidakseimbangan Kelas

摘要

Monkeypox is an infectious disease caused by the monkeypox virus. This study applies the Support Vector Machine (SVM) method to classify monkeypox cases. Utilizing SVM aids in accurate diagnosis and prevention measures. Preprocessing involves Random Oversampling (ROS) and Random Undersampling (RUS) to address class imbalance in symptom datasets. SVM classification is based on systemic symptoms and clinical signs. Evaluation via Confusion Matrix assesses accuracy, sensitivity, specificity, and AUC, with average accuracy reaching 67.1% for imbalanced data and 36.5% for balanced data. The method outperforms conventional techniques, demonstrating its potential in monkeypox symptom pattern recognition. Results indicate higher accuracy in diagnosing monkeypox using SVM, despite class imbalances. This study contributes to understanding, predicting, and managing monkeypox outbreaks effectively.