Ensemble Klasifikasi Penyakit Tuberculosis Pada Hasil Pengobatan Menggunakan Metode Hybrid K-Nearest Neighbor (K-NN), Decision Tree dan Support Vector Machine (SVM)

Alya Nurfaiza Azzahra (Universitas Dian Nuswantoro, Semarang)
Junta Zeniarja (Universitas Dian Nuswantoro, Semarang)
Ardytha Luthfiarta (Universitas Dian Nuswantoro, Semarang)
Mufida Rahayu (Universitas Dian Nuswantoro, Semarang)

JURNAL MEDIA INFORMATIKA BUDIDARMA
Vol 8, No 1 (2024): Januari 2024

Tuberculosis (TB) is an infectious disease with the highest cause of death in the world. This disease can be transmitted through the air and attacks the pulmonary respiratory system. The increase in TB cases from year to year is due to little information about the treatment of this disease. This requires the process of diagnosing and treating TB requiring accurate data analysis. From these problems, classification of tuberculosis disease is needed to improve better treatment results. In this study, experiments were used with the Hybrid model classification algorithm with a method that combines three approaches, namely K-Nearest Neighbor (K-NN), Decision Tree, Support Vector Machine (SVM) to classify treatment results using the Ensemble classification method and aims to combine each method in order to create a stronger Ensemble model and increase accuracy in treatment results, using data from the Semarang City Health Service or what is called Tuberculosis Information System (SITB) data in 2020-2023 with 80% training data and test data 20%. Based on the results of testing and analysis using the confusion matrix, the highest accuracy value was obtained at 78.55% using K-Fold Cross validation, namely k equals 7 and the Ensemble model obtained high results for treatment outcomes.