Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : JISKa (Jurnal Informatika Sunan Kalijaga)

Analisis dan Optimalisasi Performa Algoritma Gaussian Naive Bayes pada Prediksi Metabolic Syndrome Menggunakan SMOTE Fauziyah, Nadiyah Jihan; Rahmania, Fadilla; Daniyal, Muhammad; Sari, Nur Fitriyah Ayu Tunjung
JISKA (Jurnal Informatika Sunan Kalijaga) Vol. 9 No. 2 (2024): Mei 2024
Publisher : UIN Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/jiska.2024.9.2.112-122

Abstract

Metabolic syndrome is a complex global health problem, with symptoms such as abdominal obesity, insulin resistance, high blood pressure, high blood sugar, and abnormal blood lipids. With this global challenge, several studies have attempted to predict these diseases using machine learning methods. However, often, predictions about a disease result in data imbalance where minority classes are underrepresented. To balance the class proportions, the Synthetic Minority Over-sampling Technique (SMOTE) method replicates the minority class samples. In this research, the technique applied to predict is the Gaussian Naive Bayes (GNB) algorithm. The results show an increase in prediction accuracy by 0.2 from 0.81 to 0.83. This study confirms the critical role of the SMOTE oversampling method in machine learning using the Gaussian Naive Bayes (GNB) algorithm in Metabolic Syndrome prediction and its positive impact on diagnostic efficiency and public health.