Oversampling Method on Classifying Hypertension Using Naive Bayes, Decision Tree, and Artificial Neural Network

Abstract

Oversampling is a technique to balance the number of data records for each class by generating data with a small number of records in a class, so that the amount is balanced with data with a class with a large number of records. Oversampling in this study is applied to hypertension dataset where hypertensive class has a small number of records when compared to the number of records for non-hypertensive classes. This study aims to evaluate the effect of oversampling on the classification of hypertension dataset consisting of hypertensive and non-hypertensive classes by utilizing the Naïve Bayes, Decision Tree, and Artificial Neural Network (ANN) as well as finding the best model of the three algorithms. Evaluation of the use of oversampling on hypertension dataset is done by processing the data by imputing missing values, oversampling, and transforming data into the same range, then using the Naïve Bayes, Decision Tree, and ANN to build classification models. By dividing 80% of data as training data to build models and 20% as validation data for testing models, we had an increase in classification performance in the form of accuracy, precision, and recall of the oversampled data when compared without oversampling. The best performance in this study resulted in the highest accuracy using ANN with 0.91, precision 0.86 and recall 0.99.

Keywords

• oversampling
• hypertension
• naive bayes
• decision tree
• ann