CFP last date
22 April 2024
Reseach Article

Comparison of Naïve Bayes and Random Forest Methods for Diabetes Prediction

by Winda Hasanah, Lulu Chaerani Munggaran
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 174 - Number 26
Year of Publication: 2021
Authors: Winda Hasanah, Lulu Chaerani Munggaran
10.5120/ijca2021921184

Winda Hasanah, Lulu Chaerani Munggaran . Comparison of Naïve Bayes and Random Forest Methods for Diabetes Prediction. International Journal of Computer Applications. 174, 26 ( Mar 2021), 13-18. DOI=10.5120/ijca2021921184

@article{ 10.5120/ijca2021921184,
author = { Winda Hasanah, Lulu Chaerani Munggaran },
title = { Comparison of Naïve Bayes and Random Forest Methods for Diabetes Prediction },
journal = { International Journal of Computer Applications },
issue_date = { Mar 2021 },
volume = { 174 },
number = { 26 },
month = { Mar },
year = { 2021 },
issn = { 0975-8887 },
pages = { 13-18 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume174/number26/31837-2021921184/ },
doi = { 10.5120/ijca2021921184 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-07T00:23:08.870034+05:30
%A Winda Hasanah
%A Lulu Chaerani Munggaran
%T Comparison of Naïve Bayes and Random Forest Methods for Diabetes Prediction
%J International Journal of Computer Applications
%@ 0975-8887
%V 174
%N 26
%P 13-18
%D 2021
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Diabetes is a chronic metabolic disorder in which blood sugar levels exceed normal limits. Riskesdas Ministry of Health in 2018 showed the prevalence of diabetes mellitus in Indonesia increased from 2013. Classification is one of the solutions to decrease the prevalence of diabetes in Indonesia. In this research, Classification is used to predict diabetes by building a classification model. The research steps are data collection, split the dataset into training data and test data, build a classification model using the Naïve Bayes and Random Forest methods, and evaluate the model. The results showed that the Random Forest method has the best performance with accuracy = 100%, error = 0%, precision = 1 and recall = 1. The best ratios in classifying the diabetes dataset are 70:30 and 90:10.

References
  1. Annisa, R. (2019). Analisis Komparasi Algoritma Klasifikasi Data Mining Untuk Prediksi Penderita Penyakit Jantung. JTIK (Jurnal Teknik Informatika Kaputama), 3(1), 22-28.
  2. Primajaya, A., & Sari, B. N. (2018). Random Forest Algorithm for Prediction of Precipitation. Indonesian Journal of Artificial Intelligence and Data Mining, 1(1), 27-31.
  3. Widaningsih, S. (2019). Perbandingan Metode Data Mining Untuk Prediksi Nilai Dan Waktu Kelulusan Mahasiswa Prodi Teknik Informatika Dengan Algoritma C4, 5, Naïve Bayes, Knn Dan Svm. Jurnal Tekno Insentif, 13(1), 16-25.
  4. Rahmaulidyah, F. N. (2020). Perbandingan Metode Klasifikasi Naive Bayes dan K-Nearest Neighbor pada Data Status Pembayaran Pajak Pertambahan Nilai di Kantor Pelayanan Pajak Pratama Samarinda Ulu (Doctoral dissertation, universitas mulawarman).
  5. Purnamawati, A., Nugroho, W., Putri, D., & Hidayat, W. F. (2020). Deteksi Penyakit Daun pada Tanaman Padi Menggunakan Algoritma Decision Tree, Random Forest, Naïve Bayes, SVM dan KNN. InfoTekJar: Jurnal Nasional Informatika dan Teknologi Jaringan, 5(1), 212-215.
  6. Effendi, M. T., Hidayat, N., & Dewi, R. K. (2019). Sistem Diagnosis Penyakit Tumbuhan Mangga Menggunakan Metode Naive Bayes. Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer e-ISSN, 2548, 964X.
  7. Amiarrahman, M. R., & Handhika, T. (2018). Analisis dan implementasi algoritma klasifikasi Random Forest dalam pengenalan Bahasa Isyarat Indonesia (BISINDO). In Prosiding SEMNAS INOTEK (Seminar Nasional Inovasi Teknologi) (Vol. 2, No. 1, pp. 083-088).
Index Terms

Computer Science
Information Sciences

Keywords

Classification Naïve Bayes Algorithm Random Forest Algorithm Diabetes