Jurnal Sistem Komputer dan Informatika (JSON)
Vol 4, No 3 (2023): Maret 2023

Penerapan Data Mining untuk Menentukan Penyebab Kematian di Indonesia Menggunakan Metode Clustering K-Means

Lili Rahmawati (Universitas Islam Negeri Sultan Syarif Kasim Riau, Pekanbaru)
Alwis Nazir (Universitas Islam Negeri Sultan Syarif Kasim Riau, Pekanbaru)
Fadhilah Syafria (Universitas Islam Negeri Sultan Syarif Kasim Riau, Pekanbaru)
Elvia Budianita (Universitas Islam Negeri Sultan Syarif Kasim Riau, Pekanbaru)
Lola Oktavia (Universitas Islam Negeri Sultan Syarif Kasim Riau, Pekanbaru)
Ihda Syurfi (Universitas Islam Negeri Sultan Syarif Kasim Riau, Pekanbaru)



Article Info

Publish Date
31 Mar 2023

Abstract

Death in medical science is studied in a scientific discipline called tanatology. death is not only experienced by elderly people, but also can be experienced by young people, teenagers, or even babies. Death can be caused by various factors, namely, due to illness, old age, accidents, and so on. Based on information provided by the World Health Organization (WHO), there are five highest causes of death including ischemic heart disease, Alzheimer's, stroke, respiratory disorders, neonatal conditions. In this study, k-means is used to group causes of death in Indonesia based on the number of deaths that occur to determine the cases of death that have the most impact on the high mortality rate in Indonesia. Knowing what these death cases are will provide early preparation in anticipating the causes of death in Indonesia. The purpose of this study was to classify mortality rates based on the number of causes of death which were included in the low, medium, and high clusters by applying the K-Means method. In this study the authors used the K-Means clustering algorithm to classify death rates in data on causes of death in Indonesia from 2017-2021. The results of this study formed 3 clusters which were evaluated using the Davies Bouldin Index (DBI) in Rapidminer with a value of 0.259. Clustering results from a total of 21 cases obtained high, medium and low clusters. This cluster grouping was obtained according to the number of deaths per case, namely the first cluster (C0) was low with 17 cases, the second cluster (C1) was moderate with 3 cases and the third cluster (C2) was high with 1 case.

Copyrights © 2023






Journal Info

Abbrev

JSON

Publisher

Subject

Computer Science & IT Control & Systems Engineering

Description

The Jurnal Sistem Komputer dan Informatika (JSON) is a journal to managed of STMIK Budi Darma, for aims to serve as a medium of information and exchange of scientific articles between practitioners and observers of science in computer. Focus and Scope Jurnal Sistem Komputer dan Informatika (JSON) ...