Grouping the spread of the covid-19 virus based on the positive case number, population and area width using the k-means clustering method
| Autor: | Asep Muhidin, Muhtajudin Danny, Elkin Rivali |
|---|---|
| Rok vydání: | 2021 |
| Předmět: | |
| Zdroj: | ILKOM Jurnal Ilmiah. 13:314-321 |
| ISSN: | 2548-7779 2087-1716 |
| DOI: | 10.33096/ilkom.v13i3.1011.314-321 |
| Popis: | The spread of the Covid-19 virus began to enter Indonesia in early 2020. Until now, the spread of the virus is still occurring in several parts of Indonesia, although it has begun to decline in many areas. ). The possibility of direct human contact depends on the number of confirmed positives, the population and the area. Therefore, this study looks for the characteristics of the city/district area group based on the population, area and number of residents who are confirmed positive for the Covid-19 virus using the K-Means Clustering method. The clustering process begins with finding the best number of clusters (K) using the elbow method and testing cluster members using the silhouette and davies-bouldin index methods. The best K value results obtained by the elbow method are 3 clusters (K=3). The results of K-Means Clustering with 3 clusters show that in cluster 1, a city or district with a small area with a large population, the number of positive COVID-19 residents is large. In cluster 2, a city or district with a small area, with a moderate population, the number of people who are positive for COVID-19 is small. And in cluster 3, a city or district with a large area, with a very small population, the number of positive COVID-19 residents tends to be moderate. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|