TY - JOUR AU - Deswiaqsa, Kathina AU - Darmawan, Endang AU - Sugiyarto, Sugiyarto PY - 2022/09/06 Y2 - 2024/03/29 TI - Application of K-Means for Clustering Based on the Severity of COVID-19 in Indonesian Private Hospitals: Application of K-Means for Clustering Based on the Severity of COVID-19 JF - EKSAKTA: Journal of Sciences and Data Analysis JA - EKSAKTA: J. Sci. Data Anal. VL - 3 IS - 2 SE - Research Articles DO - 10.20885/EKSAKTA.vol3.iss2.art5 UR - https://journal.uii.ac.id/Eksakta/article/view/23535 SP - AB - <p><span class="fontstyle0">In December 2019, coronavirus (COVID-19) caused by SARS-CoV-2 was first discovered in Wuhan, China. This virus has a high transmission rate and can be transmitted through droplets, airborne, and aerosols. The clinical manifestations are very diverse ranging from mild, moderate, and severe. Therefore, this study aims to conduct a clustering of the spread of the Covid-19 pandemic to facilitate the identification and handling. The method of the K-Means algorithm can be used as a method to obtain the desired clustering. The implementation and evaluation were conducted using RapidMiner tools and Davies Bouldin Index (DBI) respectively. Furthermore, the data sources by Kangdra (2020) were used with a total sample of 110 for the period March-June 2020. The results showed that the optimal cluster is located at k: 2 with a DBI value: 0,094 as the lowest value. Therefore, the cluster is strong since a smaller DBI value gives a better cluster. The clustering obtained is Cluster 1 and 2 with mild and moderate severity. The results are expected to facilitate a better zone identification of the COVID-19 severity level and rising people awareness.</span></p> ER -