The application of K-means clustering for province clustering in Indonesia of the risk of the COVID-19 pandemic based on COVID-19 data.
The application of K-means clustering for province clustering in Indonesia of the risk of the COVID-19 pandemic based on COVID-19 data.
复制标题
DOI：
10.1007/s11135-021-01176-w
复制
发表时间：
2022
影响因子：
--
通讯作者：
Hidayat R
中科院分区：
文献类型：
--
作者：
Abdullah D;Susilo S;Ahmar AS;Rusli R;Hidayat R
这项研究旨在根据冠状病毒病2019年(新冠肺炎)的数据，对印度尼西亚各省感染新冠肺炎大流行的风险进行聚类。这一聚类基于2020年4月19日从印度尼西亚新冠肺炎工作组(SATGAS新冠肺炎)获得的数据。根据新冠肺炎确诊病例、死亡病例和恢复病例的数据，对印度尼西亚各省进行了分组。这是使用K-均值聚类法进行的。聚类产生了3个省级组。预计省级聚类的结果将为政府制定与限制社区活动相关的政策或其他克服新冠肺炎传播的政策提供意见。基于印度尼西亚新冠肺炎病例的省级聚类是根据确诊、康复和死亡病例确定省份的接近或相似程度的尝试。根据本研究的结果，有3个省份的集群。
This study was conducted with the aim to the clustering of provinces in Indonesia of the risk of the COVID-19 pandemic based on coronavirus disease 2019 (COVID-19) data. This clustering was based on the data obtained from the Indonesian COVID-19 Task Force (SATGAS COVID-19) on 19 April 2020. Provinces in Indonesia were grouped based on the data of confirmed, death, and recovered cases of COVID-19. This was performed using the K-Means Clustering method. Clustering generated 3 provincial groups. The results of the provincial clustering are expected to provide input to the government in making policies related to restrictions on community activities or other policies in overcoming the spread of COVID-19. Provincial Clustering based on the COVID-19 cases in Indonesia is an attempt to determine the closeness or similarity of a province based on confirmed, recovered, and death cases. Based on the results of this study, there are 3 clusters of provinces.