Grouping of Covid-19 Affected Areas in Bogor City Using The K-Means Algorithm

Abstract

Clustering plays an important role in processing big data, making predictions and overcoming anomalies in data, identical characteristics in data sets are grouped using iterative techniques. Because data is always evolving from day to day, very large data sets with little can be identified into interesting patterns by grouping, special methods are needed to handle it. In December 2019 there was an outbreak of acute respiratory syndrome caused by coronavirus 2 infection that occurred in Wuhan and on February 12, 2020, the World Health Organization officially named the disease Corona Virus 2019 (Covid 19). This research will conduct clustering of areas affected by Covid 19 in the City of Bogor. The clustering was done using the K-Means method and dividing the data into 3 clusters, namely the low-impact cluster, the medium-impact cluster and the high-impact cluster. The results showed that from 68 urban villages in the city of Bogor, 45% of the area was in the low-affected category, 35.29% of the area was in the medium-affected category and 19.12% of the area was in the high-affected category.