Mapping Spread Virus COVID-19 in India Using K-Means Clustering

ABSTRACT

Covid have confirmed as pandemic global by the World Health Organization (WHO), because spread that very fast among humans. As a result of the Covid-19 virus, many infected patients died, including from all countries on the Asian continent. Like the case that occurred in one of the Asian countries, namely India, which is one of the countries that experienced a spike in Covid-19 cases, the transmission of thevirus Covid-19 in India penetrated more than 400,000 cases in 1 day. The number is the highest daily record set by India during the Covid-19 pandemic. However, it was found that the problem of the spread of Covid-19 tends to increase, this is the country with the second largest population in the world. The total number of Covid-19 cases in the country has reached 21 million or second only to the United States. The vastness of India's territory allows the need for grouping the parts by region in India. This grouping produces the center points for the spread of Covid-19 cases. The purpose of grouping Covid-19 cases based on clusters is to find out the weight/percentage value generated from each of these clusters using the K-Means Clustering method. This method is used to map the spread of the Covid-19 virus from various regions in India based on confirmed cases, dead, recovered and active/new clusters. The benefits obtained for the government in overcoming Covid-19 cases are to create strategies to prevent the spread of Covid-19 based on information from the results of regional clustering in India The results obtained from research conducted in 38 regions in India using 4 clusters resulted in Confirmed cases (C0) 199 items, Died (C1) 779 items, Recovered (C2) 21 items, and Active/new cluster (C3) 231 items with a totalcluster of 1230items. © 2021 IEEE.