CLUSTERING OF COUNTRIES BASED ON NUMBER OF COVID-19 CASES BY USING DBSCAN ALGORITHM

Abstract

Nowadays, clustering is the important technique for the analysis of data. There are many clustering algorithms. Among them, Density-Based Spatial Clustering of Application with Noise (DBSCAN) is useful for medical domain. Therefore, the clustering of COVID-19 statistic data is implemented by using DBSCAN method. It is a density-based clustering algorithm, grows regions with sufficiently high point density into clusters and discovers cluster of arbitrary shape and size in medical databases. This system clusters in each country occurs the similar number of COVID-19 cases. Three distance measuring methods namely Euclidean, Manhattan and Minkowski are used to calculate the distance between each country and they evaluate the effectiveness of clustering performance in DBSCAN. The silhouette coefficient is used to measure the goodness of clustering quality. According to the experiments, using DBSCAN with Euclidean distance achieved the superior result. This system is implemented by using Python programming language.