CLUSTERING NEGARA BERDASARKAN SKOR PENGENDALIAN KONSUMSI TEMBAKAU MENGGUNAKAN ALGORITMA DBSCAN

Abstract

Smoking is an activity that has a detrimental impact on the health of individuals, families, communities and the environment, both directly and indirectly. Therefore, it is necessary to control global tobacco consumption. The World Health Organization (WHO) in the Framework Convention on Tobacco Control (FTCT) developed the MPOWER strategy: a which countries can use to control tobacco consumption. In this study a clustering analysis of tobacco use control will be carried out based on the MPOWER score: a from WHO for each country using the Density Based Spatial Clustering of Applications with Noise (DBScan) algorithm. DBSCAN is a cluster formation algorithm based on the level of distance density between objects in a dataset. Using a density radius of 1.72 with a minimum point of 4 objects obtained from the kNNdisplot function on Rstudio produces 4 clusters, 75 data as noise, and the Davies Bouldin-Index value as the best cluster validity is 1.08118.