K-MEANS CLUSTERING FOR DISEASE SPREAD AREAS DENGUE HEMORRHAGIC FEVER (DHF) IN EAST LOMBOK NTB

Abstract

K-Means is one algorithm in Data Mining that is used to categorize or cluster data. The advantages of K-Means compared to other cluster methods are that it is easy to implement and can be scalable for large datasets. K-Means can be applied in various fields, one of which is the health sector, namely Dengue Haemorrhagic Fever (DHF) data. DHF is one of the environmental health problems that increases in East Lombok Regency, NTB, so clustering is necessary to see the spread of DHF itself. The purpose of this study was to view the description of DHF data and to classify the areas of DHF distribution in East Lombok. Based on the results of the analysis, information was got that the highest number of cases occurred in Selong District, 85 cases and the lowest cases were in Suela and Sembalun Districts, where there were no dengue cases. For the DHF distribution area, we got three clusters. Cluster-1 with a high category that is 13 sub-districts, and Cluster-2 with a low category that is 8 sub-districts.