Penerapan Algoritma K-Means clustering Untuk Mengelompokkan Provinsi Berdasarkan Banyaknya Desa/Kelurahan Dengan Upaya Antisipasi/Mitigasi Bencana Alam

Abstract

Natural disasters are one of the natural phenomena that threaten human survival. The negative impacts can be in the form of material or non-material losses. However, with the ability to recognize the early symptoms of a disaster, humans can prepare themselves for disaster. Application of the K-Means clustering Algorithm in Grouping Provinces Based on the Number of Villages / Sub-districts with Anticipation / Mitigation Efforts for Natural Disasters Using the WEKA Application. The data sources for this research were collected based on documents describing the Number of Villages/ Urban According to Natural Disaster Anticipation/Mitigation Efforts produced by the National Statistics Agency. The data used in this study is provincial data which consists of 34 provinces. There are 4 variables used, namely Natural Disaster Early Warning System, Tsunami Early Warning System, Safety Equipment, Evacuation Path. The data will be processed by clustering in 2 clusters, namely clusters with high anticipation/mitigation levels and low anticipation/mitigation levels. The results obtained from the assessment process are that there are 5 (14.71 %) provinces with a high level of anticipation/mitigation and 29 (85.29%) other provinces including a low level of anticipation/mitigation. This can be an input for the government to pay more attention to the Village/Kelurahan based on the clusters that have been carried out