Perbandingan Metode Perhitungan Jarak pada Nilai Centroid dan Pengelompokan Data Menggunakan K-Means Clustering

This study will observe the process of grouping data or forming clusters using K-Means with three methods measuring distances, namely Euclidean distance, Manhattan and Minkowski distance. Observations are more focused on changing centroid value results data, as well number iterations required. Experimental amounted to 20, 30, 40, 50 pieces which were grouped into 2 groups. research also summarizes application have been widely used in various fields, including Health, Education, Disaster. The distance measurement not too much different, highest difference is members test data. most 40 use 7 iterations, least iteration 20 uses i.e. 3 iterations. On it takes 4 amount directly proportional needed reach cluster a stable state.