Perbandingan Metode Perhitungan Jarak Euclidean dengan Perhitungan Jarak Manhattan pada K-Means Clustering Dalam Menentukan Penyebaran Covid di Kota Bekasi

Abstract

Clustering is a method of grouping in an information database based on certain conditions. The research applies the k-means clustering calculation problem with the euclidean distance calculation approach with the manhattan distance calculation. The method formed aims to compare in terms of the working process between the calculation of the Euclidean distance with the calculation of the Manhattan distance. The result is a comparison of the distance calculation between the distance calculation euclidean and the distance calculation manhattan in terms of the work process to be able to determine the center points of the spread of the covid disease from the comparison of the distance calculation Euclidean and the distance calculation Manhattan. The calculation results obtained are the K-Means calculation with the euclidean distance calculation approach, the number of iterations is 15 times, while by using the manhattan distance calculation, the number of iterations is 7 times. So it is concluded that in terms of processing manhattan is faster than euclidean. The calculation results obtained are the results of calculations from Covid-19 data in Bekasi City up to September 1, 2021.