Optimizing the Evaluation of K-means Clustering Using the Weight Product
Rozzi Kesuma Dinata, Bustami, Sujacka Retno · Revue d intelligence artificielle · 2024
In the process of the K-means clustering algorithm, one of the issues that arises is the high number of iterations.This study aims to optimize the cluster evaluation results in K-means by reducing iterations through the application of the Weight Product Model (WPM).The evaluation method used in this research is the Davies-Bouldin Index (DBI).Three datasets were analyzed: the QSAR Dataset consisting of 908 data points, 7 attributes; the Whoscale Customer dataset consisting of 440 data points, 8 attributes from the UCI Machine Learning Repository, as well as direct observational data from captured fisheries obtained from the North Aceh District Office of Marine and Fisheries, Indonesia consisting of 75 data points, 8 attributes.The results of 10 testing iterations on three different datasets show that for the QSAR Dataset, the average cluster evaluation using DBI with K-means is 0.852.However, when applying WPM+K-means, the average DBI value increases to 0.727, with the average number of K-means iterations reduced from 23 to 8 iterations.For the Whoscale Customer dataset, the average cluster evaluation using DBI with K-means is 0.921.In contrast, when employing WPM+K-means, the average DBI value slightly improves to 0.910, accompanied by a reduction in the average number of K-means iterations from 23 to 10 iterations.In the case of the captured fisheries dataset, the average cluster evaluation using DBI with K-means yields a value of 1.222.However, implementing WPM+K-means results in an improved average DBI of 1.052.Furthermore, the average number of K-means iterations is reduced to 9 iterations, whereas for WPM+K-means, this number is reduced to 4 iterations.The results of this study demonstrate an improvement in DBI values, where lower DBI values indicate better performance of the K-means algorithm.These also findings demonstrate that WPM is effective in optimizing cluster evaluation values in Kmeans clustering.With the reduction in the number of K-means iterations, computational time is expected to be faster.