Optimization of k-means clustering using particle swarm optimization algorithm for human development index

Laili, Ufil Hidayatul, Faisal, Muhammad ORCID: https://orcid.org/0000-0003-4884-7254 and Kurniawan, Fachrul ORCID: https://orcid.org/0000-0002-3709-8764 (2024) Optimization of k-means clustering using particle swarm optimization algorithm for human development index. Bulletin of Social Informatics Theory and Application. Indonesia. ISSN 2614-0047

Text 21131.pdf Download (512kB)

Abstract

K-Means algorithm can be used to cluster the Human Development Index in East Java in particular for the people, the hope is that with this development all the problems that exist in the community including poverty, unemployment, school dropouts, health and social inequality can be resolved. However, this algorithm has a weakness that is sensitive to the determination of the initial centroid. Initial centroids that are determined randomly will reduce the level of accuracy, often get stuck at the local optimum, and get random solutions. Optimization algorithms such as PSO can overcome this by determining the optimal initial centroid. The quality of clusters produced by K-Means algorithm with and without PSO algorithm ismeasured using the average Silhouette Coefficient (SC). In this study, better accuracy was obtained between pure kmeans and PSO based kmeans where the comparison value of pure kmeans was 0.27% while PSO based kme

Item Type:	Journal Article
Keywords:	Human development index; K-means clustering; particle swarm optimization
Subjects:	08 INFORMATION AND COMPUTING SCIENCES > 0899 Other Information and Computing Sciences > 089999 Information and Computing Sciences not elsewhere classified
Divisions:	Graduate Schools > Magister Programme > Graduate School of Informatics Engineering
Depositing User:	Fachrul Kurniawan
Date Deposited:	31 Oct 2024 13:27

Downloads

Origin of downloads

Actions (login required)

View Item