Determining a Cluster Centroid of Kmeans Clustering Using Genetic Algorithm

Abdullah, Dahlan (2015) Determining a Cluster Centroid of Kmeans Clustering Using Genetic Algorithm. International Journal of Computer Science and Software Engineering (IJCSSE), 4 (6). pp. 160-164. ISSN 2409-4285

Preview

Text p4-V4I6.pdf Download (304kB) | Preview

Abstract

Clustering is a function of data mining that served to define clusters (groups) of the object in which objects are in one cluster have in common with other objects that are in the same cluster and the object is different from the other objects in different clusters. One method of clustering that can be used is the K-Means Clustering are included in the category of partitioning methods. One of the stages yan important in the K-Means Clustering is the cluster centroid determination, which will determine the placement of an object into a cluster based on the shortest distance between the object coordinate with cluster centroid. Genetic algorithms can be used in determining the initial value of the cluster centroid. the data set used in this study is the Iris data sets derived from the UCI Machine Learning Repository. Genetic algorithm is a heuristic search algorithm based on the idea of natural selection that Occurs in the process of evolution and genetic operations. This algorithm perform an intelligent search for a solution and have a broad spectrum of possible sollution. The determination of the initial value of the cluster centroid using genetic algorithms can provide better results than by using random numbers.

Actions (login required)

View Item