文章基本信息

标题：Cooperative Swarm based Evolutionary Approach to findoptimal cluster centroids in Cluster Analysis
本地全文：下载
作者：Bighnaraj Naik ; Sarita Mahapatra ; Subhra Swetanisha 等
期刊名称：International Journal of Computer Science Issues
印刷版ISSN：1694-0784
电子版ISSN：1694-0814
出版年度：2012
卷号：9
期号：3
出版社：IJCSI Press
摘要：Centroid-based clustering is a NP-hard optimization problem, and thus the common approach is to search for cluster centers only for approximate solutions. Well-known centroid-based clustering methods are k-means, k-medoids and fuzzy c-means. In this paper we proposed swarm intelligence based natureinspired center-based clustering method using PSO optimization. PSO searches the optimized solution from available solutions in multidimensional search space. So PSO is capable to search best cluster with maximum fitness using social-only model and cognition-only model, such that the square distances from the cluster are minimized. In this article, it is shown that how PSO based clustering can be used to find N number of cluster specified by the user in a dataset. Our suggested method has been tested with artificial dataset and several real multidimensional dataset from UCI repository. Effectiveness of the method is demonstrated by comparing fitness of proposed method with effectiveness of K-means and Fuzzy c-means technique. Results shows that, this method is quite simple, effective and has much potential to search best cluster centers in multidimensional search space.
关键词：Centroid;based clustering; Cluster Analysis; Swarm