文档下载 文档下载导航
设为首页 | 加入收藏
搜索 请输入内容:  
 导航当前位置: 文档下载 > 所有分类 > IT/计算机 > Fuzzy clustering with artificial bee colony algorithm
侵权投诉

Fuzzy clustering with artificial bee colony algorithm

人工蜂群算法应用于模糊聚类。

Scientific Research and Essays Vol. 5(14), pp. 1899-1902, 18 July, 2010 Available online at doc.guandang.net ISSN 1992-2248 ©2010 Academic Journals

Full length Research Paper

Fuzzy clustering with artificial bee colony algorithm

Department of Computer Engineering, Faculty of Engineering, Erciyes University, Kayseri, Turkey.

Accepted 23 June, 2010

Dervis Karaboga and Celal Ozturk*

INTRODUCTION

Clustering is an important tool for a variety of applications in data mining, statistical data analysis, data compression and vector quantization, aims gathering data into clusters (or groups) such that the data in each cluster shares a high degree of similarity while being very dissimilar to data from other clusters (Jain and Dubes, 1998; Sarkar et al., 1997; Han and Kamber, 2001). The goal of clustering is to group data into clusters such that the similarities among data members within the same cluster are maximal while similarities among data members from different clusters are minimal.

The most popular class of clustering algorithms is K-means algorithm, a center based, simple, and fast alg-orithm, aims to partition n objects into k clusters in which each object belongs to the cluster with the nearest mean (MacQueen, 1967). However, in real applications there are no sharp boundaries within the clusters so that data objects might partially belong to multiple cluster. In fuzzy clustering, the data points can belong to more than one cluster and membership degrees between zero and one are used instead of crisp assignments of the data to clusters (Jain et al., 1999). The degree of membership in the fuzzy clusters depends on the closeness of the data object to the cluster centers.

Fuzzy c-means (FCM) which is introduced by Bezdek (1981) is the most popular fuzzy clustering algorithm.

In this work, performance of the Artificial Bee Colony Algorithm which is a recently proposed algorithm, has been tested on fuzzy clustering. We applied the Artificial Bee Colony (ABC) Algorithm fuzzy clustering to classify different data sets; Cancer, Diabetes and Heart from UCI database, a collection of classification benchmark problems. The results indicate that the performance of Artificial Bee Colony Optimization Algorithm is successful in fuzzy clustering.

Key words: ABC Algorithm, classification, fuzzy clustering.

Tel: 352 4374901 # 32581. Fax: 352 4375784.

However, FCM is an effective algorithm; the random selection in center points makes iterative process falling into the local optimal solution easily. To tackle this pro-blem, evolutionary algorithms such as genetic alg-orithm (GA), differential evolution (DE), ant colony optimization (ACO), and particle swarm optimization (PSO) have been successfully applied (Gan et al., 2009; Das et al., 2006; Zhao, 2007; Runkler and Katz, 2006). The motivation of this paper is apply to Artificial Bee

Colony (ABC) algorithm, which is described by Kara-boga based on the foraging behavior of honey bees for numerical optimization problems (Karaboga, 2005), in fuzzy clustering. The performance of ABC algorithm is tested on benchmark classification problems of cancer, diabetes and heart obtained from the UCI data (Frank and Asuncion, 2010). The classification task is done by neural networks and clustering, and ABC algorithm is used for training feed-forward neural networks and find-ing the cluster centers. This work is the first experiment of ABC algorithm on fuzzy clustering. The paper is organ-ized as describing fuzzy clustering and ABC algorithm, and then presenting the results and discussion. Finally, the last section concludes the paper.

FUZZY CLUSTERING

Clustering is the process of recognizing natural groupings or clusters in multidimensional data based on some similarity measures (Jain et al., 1999). Distance me-asurement is generally used for evaluating similarities

第1页

你可能喜欢

热门文档

相关文档

站点地图 | 文档上传 | 侵权投诉 | 手机版
本站所有资源均来自互联网,本站只负责收集和整理,均不承担任何法律责任,如有侵权等其它行为请联系我们.
文档下载 Copyright 2013 doc.guandang.net All Rights Reserved.  -  email