智能优化算法在聚类分析中的应用  

Intelligent optimization algorithm for clustering analysis

作　　者：刘勇[1,2] 许秋艳[3] 王洪刚[1] 马良[1] 

机构地区：[1]上海理工大学管理学院,上海200093 [2]盐城工学院基础教学部,江苏盐城224051 [3]盐城工学院信息工程学院,江苏盐城224051

出　　处：《计算机工程与应用》2009年第19期123-124,149,共3页Computer Engineering and Applications

基　　金：国家自然科学基金(No.70471065);上海市重点学科建设项目(No.T0502)~~

摘　　要：聚类分析是数据挖掘的重要技术,可根据数据间的相似程度,将数据进行分类,现已广泛应用于工程和技术等领域中。元胞蚁群算法是在将元胞自动机的邻居和规则引入传统蚁群算法的基础上,利用元胞在离散元胞空间的演化规律和蚁群寻优特点的新型优化算法。针对聚类分析的特点,利用元胞蚁群算法进行求解,经实验测试和验证,获得了较好的结果。Clustering analysis is an important technique of data mining.It is a division of data into groups of similar objects, which is widely used in many fields of engineering and technology.Cellular ant algorithm is a new optimization algorithm which introduces the concept of neighborhood and the rules of cellular automata into the basic ant algorithm.Cellular ant algorithm uses both the evolutionary rule of cellular in cellular space and the characteristics of ant colony optimization.Based on some characteristics of clustering analysis,this paper provides cellular ant algorithm for clustering analysis.The result of the experiment demonstrates that the proposed algorithm has better clustering results in performance.

关 键 词：聚类分析 元胞自动机 蚁群算法 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]