一种基于动态近邻选择模型的Chameleon算法  

Chameleon algorithm based on dynamic nearest neighbors selection model

作　　者：赵学锋[1] 杨海斌[1] 王秀花[1] 

机构地区：[1]西北师范大学数学与信息科学学院,甘肃兰州730070

出　　处：《西北师范大学学报（自然科学版）》2010年第6期42-45,共4页Journal of Northwest Normal University(Natural Science)

基　　金：甘肃省科技攻关项目(2GS035-A052-011)

摘　　要：在分析Chameleon聚类算法的基础上,提出了一种基于动态近邻选择模型的Chameleon算法(DNMC).新的算法考虑了回溯机制,有利于合并之后的分解.在标准数据集Wine和Iris上的实验表明,DNMC算法的fa指标优于M-Chameleon算法.通过计算各个属性的差异度,显示出一些属性的存在对于聚类结果影响很小,删除这些属性列可以降低时间复杂度.After the analysis for the performance of Chameleon algorithms,a new algorithm named DNMC is presented,which considers the backtracking mechanism making CNMC benefit to the decomposition after the merger.Experimental results on databases Wine and Iris demonstrate that DNNC outperforms M-Chameleon based on the evaluation metrics.Following the calculation of disparity of each attribute,it is found that some attributes have little effect on the results of clustering.Therefore,the complexity of the time can be improved if those attributes are neglected.

关 键 词：层次聚类 CHAMELEON算法 结构等价相似度 模块度 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]