一种基于云模型改进蚁群聚类算法的研究  

The research for an improved ant colony clustering algorithm based on cloud model

作　　者：谢彦峰[1] 米伟[1] 

机构地区：[1]兰州交通大学电子与信息工程学院,甘肃兰州730070

出　　处：《自动化与仪器仪表》2010年第6期4-6,共3页Automation & Instrumentation

摘　　要：基于云模型在非规范知识的定性、定量表示及其相互转换过程中的优良特征结合LF蚁群聚类算法的基本思想,提出了一种基于云模型的蚁群聚类算法。从模仿蚂蚁堆积的尸体的基本模型出发,引入了相似因子和相异因子的概念,通过在邻域内进行快速云模型动态概念软划分产生最大的内聚核,进而重新定义接受分数的计算公式,能够使聚类收敛速度更快、聚类结果更纯,更符合人的常理判断。实验结果表明新算法对聚类质量有很好的效果。Based on cloud model in the non-standardized qualitative knowledge,quantified and their mutual conversion process＇s fine features,LF with the basic idea of ant colony clustering algorithm based on cloud model proposed Ant Colony Clustering Algorithm.Piled the bodies of ants from the imitation of the basic model,introduce similar factor and dissimilarity factor concept,through the neighborhood of the concept of fast dynamic cloud model can produce the largest soft-division cohesive core,thus redefining the accepted formula for calculating the scores,enables faster convergence clustering,clustering result is more pure,more in line with people＇s common sense.The experimental results show that the new algorithm has very good results clustering quality.

关 键 词：云模型 概念软划分 蚁群算法 相似因子 相异因子 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]