基于基因表达式编程的多目标自动聚类算法  

MULTI-OBJECTIVE AUTOMATIC CLUSTERING ALGORITHM BASED ON GENE EXPRESSION PROGRAMMING

作　　者：徐丽丽 许春秀 张静 齐峰 Xu Lili;Xu Chunxiu;Zhang Jing;Qi Feng(Department of Information Engineering,Shandong Labor Vocational and Technical College,Jinan 250022,Shandong,China;Business College,Shandong Normal University,Jinan 250014,Shandong,China)

机构地区：[1]山东劳动职业技术学院信息工程系,山东济南250022 [2]山东师范大学商学院,山东济南250014

出　　处：《计算机应用与软件》2022年第3期247-253,共7页Computer Applications and Software

基　　金：国家自然科学基金项目(61502283);中国职协研究课题(2019069)。

摘　　要：聚类是将物理或抽象对象的集合分成由类似的对象组成的多个类(簇)的过程。同一个簇中的对象彼此相似,而不同簇中的对象差异较大。以基因表达式编程算法为基础,结合新设计的广义聚类代数算子和目标优化函数,提出一种基于基因表达式编程的多目标自动聚类算法(MAGEP-Cluster)。该算法不仅可以自动确定最优聚类的数目,还可以同时基于簇内数据紧凑性和簇间数据连通性两个指标实现数据的有效划分。在三个人工数据集和五个UCI数据集上的实验结果表明,与GEP-Cluster、MOCK和VAMOSA等算法相比,MAGEP-Cluster具备更好的聚类性能。Clustering is the process of dividing a collection of physical or abstract objects into clusters of similar objects.Objects in the same cluster are similar to each other,while objects in different clusters are quite different.On the basis of gene expression programming algorithm,this paper combines the newly designed generalized clustering algebra operator and objective optimization function and proposes a multi-objective automatic clustering algorithm based on gene expression programming(MAGEP-Cluster).It automatically determined the optimal number of clusters,and reasonably divided all data sets according to the compactness of data in clusters and the connectivity of data between clusters.Experimental results on three artificial datasets and five UCI datasets show that,MAGEP-cluster has better clustering performance than GEP-cluster,MOCK and VAMOSA.

关 键 词：自动聚类 多目标 基因表达式编程 簇间连通性 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]