语义减法聚类研究  

A semantic driven subtractive clustering method

作　　者：马慧[1] 赵捧未[1] 王婷婷[2] 

机构地区：[1]西安电子科技大学经济与管理学院,陕西西安710126 [2]鲁东大学信息与电气工程学院,山东烟台264000

出　　处：《计算机工程与科学》2016年第9期1924-1929,共6页Computer Engineering & Science

摘　　要：针对传统减法聚类算法需要人工输入参数τ1和τ2的不足,对算法进行改进。引入AFS理论,通过隶属度矩阵自动确定密度半径τ1、半自动确定权重参数τ2,提出了改进的语义减法聚类算法SDSCM,并在Iris和Wine数据集上将其与FCM、KMEANS算法进行比较实验。实验结果表明,SDSCM在评价指标语义强度期望上高于FCM、KMEANS 1%～5%。SDSCM的SPT指标低于FCM、KMEANS,算法的类间分离度有待提高。SDSCM较好地解决了传统减法聚类人工输入参数τ1和τ2带来的弊端,并给出了更贴近用户给定语义的聚类。Aiming at the unnecessary need of manual input of parametersrl andr2, we propose a se mentic driven subtractive clustering mehtod （SDSCM） to improve the traditional subtractive clustering algorithms by introducing the axiomatic fuzzy sets （AFS） thoery. The density radius rl is automatically determined and weight v2 is semi-automatically determined based on the membership matrix. We eom pare the SDSCM with the FCM and the KMEANS on the Iris and Wine data sets. Experimental results show that the SDSCM is 1 ~//00 to 5 % higher than the FCM and the KMEANS in terms of evaluation index （semantic strength expectation）, while the SPT is lower than the other two methods, where it still needs to be improved. The SDSCM can effectively solve the disadvantages caused by manual input of pa rameters rl and r2, and find the clusters which are closer to the user semantics

关 键 词：减法聚类 AFS理论 隶属度矩阵 语义强度期望 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]