基于阴影集的截集式可能性C-均值聚类截集门限的选取  

Selection of Cutset Threshold for Cutset-type Possibilistic C-means Clustering Based on Shadowed Set

作　　者：雒僖 范九伦 于海燕 梁丹 LUO Xi;FAN Jiu-lun;YU Hai-yan;LIANG Dan(School of Communication and Information Engineering,Xi’an University of Posts and Telecommunications,Xi’an 710121,China;Key Laboratory Electronic Information Application Technology for Scene Investigation,Ministry of Public Security,Xi’an 710121,China;Internation Joint Resesrch Center for Wireless Communication and Information Processing,Xi’an 710121,China)

机构地区：[1]西安邮电大学通信与信息工程学院,西安710121 [2]电子信息勘验应用技术公安部重点实验室,西安710121 [3]陕西省无线通信与信息处理技术国际合作研究中心,西安710121

出　　处：《计算机科学》2019年第8期249-254,共6页Computer Science

基　　金：国家自然科学基金项目(61671377,61571361,61601362);西安邮电大学西邮新兴团队(xyt2016-01)资助

摘　　要：截集式可能性C-均值聚类算法通过引入截集门限,修改典型性值,克服了可能性C-均值聚类算法的最关键问题:一致性聚类。针对算法中截集门限的选取问题,采用阴影集理论,提出了一种新的截集门限的选取方法。该算法利用最优化方法为每一个类确定一个阴影集阈值,并将该阈值作为截集门限;通过分析该选取方法对典型性值和中心偏移量的影响来改进典型性值的修改方式。最后,通过人工数据分析了新的截集门限选取方式对聚类算法性能的影响,利用实际UCI数据分析算法的迭代次数和聚类正确率。实验结果表明,给出的截集门限选取方法能够有效减少迭代次数,提高聚类正确率。By introducing the cutset threshold and modifying the typicality,the cutset-type possibilistic C-means clustering algorithm overcomes the most critical problem(consistent clustering)of the possibilistic C-means clustering algorithm.Aiming at the parameter selection problem in the algorithm,this paper proposed a new method based on the shadowed set.This algorithm uses the optimization method to determine the threshold of the shadowed set for each cluster and takes this threshold as the cutset threshold.The modification method of the typicality is improved by analyzing the influence of the selection method on the typicality and the center deviation.Finally,the influence of the new parameter selection method on the performance of the clustering algorithm is analyzed by artificial dataset.The number of iterations and the clustering accuracy of the algorithm are analyzed through the UCI dataset.Experimental results show that the proposed method can effectively reduce the number of iterations and improve the accuracy of clustering.

关 键 词：可能性C-均值聚类 截集式可能性C-均值聚类 聚类核 截集门限 阴影集 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]