《计算机应用研究》|Application Research of Computers

新模糊聚类有效性指标

New fuzzy clustering validity index

免费全文下载 (已被下载 次)  
获取PDF全文
作者 耿嘉艺,钱雪忠,周世兵
机构 江南大学 物联网工程学院,江苏 无锡 214122
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2019)04-010-1001-05
DOI 10.19734/j.issn.1001-3695.2017.10.0991
摘要 模糊聚类是模式识别、机器学习和图像处理等领域的重要研究内容。模糊C-均值聚类算法是最常用的模糊聚类实现算法。该算法需要预先给定聚类数才能对数据集进行聚类。提出了一种新的聚类有效性指标,对聚类结果进行有效性验证。该指标从划分熵、隶属度、几何结构角度,定义了紧凑度、分离度、重叠度三个重要特征测量。在此基础上,提出了一种最佳聚类数确定方法。将新聚类有效性指标与传统有效性指标在六个人工数据集和三个真实数据集进行实验验证。实验结果表明,所提出的指标和方法能够有效地对聚类结果进行评估,适合确定样本的最佳聚类数。
关键词 模糊C-均值聚类; 聚类数; 聚类有效性指标; 模糊聚类
基金项目 国家自然科学基金资助项目(61673193)
中央高校基本科研业务费专项资金资助项目(JUSRP11235,JUSRP51635B)
本文URL http://www.arocmag.com/article/01-2019-04-010.html
英文标题 New fuzzy clustering validity index
作者英文名 Geng Jiayi, Qian Xuezhong, Zhou Shibing
机构英文名 School of Internet of Things Engineering,Jiangnan University,Wuxi Jiangsu 214122,China
英文摘要 Fuzzy clustering is an important research content in the fields of pattern recognition, machine learning and image processing. Fuzzy C-means clustering algorithm is the most commonly used fuzzy clustering algorithm. The algorithm needs to preset the number of clusters in order to cluster the data set. This paper proposed a new clustering validity index to validate the clustering results. This index defined the three important features of compactness, resolution and overlap degree from the perspective of partition entropy, membership degree and geometric structure. On this basis, this paper proposed a method of determining the optimal clustering number. It validated the new clustering validity index and the traditional effectiveness index in six artificial data sets and three real data sets. The experimental results show that the proposed indexes and methods can effectively evaluate the clustering results and are suitable for determining the optimal clustering number of the samples.
英文关键词 fuzzy C-means clustering; number of clusters; clustering validity index; fuzzy clustering
参考文献 查看稿件参考文献
 
收稿日期 2017/10/31
修回日期 2017/12/18
页码 1001-1005
中图分类号 TP318
文献标志码 A