|
|||||
|
|
| 基于连通分量的分类变量聚类算法 | |
| 引用本文： | 周红芳,周扬,张晓鹏,谈姝辰.基于连通分量的分类变量聚类算法[J].控制与决策,2015,30(1):39-45. |
| 作者姓名： | 周红芳 周扬 张晓鹏 谈姝辰 |
| 作者单位： | 1. 西安理工大学计算机科学与工程学院，西安710048； 2. 陕西应用物理化学研究所，西安710061. |
| 基金项目： | 国家自然科学基金项目(61402363,61272284);陕西省工业攻关项目(2014K05-49);陕西省自然科学基础研究计划项目(2014JQ8361);西安市碑林区科技计划项目(GX1405);西安市科学计划项目(CXY1339(5));校特色研究计划项目(116-211302) |
| 摘 要： | 针对分类变量相似度定义存在的不足, 提出一种新的相似度定义. 利用新的相似度定义, 将数据集抽象为无向图, 将聚类过程转化为求无向图连通分量的过程, 进而提出一种基于连通分量的分类变量聚类算法. 为了定量地分析该算法的聚类效果, 针对类别归属已知的数据集, 提出一种新的聚类结果评价指标. 实验结果表明, 所提出的算法具有较高的聚类精度和聚类效率. |
| 关 键 词： | 聚类 分类变量 相似度 连通分量 聚类精度 |
| 收稿时间： | 2013-10-29 |
| 修稿时间： | 2014/3/20 0:00:00 |
A clustering algorithm for categorical variables based on connected components |
|
| ZHOU Hong-fang ZHOU Yang ZHANG Xiao-peng TAN Shu-chen.A clustering algorithm for categorical variables based on connected components[J].Control and Decision,2015,30(1):39-45. | |
| Authors: | ZHOU Hong-fang ZHOU Yang ZHANG Xiao-peng TAN Shu-chen |
| Affiliation: | 1. School of Computer Science and Engineering，Xi’an University of Technology，Xi’an 710048，China； 2. Shanxi Applied Physics and Chemistry Research Institute，Xi’an 710061，China． |
| Abstract: | For the insufficient similarity concepts for categorical variables, a new more reasonable concept is proposed. Firstly, a data set is organized into an undirected graph by the new definition. The clustering process is converted into the problem of determining connected components in the undirected graph. Then a novel clustering algorithm for categorical variables based on connected components is proposed. In order to analyze the clustering results quantitatively, a new index is proposed for the known labels. Finally, the experimental results show that the proposed algorithm has a higher clustering precision and faster execution speed compared with several existing ones. |
| Keywords: | clustering categorical variables similarity connected components clustering precision |
| 本文献已被 CNKI 万方数据 等数据库收录！ | |
| 点击此处可从《控制与决策》浏览原始摘要信息 | |
| 点击此处可从《控制与决策》下载全文 | |