期刊
KNOWLEDGE-BASED SYSTEMS
卷 67, 期 -, 页码 401-411出版社
ELSEVIER
DOI: 10.1016/j.knosys.2014.03.013
关键词
Data mining; Clustering; Categorical data; Gain ratio; Information theory
资金
- Fundamental Research Grant Scheme from Ministry of Higher Education of Malaysia [RDU130115]
- University of Malaya High Impact Research Grant from Ministry of Higher Education of Malaysia [UM.C/625/HIR/MOHE/SC/13/2]
- Universiti Malaysia Pahang [RDU130367, RDU130398]
Categorical data clustering has attracted much attention recently due to the fact that much of the data contained in today's databases is categorical in nature. While many algorithms for clustering categorical data have been proposed, some have low clustering accuracy while others have high computational complexity. This research proposes mean gain ratio (MGR), a new information theory based hierarchical divisive clustering algorithm for categorical data. MGR implements clustering from the attributes viewpoint which includes selecting a clustering attribute using mean gain ratio and selecting an equivalence class on the clustering attribute using entropy of clusters. It can be run with or without specifying the number of clusters while few existing clustering algorithms for categorical data can be run without specifying the number of clusters. Experimental results on nine University of California at Irvine (UCI) benchmark and ten synthetic data sets show that MGR performs better as compared to baseline algorithms in terms of its performance and efficiency of clustering. (C) 2014 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据