An improved cluster labeling method for support vector clustering

被引：215

作者：

Lee, J ^{[1
]}

Lee, D ^{[1
]}

机构：

[1] Pohang Univ Sci & Technol, Dept Ind Engn, Informat Lab, Pohang 790784, Kyungbuk, South Korea

来源：

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | 2005年 / 27卷 / 03期

关键词：

clustering; unsupervised learning method; support vector machines;

D O I：

10.1109/TPAMI.2005.47

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The support vector clustering (SVC) algorithm is a recently emerged unsupervised learning method inspired by support vector machines. One key step involved in the SVC algorithm is the cluster assignment of each data point. A new cluster labeling method for SVC is developed based on some invariant topological properties of a trained kernel radius function. Benchmark results show that the proposed method outperforms previously reported labeling techniques.

引用

页码：461 / 464

页数：4