期刊
COMPUTERS IN BIOLOGY AND MEDICINE
卷 64, 期 -, 页码 236-245出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.compbiomed.2015.07.008
关键词
Discriminant neighborhood embedding; Adjacent graph; Gene expression data; Cancer classification; Microarray data
类别
资金
- National Natural Science Foundation of China [61373093]
- Natural Science Foundation of Jiangsu Province of China [BK20140008, BK201222725]
- Natural Science Foundation of the Jiangsu Higher Education Institutions of China [13KJA520001]
- Qing Lan Project
The family of discriminant neighborhood embedding (DNE) methods is typical graph-based methods for dimension reduction, and has been successfully applied to face recognition. This paper proposes a new variant of DNE, called similarity-balanced discriminant neighborhood embedding (SBDNE) and applies it to cancer classification using gene expression data. By introducing a novel similarity function, SBDNE deals with two data points in the same class and the different classes with different ways. The homogeneous and heterogeneous neighbors are selected according to the new similarity function instead of the Euclidean distance. SBDNE constructs two adjacent graphs, or between-class adjacent graph and within-class adjacent graph, using the new similarity function. According to these two adjacent graphs, we can generate the local between-class scatter and the local within-class scatter, respectively. Thus, SBDNE can maximize the between-class scatter and simultaneously minimize the within-class scatter to find the optimal projection matrix. Experimental results on six microarray datasets show that SBDNE is a promising method for cancer classification. (C) 2015 Elsevier Ltd. 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