期刊
NEUROCOMPUTING
卷 72, 期 4-6, 页码 991-999出版社
ELSEVIER
DOI: 10.1016/j.neucom.2008.04.005
关键词
Microarray data; Gene expression; Gene selection; Mutual information; Parzen window density estimation
Gene selection, a significant preprocessing of the discriminant analysis of microarray data, is to select the most informative genes from the whole gene set. In this paper, an efficient mutual information-based gene selection algorithm (MIGS) is proposed, in which genes are sequentially forward selected according to an approximate measure of the mutual information between the class and the selected genes. In order to improve the efficiency of the MIGS, an effective pruning strategy is introduced in the selection procedure as well as the employment of Parzen window density estimation technique. Extensive experiments are conducted on three public gene expression datasets and the experimental results confirm the efficiency and effectiveness of the algorithm, Though the computational cost of MIGS-Pruning increases with the number of selected genes, it still has good performance applied in the microarray problems. (C) 2008 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