《计算机应用研究》|Application Research of Computers

基于邻域粗糙集和概率神经网络集成的基因表达谱分类方法

Gene expression profiles classification method based on neighborhood rough set and probabilistic neural networks ensemble

免费全文下载 (已被下载 次)  
获取PDF全文
作者 明利特,蒋芸,王勇,王明芳
机构 1.西北师范大学 数学与信息科学学院,兰州 730070;2.西北工业大学 计算机学院,西安 710072
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2011)12-4440-05
DOI 10.3969/j.issn.1001-3695.2011.12.010
摘要 从癌症基因表达谱分析入手,针对基因表达谱维数高、样本少的特点,提出一种用于癌症分类的基于邻域粗糙集和概率神经网络集成的分类方法。首先利用Relief算法对基因进行排序,然后利用邻域粗糙集选取分类特征基因,最后结合概率神经网络集成分类模型进行癌症分类。实验结果表明,该方法可以快速有效地选取癌症特征基因,能获得更好的分类效果。
关键词 分类;基因表达谱;概率神经网络集成;邻域粗糙集
基金项目 国家自然科学基金资助项目(61163036,60873196);甘肃省自然科学基金资助项目(1010RJZA022);西北师范大学2010年第三期知识与创新工程科研骨干资助项目(nwnu-kjcxgc-03-67)
本文URL http://www.arocmag.com/article/1001-3695(2011)12-4440-05.html
英文标题 Gene expression profiles classification method based on neighborhood rough set and probabilistic neural networks ensemble
作者英文名 MING Li-te, JIANG Yun, WANG Yong, WANG Ming-fang
机构英文名 1. College of Mathematics & Information Science, Northwest Normal University, Lanzhou 730070, China; 2. College of Computer Science, Northwestern Polytechnical University, Xi'an 710072, China
英文摘要 Begined with the cancer gene expression profiles analysis and aiming at the characteristics of high dimension and small samples, this paper proposed a classification method for cancer classification which was based on neighborhood rough set and probabilistic neural networks ensemble. Firstly, sorted genes by using Relief algorithm, then selected classification informative genes by using the neighborhood rough set, lastly, classified cancers with probabilistic neural networks ensemble classification model.The experiment results show that the method can promptly and effectively select cancer informative genes, and obtain better classification results.
英文关键词 classification; gene expression profile; probabilistic neural networks ensemble; neighborhood rough set
参考文献 查看稿件参考文献
 
收稿日期
修回日期
页码 4440-4444
中图分类号
文献标志码 A