基于改进的核模糊粗糙集的混合特征基因选择方法
A hybrid feature gene selection algorithm based on improved kernelized fuzzy rough sets
投稿时间:2018-01-02  修订日期:2018-01-02
DOI:
中文关键词: 基因表达谱  特征基因选择  relieff  核模糊粗糙集  差分进化算法
英文关键词: gene expression profile  feature gene selection  reliefF algorithm  kernelized fuzzy rough sets  differential evolution
基金项目:国家自然科学基金资助项目(11502132)、陕西省教育厅科研资助项目(16JK1149)
作者单位E-mail
陈涛 陕西理工大学 数学与计算机科学学院 ct79hz@126.com 
摘要点击次数: 883
全文下载次数: 
中文摘要:
      针对基因表达谱的高维、小样本、高冗余和高噪声等特点,本文提出一种混合特征基因选择方法。首先,采用relieff方法对原始基因进行排序过滤,剔除无效基因和噪声数据,获得初选基因子集;然后,提出基于差分进化算法优化的核模糊粗糙集模型,进行特征基因最终选择。仿真实验结果表明本文算法比Relieff、Kruskalwallis、Gini Index等算法有明显优势。
英文摘要:
      This paper proposes a hybrid feature gene selection algorithm based on an improved kernel fuzzy rough sets aiming at the characteristics of high-dimensions, small samples, high noise and high redundancy of gene expression profiles. Firstly, the top-ranked genes based on relieff algorithm is selected to construct a primary gene subset in order to remove the invalid gene and noise data. And then, an improved kernelized fuzzy rough sets model based on the differential evolution algorithm is proposed to achieve the selection of feature genes. Simulation results show that the proposed algorithm has obvious advantages comparison with relieff, kruskal-wallis and gini index algorithms.
View Fulltext   查看/发表评论  下载PDF阅读器
关闭