首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于支持向量机的结肠癌信息基因提取
引用本文:李烨,王永丽,贺国平.基于支持向量机的结肠癌信息基因提取[J].山东科技大学学报(自然科学版),2012(3):84-89.
作者姓名:李烨  王永丽  贺国平
作者单位:山东科技大学 信息科学与工程学院,山东 青岛 266590
基金项目:国家自然科学基金项目(10971122);山东省优秀中青年科学家科研奖励基金项目(2010BSE06047);高等学校博士学科点专项科研基金项目(20093718110005);山东省科技攻关计划项目(2009GG10001012);山东省自然科学基金项目(Y2008A01)
摘    要:基于结肠癌基因表达谱数据集,提出了一种信息基因提取的新方法。该方法结合了支持向量机(SVM)、Bhattacharyya距离、递归特征消除(RFE)和快速基于相关性过滤器(FCBF)方法。首先,利用Bhattacharyya距离与SVM-RFE方法结合去除无关基因,然后运用FCBF方法得到信息基因,最后以支持向量机作为分类器对结肠癌样本进行分类识别。实验结果表明,同现有的方法相比,该方法在提取基因数量和准确率上都有明显的优势。

关 键 词:结肠癌  支持向量机  信息基因  Bhattacharyya距离  递归特征消除  快速基于相关性过滤器

The Extraction for Informative Genes of Colon Cancer Based on Support Vector Machine
LI Ye,WANG Yongli,HE Guoping.The Extraction for Informative Genes of Colon Cancer Based on Support Vector Machine[J].Journal of Shandong Univ of Sci and Technol: Nat Sci,2012(3):84-89.
Authors:LI Ye  WANG Yongli  HE Guoping
Institution:(College of Information Sciences and Engineering,Shandong University of Science and Technology,Qingdao,Shandong 266590,China)
Abstract:A new informative gene extracting method was developed based on the dataset of expressible spectrum in colon cancer genes and the method combined with the support vector machine,Bhattacharyya distance,recursive feature elimination(RFE) and fast correlation-based filter(FCBF).Firstly,a combination of Bhattacharyya distance and SVM-RFE was applied to remove the irrelevant genes.Secondly,FCBF was employed to generate the informative genes.Finally,SVM was used to classify the colon datasets.The experimental results demonstrated that compared to existing methods,the classification accuracy was improved and the number of informative genes was decreased.
Keywords:colon cancer  support vector machine  informative genes  Bhattacharyya distance  recursive feature elimination  fast correlation-based filter
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号