文章摘要
引用本文:
基于邻域熵与蚁群优化的基因选择算法
Gene selection algorithm based on neighborhood entropyand ant colony optimization
投稿时间:2017-05-15  修订日期:2017-06-15
DOI:
中文关键词: 基因选择  蚁群优化  邻域熵  邻域粗糙集
英文关键词: gene selection  ant colony optimization  neighborhood entropy  neighborhood rough sets
基金项目:国家自然科学基金资助(61573297),福建省教育厅A类资助(JA15363)
作者单位E-mail
许明 厦门理工学院 计算机与信息工程学院 mxu@xmut.edu.cn 
郑鹭斌 厦门理工学院 计算机与信息工程学院  
谢彦麒 厦门理工学院 计算机与信息工程学院  
陈玉明 厦门理工学院 计算机与信息工程学院  
摘要点击次数: 39
全文下载次数: 
中文摘要:
      针对高维、小样本及不确定性特点的基因表达数据集中有效特征基因子集的选择问题,采用邻域熵度量与蚁群优化原理,提出一种基因子集选取方法。首先,引入邻域粗糙集模型对连续型的基因表达数据进行邻域粒化,定义邻域熵度量基因表达数据的不确定性,证明了邻域熵的单调性原理,并采用邻域熵剔除冗余基因构成预选择基因子集;然后,定义基于邻域熵的特征基因重要度作为启发式信息,发挥蚁群优化算法具有分布式、正反馈及全局寻优特点的优势,采用蚁群优化算法从预选择基因子集中搜索出最小特征基因子集;最后,将该算法获取的最小特征基因子集进行分类器构建,在2个经典基因表达数据集上的分类实验表明:建立在该最小特征基因子集上的分类器具有良好的分类性能。
英文摘要:
      To deal with the challenging problem of selecting the feature gene subset in a gene expression dataset with high dimension, small sample and uncertainty characteristics, a novel gene selection algorithm is proposed in this paper based on the neighborhood entropy and ant colony optimization (ACO). First of all, we introduce the neighborhood rough set model for grain on the continuous expression gene. The neighborhood entropy is defined for measuring the uncertainty of gene expression data. The monotonic principle of neighborhood entropy is proved, and the use of neighborhood entropy for removing the redundant genes constitutes a pre-selected subset. Furthermore, the neighborhood entropy based gene importance is defined as the heuristic information in the proposed ACO algorithm, which has the advantages of distributed, positive feedback and global optimization. The proposed algorithm has a good ability for finding the minimum critical gene subset from the pre-selected set. Finally, the classifier is constructed by the selected genes, and the experiments are tested on two gene expression datasets. The experimental results show that the classifier constructed on the selected genes has a good classification performance.
View Fulltext   查看/发表评论  下载PDF阅读器
关闭