基于判别结构向量互补的集成特征选择方法  

Ensemble feature selection method based on discriminant structure vector complementarity

作　　者：任晓莹 陈浩 刘玘晗 李紫璇 王淑琴[1] REN Xiaoying;CHEN Hao;LIU Qihan;LI Zixuan;WANG Shuqin(College of Computer and Information Engineering,Tianjin Normal University,Tianjin 300387,China)

机构地区：[1]天津师范大学计算机与信息工程学院,天津300387

出　　处：《天津师范大学学报（自然科学版）》2023年第4期57-63,共7页Journal of Tianjin Normal University：Natural Science Edition

基　　金：国家自然科学基金资助项目(61070089);天津市应用基础与前沿技术研究计划重点资助项目(15JCYBJC4600);天津市科技计划资助项目(19JCZDJC35100);天津市科技计划项目技术创新引导专项基金资助项目(22YDTPJC00610).

摘　　要：提出一种基于判别结构向量互补的集成特征选择方法,分别使用互信息、ReliefF和Fisher判别比度量特征对子问题的分类能力,并根据判别结构向量互补分别确定特征子集,再将其合并为最优特征子集.使用4个UCI数据集和2个基因表达数据集进行实验,将本文算法与基于排序的特征选择算法、特征子集选择算法和其基特征选择算法进行比较,结果表明,本文算法的整体性能优于其他算法.An ensemble feature selection algorithm based on discriminant structure vector complementarity is proposed.Mutual information,ReliefF and Fisher′s discriminant ratio are used to measure the ability of features to classify subproblems,and fea-ture subsets are determined according to discriminant structure vector complementarity.Finally,the selected subsets are merged into the optimal feature subset.Four UCI datasets and two gene expression datasets are used for experiments,and the proposed algorithm is compared with the sorting based feature selection algorithms,feature subset selection algorithms and the base feature selectors.The results show that the overall performance of the proposed algorithm is better than other algorithms.

关 键 词：集成特征选择 判别结构向量 互信息 Fisher判别比 RELIEFF 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] TP311.13[自动化与计算机技术—控制科学与工程]