多尺度邻域决策信息系统的特征子集选择  

Feature Subset Selection for Multi-scale Neighborhood Decision Information System

作　　者：张庐婧 林国平 林艺东[1] 寇毅 ZHANG Lujing;LIN Guoping;LIN Yidong;KOU Yi(School of Mathematics and Statistics,Minnan Normal University,Zhangzhou 363000;Fujian Key Laboratory of Granular Computing and Applications,Minnan Normal University,Zhangzhou 363000)

机构地区：[1]闽南师范大学数学与统计学院,漳州363000 [2]闽南师范大学福建省粒计算及其应用重点实验室,漳州363000

出　　处：《模式识别与人工智能》2023年第1期49-59,共11页Pattern Recognition and Artificial Intelligence

基　　金：国家自然科学基金项目(No.11871259,12101289,12201284);福建省自然科学基金项目(No.2021J01983,2021J01979)资助。

摘　　要：多尺度决策信息系统的特征子集选择是处理多尺度分类问题的一种有效的数据预处理方法.在实际应用中,数据类型往往多样混合,现有的多尺度模型无法有效处理这类数据.针对该问题,文中面向多源异构多尺度数据,提出多尺度邻域半径的形式化定义,构造多尺度邻域信息粒并讨论其相关性质.在此基础上,探讨特征的重要度,提出可同步进行最优尺度选择和特征选择的特征子集选择算法.改进原有的Wu-Leung模型,在一定程度上扩展其在实际问题上应用的范围.最后,在UCI数据集上验证模型和算法的可行性和有效性.Feature subset selection for multi-scale decision information system is an effective data preprocessing method for multi-scale classification problems.However,data types are often diverse and mixed in real application.The existing multi-scale models cannot handle these data effectively.To solve this problem,a formal definition of multi-scale neighborhood radius for multi-source heterogeneous multi-scale data is proposed in this paper.Multi-scale neighborhood information granule is constructed and its related properties are studied.Attribute significance is discussed,and a feature subset selection algorithm is proposed.Optimal scale selection and feature selection are conducted synchronously.By improving the Wu-Leung model,the scope of its application in practical problems is expanded to some extent.Finally,the feasibility and effectiveness of the proposed model and algorithm are verified on UCI datasets.

关 键 词：粒计算 邻域决策系统 邻域半径 多尺度邻域信息粒 特征子集选择 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]