计算机与数字工程2025，Vol.53Issue(1)：15-20,6.DOI:10.3969/j.issn.1672-9722.2025.01.004
监督邻域粗糙集下基于标准差属性重要度的启发式算法
Heuristic Algorithm Based on Standard Deviation Attribute Significance in Supervised Neighborhood Rough Set
摘要
Abstract
As a significant model in rough set theory,the supervised neighborhood rough set has been paid much attention be-cause of its better discriminating performance.However,when deriving reduct in supervised neighborhood rough set,most research-es will cause massive time consumption because of repeatedly computing the significance of candidate attributes.To fill such a gap,a heuristic algorithm based on the standard deviation attribute significance is proposed.The attribute significance is sorted according to the degree of the dispersion of the samples,so as to reduce the traversal scale of attributes in the process of deriving reduct.Exper-imental results over 12 UCI data sets show that the proposed algorithm can effectively decrease the elapsed time of deriving reduct and improve the classification performance simultaneously over the other three algorithms.关键词
加速策略/属性约简/属性重要度/标准差/监督邻域粗糙集Key words
acceleration strategy/attribute reduction/attribute significance/standard deviation/supervised neighborhood rough set分类
信息技术与安全科学引用本文复制引用
刘旭东..监督邻域粗糙集下基于标准差属性重要度的启发式算法[J].计算机与数字工程,2025,53(1):15-20,6.基金项目
国家自然科学基金项目(编号:61906078,62006099,62076111,62006128) （编号:61906078,62006099,62076111,62006128）
江苏省高等学校自然科学基金项目(编号:20KJB520010) （编号:20KJB520010）
浙江省海洋大学数据挖掘与以应用重点实验室开放课题(编号:OBDMA202104)资助. （编号:OBDMA202104）
