摘要
属性约简是粗糙集理论研究的一个基本问题,它是一种有效的数据约简方法。然而,目前很多的属性约简算法在面对高维数据集时仍然不够高效。文中利用图论的相关理论和方法,对基于区分矩阵的粗糙集属性约简方法给出了直观和等价的刻画。在此基础上提出了基于图论的粗糙集属性约简方法。实验结果表明,新的属性约简算法在面对较大规模的数据集,尤其是高维的数据集时,不仅能有效地降低数据的维数,同时运行速度快且能保持较高的分类精度。
Attribute reduction is a basic problem in Rough set theory,which is regarded as an effective data reduction method. However,many attribute reduction algorithms are not efficient enough to handle the high-dimensional data sets. In this paper,the attribute reduction method with Rough sets based on the discernibility matrix is described intuitively and equivalently by using the theory and method of graph theory. Then,some graph-based approaches for the attribute reduction in Rough sets are proposed. The experimental results show that the new attribute reduction algorithms can not only effectively reduce the dimension of data,but also run fast and maintain high classification accuracy when dealing with large-scale data sets,especially high-dimensional data sets.
作者
米据生
陈锦坤
MI Jusheng;CHEN Jinkun(College of Mathematics and Information Science,Hebei Normal University,Shijiazhuang 050024,China;Hebei Key Laboratory of Computational Mathematics and Applications,Shijiazhuang 050024,China;School of Mathematics and Statistics,Minnan Normal University,Zhangzhou 363000,China)
出处
《西北大学学报（自然科学版）》
CAS
CSCD
北大核心
2019年第4期508-516,共9页
Journal of Northwest University（Natural Science Edition）
基金
国家自然科学基金资助项目(61573127)
河北省自然科学基金资助项目(A2018205103,F2018205196)
关键词
粗糙集
属性约简
图论
顶点覆盖
Rough set
attribute reduction
graph theory
vertex cover
