可区分度与全粒度属性约简  

Distinguishability and Attribute Reduction for Entire-Granulation Rough Sets

作　　者：姚坤 邓大勇 吴越[1] YAO Kun;DENG Dayong;WU Yue(College of Mathematics and Computer Science,Zhejiang Normal University,Jinhua 321004;Xingzhi College,Zhejiang Normal University,Jinhua 321004)

机构地区：[1]浙江师范大学数学与计算机科学学院,金华321004 [2]浙江师范大学行知学院,金华321004

出　　处：《模式识别与人工智能》2019年第8期699-708,共10页Pattern Recognition and Artificial Intelligence

基　　金：浙江师范大学网络空间安全浙江省一流学科资助~~

摘　　要：全粒度粗糙集时空复杂度较高,难于计算属性约简.针对此问题,文中利用等价类定义信息系统中的可区分度,并研究其性质,证明基于可区分度的属性约简等价于绝对约简.定义决策系统中的正区域可区分度,并探究其性质,证明基于正区域可区分度约简是全粒度Pawlak约简的超集,但绝大部分情况下等于全粒度Pawlak约简,可作为全粒度Pawlak约简的近似.理论分析和实验表明,相比其它属性约简算法,基于正区域可区分度约简在计算复杂度和分类准确率等方面具有较大优势.It is difficult to calculate attribute reduct due to high time and space complexity of entire-granulation rough sets.To solve this problem,distinguishability in information systems is defined by equivalent class,and its properties are studied.It is proved that the attribute reduct based on distinguishability is equivalent to absolute reduct.The positive region distinguishability in decision systems is defined and its properties are discussed.It is also proved that positive region distinguishability reduct is a superset of entire-granulation Pawlak reduct,but in most cases it is equal to entire-granulation Pawlak reduct and it can be regarded as an approximation of entire-granulation Pawlak reduct.Theoretical analysis and experiments show that compared with other attribute reduction algorithms,positive region distinguishability reduct has great advantages in computational complexity and classification accuracy.

关 键 词：全粒度粗糙集 可区分度 属性约简 正区域可区分度 全粒度Pawlak约简 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]