混合不完备数据的新型双邻域粗糙集分类方法  

A New Double-Neighborhood Rough Set Classification Method in Mixed Incomplete Data

作　　者：黄恒秋[1] 陈素霞 翁世洲[3] Huang Hengqiu;Chen Suxia;Weng Shizhou(Department of Mathematics,Physics and Electronic Information Engineering,Guangxi Minzu Normal University,Chongzuo 532200;Department of Computer Science and Art Design,Henan Light Industry Vocational College,Zhengzhou 450052;Department of Economic management,Guangxi Minzu Normal University,Chongzuo 532200)

机构地区：[1]广西民族师范学院数理与电子信息工程学院,崇左532200 [2]河南轻工职业学院计算机与艺术设计系,郑州450052 [3]广西民族师范学院经济管理学院,崇左532200

出　　处：《现代计算机》2022年第22期31-36,共6页Modern Computer

基　　金：广西高校中青年教师科研基础能力提升项目(2020KY20012):混合型不完备数据的邻域粗糙集分类方法;广西高校中青年教师科研基础能力提升项目(2022KY0764):概率数及其在不确定决策理论中的应用研究;广西民族师范学院校级科研项目(2020YB007):模糊区间粗糙数信息系统下的多属性决策方法及应用研究。

摘　　要：针对混合不完备数据集,提出了一种新型双邻域粗糙集分类方法。首先,定义一个无参数的邻域联系度距离,并建立基于无参数邻域联系度距离的双邻域粗糙集模型;其次,基于所构建的模型,给出基于覆盖约简的双邻域粗糙集规则约简方法,获得约简后的上近似规则集和下近似规则集;再次,基于约简后的上、下近似规则集,给出最近邻分类方法;最后,取7个UCI公共测试集做实验分析,通过与混合距离HEOM、带参数邻域联系度距离的双邻域粗糙集分类方法对比,结果表明提出的分类方法仍然取得了优异的分类效果,其突出的优势是不再需要通过大量实验来确定其参数值。In order to process the mixed incomplete data sets,a new classification method based on the double-neighborhood rough set model is proposed.Firstly,a no parameters neighborhood connection degree distance is defined,and the double neighborhood rough set model based on the defined distance is constructed.Secondly,based on the established model,a double neighborhood rough set rule reduction method based on covering reduction is proposed,and the reduced upper and lower approximate rule sets are obtained.Thirdly,based on the lower and upper approximation rule sets after reduction,the nearest neighbor classification method is given.Finally,several UCI datasets were used for empirical analysis,and the results show that the proposed classification method still achieves a good classification effect by comparing with the double-neighborhood rough set classification method with parameter neighborhood relation distance and Mixing distance HEOM.The prominent advantage of the proposed classification method is that it no longer needs a large number of experiments to determine its parameter values.

关 键 词：混合不完备数据集 双邻域粗糙集 邻域联系度距离 分类 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]