广义相似关系下的不完备信息系统粗糙集模型  

Rough set model based on general similarity relation in incomplete information systems

作　　者：谭旭[1,2] 陈英武[2] 王桢珍[2] 

机构地区：[1]深圳信息职业技术学院计算机应用系,广东深圳518029 [2]国防科学技术大学信息系统与管理学院,湖南长沙410073

出　　处：《中南大学学报（自然科学版）》2009年第5期1360-1366,共7页Journal of Central South University:Science and Technology

基　　金：国家自然科学基金资助项目(70272002)

摘　　要：为了更好地从含有杂合数据和不完备数据的信息系统中提取合理的规则知识,构建基于广义相似关系的不完备信息系统粗糙集模型。其步骤为:针对决策信息系统中存在杂合数据的情况,并对决策信息系统中所存在的不完备信息进行细致区分,给出广义相似关系的定义;通过提出上、下广义相似划分的上、下近似的概念,给出2种划分意义下的属性约简和规则知识提取策略;最后,在理论上对该扩展粗糙集模型的正确性进行相关证明,并用实际算例进一步验证该模型的有效性和优越性。In order to extract reasonable rule-based knowledge from information systems with hybrid data and incomplete data,a new rough set model based on general similarity relation in incomplete information systems was proposed.The procedures were as follows：Firstly,general similarity relations were defined for the situation of hybrid data and different kinds of incomplete data in information systems.Secondly,two kinds of attribute reduction methods and rule-based knowledge extraction methods were investigated,which were built upon the concepts of upper and lower approximations with upper and lower general similarity partitions.Lastly,the extended rough set model was proved theoretically,and a numerical example reveals the validity and advantage of the proposed model.

关 键 词：广义相似关系 不完备信息系统 上近似 下近似 粗糙集 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]