粗糙集的近似约简及其算法  

A Rough Set of Approximate Attribute Reduction and Its Algorithm

作　　者：申锦标[1] 吕跃进[1] 

机构地区：[1]广西大学数学与信息科学学院,广西南宁530004

出　　处：《计算机技术与发展》2009年第12期17-20,共4页Computer Technology and Development

基　　金：广西自然科学基金(桂科自0991027);广西教育厅面上项目(200707MS061)

摘　　要：针对经典粗糙集中属性约简的不足,进一步拓展粗糙集属性约简的应用。提出了一种粗糙集属性近似约简的概念和一种新的粗糙集属性重要性的定义并给出和证明了属性近似约简的性质,理论证明了近似属性约简是传统属性约简的一种推广。在保持知识库分类能力基本不变的条件下,利用所给属性重要性作为启发信息给出了粗糙集属性近似约简的算法。通过一个具体的例子,说明了近似属性约简在信息系统中处理模糊和不确定性知识的可行性和有效性。In view of the deficiencies of attribute reduction in classic rough set and to further expand the application of rough set attribute reduction, Render an approximate attribute reduction of rough set and a new definition of the importance of attribute. Theory proves that approximate attribute reduction is an extension of the traditional attribute reduction. With the knowledge elassification ability remaining basically unchanged,put forward a rough set of approximate attribute reduction and its methods. Finally, a concrete example demonstrates the feasibility and effectiveness of approximate attribute reduction dealing with ambiguity and uncertainty of knowledge in information systems.

关 键 词：粗糙集 近似属性约简 约简算法 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]