优势信息系统的属性约简算法  

Algorithm on Attribute Reduction in Dominance Information System Based on Dominance Relation

作　　者：李学文[1] 王小刚[1] 

机构地区：[1]北方民族大学,宁夏银川750021

出　　处：《计算机技术与发展》2009年第8期107-109,共3页Computer Technology and Development

基　　金：教育部科学技术研究重点项目(206159);宁夏自然科学基金资助项目(NZ0516);北方民族大学校级科研项目(2006Y048)

摘　　要：粗糙集理论是一种新的软计算方法,已成为知识发现和属性约简算法领域的一个研究热点。但经典的粗糙集理论是建立在等价关系基础之上的。从粗糙集理论出发,在优势关系之上给出了优势信息系统中信息量的概念,建立了知识粒度与信息量之间的关系。在此基础上,提出了一种基于信息量的属性约简启发式算法,得到了该算法的时间复杂性为O(|A|3×|U|2)。通过实例分析表明该算法是有效的,为进一步研究约简算法提供了一种可行的方法。Rough set theory is a relatively new soft computing technique and has become a topic of general interest in the field of knowledge discovery and algorithm of attribute reduction. The classical rough set theory is based on relation of equivalence. In this paper, the concept of information quantity is given in dominance information system from rough set theory. Relationships between knowledge and information quantity have been built. Accordingly, a new heuristic reduction algorithm based on information quantity, of which time complexity is O（｜A｜^3×｜U｜^2） , is proposed. It proves that the algorithm is effective through example analysis, moreover, puts forward new methods for further researching of attribute reduction.

关 键 词：粗糙集 优势关系 信息量 属性约简 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]