基于信息量的不完备信息系统属性约简  

Attribute Reduction Based on Information Quantity under Incomplete Information Systems

作　　者：黄兵 周献中[2] 张蓉蓉 

机构地区：[1]南京审计学院计算机科学与技术系,江苏南京210029 [2]南京大学工程管理学院,江苏南京210093 [3]合肥烟草专卖局,安徽合肥230031

出　　处：《系统工程理论与实践》2005年第4期55-60,共6页Systems Engineering-Theory & Practice

基　　金：江苏省自然科学基金(2004BK137)

摘　　要：　通过引入信息量和条件信息量,对不完备信息系统中属性的重要性进行了定义;针对不完备数据表和不完备决策表提出了一种基于信息量和条件信息量的属性约简启发式算法,该算法的时间复杂度是多项式的.通过实例说明,该算法能得到信息表的约简和决策表的相对约简.Knowledge acquisition based on rough set theory is an important and difficult task under incomplete information systems. Information quantity and conditional information quantity are defined to express indispensable of attributes under incomplete information systems. A heuristic algorithm based on information quantity or conditional information quantity for reduction of attributes is presented, and the complexity of this algorithm is analyzed. Finally, the experimental results show that this algorithm can find the reduct of an incomplete information system.

关 键 词：粗糙集 不完备信息系统 信息量 属性约简 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]