计算机工程与应用 ›› 2014, Vol. 50 ›› Issue (19): 128-131.

• 数据库、数据挖掘、机器学习 • 上一篇    下一篇

合成随机信息系统的属性约简方法

赵  兹1,马建敏2   

  1. 1.陕西国防工业职业技术学院 基础课部,西安 710300
    2.长安大学 理学院,西安 710064
  • 出版日期:2014-10-01 发布日期:2014-09-29

Attribute reduction of combined random information systems

ZHAO Zi1, MA Jianmin2   

  1. 1.Department of Basic Courses, Shaanxi Institute of Technology, Xi’an 710300, China
    2.College of Science, Chang’an University, Xi’an 710064, China
  • Online:2014-10-01 Published:2014-09-29

摘要: 基于一般随机信息系统上的属性约简方法讨论合成随机信息系统上的属性约简问题,分析它与原随机信息系统上属性约简问题之间的联系,并尝试讨论其上、下近似算子之间的关系,发现合成随机信息系统上的协调集可以通过两个原随机信息系统的协调集来构造;另一方面从包含度的角度讨论属性约简问题,验证合成随机信息系统上的包含度和原随机信息系统上包含度之间是否存在等价关系。最后通过实例验证了得出的结论。

关键词: 合成随机信息系统, 属性约简, 协调集, 近似算子, 包含度

Abstract: This paper discusses the attribute reduction problem in combined random information systems based on the random information systems, and analyzes the relationship between the combined and the original information systems, as well as the relationship between the lower and upper approximation operators, then finds the consistent set on the combined random information systems can be constructed through two consistent sets of the original information systems. On the other hand, from the point of the inclusion degree it considers the reduction problem on the combined information systems, to verify whether the equivalent relationship exists between the inclusion degrees. Finally, the conclusions are verified through the instance.

Key words: combined random information systems, attribute reduction, consistent set, approximation operators, inclusion degree