计算机应用 ›› 2014, Vol. 34 ›› Issue (2): 401-405.

• 数据技术 • 上一篇    下一篇

基于灰关联分析的连续值属性约减算法

张健,王晋东,余定坤   

  1. 信息工程大学,郑州 450000
  • 收稿日期:2013-07-29 修回日期:2013-09-03 出版日期:2014-02-01 发布日期:2014-03-01
  • 通讯作者: 张健
  • 作者简介:张健(1989-),男,山东滨州人,硕士研究生,主要研究方向:风险评估、属性约减;王晋东(1966-),男,河南郑州人,教授,主要研究方向:资源管理、风险评估、嵌入式系统安全;余定坤(1991-),男,广东广州人,硕士研究生,主要研究方向:评估指标体系、可信计算。
  • 基金资助:
    国防预研项目

Continuous-valued attributes reduction algorithm based on gray correlation

ZHANG Jian,WANG Jindong,YU Dingkun   

  1. Information Engineering University, Zhengzhou Henan 450000, China
  • Received:2013-07-29 Revised:2013-09-03 Online:2014-02-01 Published:2014-03-01
  • Contact: ZHANG Jian

摘要: 针对目前大多数属性约减算法只能用于离散值决策表的情况,将条件属性与决策属性的关联度作为属性约减的重要性测度,同时基于条件属性间的关联度和重要度定义了条件属性的重叠性测度,据此对条件属性进行去重叠化处理,提出了一种基于灰关联分析的连续值属性约减算法CARAG,实现了对连续值属性集的约减,并在仿真实验中对算法的可行性和有效性进行了对比验证。

关键词: 属性约减, 灰关联分析, 重叠度, 连续值属性

Abstract: Since most current attributes reduction algorithm can be only used for discrete decision tables, the correlation degree between condition attributes and decision attributes was defined as the importance degree of attributes, and meanwhile the overlap degree was defined based on the correlation degree and importance degree among attributes. The condition attributes' importance was renewed according to the overlap degree. To achieve the reduction of continuous-valued attributes set, an attributes reduction algorithm based on gray correlation analysis was proposed. The feasibility and effectiveness of the algorithm were verified in the simulation.

Key words: attribute reduction, grey correlation analysis, overlap degree, continuous-valued attribute

中图分类号: