计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (34): 134-136.

• 数据库、信号与信息处理 • 上一篇    下一篇

基于离散差分演化的粗糙集属性约简算法

姚跃华,艾浩峰   

  1. 长沙理工大学 计算机与通信工程学院,长沙 410014
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-12-01 发布日期:2011-12-01

Rough set attribute reduction algorithm based on discrete differential evolution

YAO Yuehua,AI Haofeng   

  1. Institute of Computer and Communication Engineering,Changsha University of Sciences and Technology,Changsha 410014,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-12-01 Published:2011-12-01

摘要: 为了有效地获取属性最小相对约简,提出了一种新的基于离散差分演化算法的粗糙集属性约简算法。利用一种新的区间编码机制将差分演化算法离散化,用于求解最小属性约简问题。提出了一种新的适应度函数计算方法来控制染色体朝着最小约简的方向进化。实验结果表明该算法是有效的,特别是当数据规模较大时收敛速度更快,更加节省计算时间,为属性约简提供了一个新的思路。

关键词: 粗糙集, 属性约简, 差分演化算法, 区间编码映射

Abstract: In order to get minimal subsets of attributes,this paper proposes a rough set attribute reduction algorithm based on discrete differential evolution algorithm.Using a new range encoding mapping,the differential evolution algorithm can be used to deal with minimum attribute reduction problem.Secondly,a new calculation of the fitness function is proposed to control chromosomes’evolution in the direction of the minimum reduction.Experimental results show that the algorithm is effective,especially when data is large-scale,with fast convergence speed and more time saved in computation,which provides a new idea for attribute reduction.

Key words: rough set, attribute reduction, differential evolution algorithm, range encoding mapping