• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

J4 ›› 2010, Vol. 32 ›› Issue (5): 82-84.doi: 10.3969/j.issn.1007130X.2010.

• 论文 • 上一篇    下一篇

基于量子蚁群算法的粗糙集属性约简方法

袁浩   

  1. (重庆邮电大学电子商务与现代物流实验室,重庆 400065)
  • 收稿日期:2009-11-15 修回日期:2010-02-09 出版日期:2010-04-28 发布日期:2010-05-11
  • 通讯作者: 袁浩 E-mail:yln2446@21cn.com
  • 作者简介:袁浩(1970),男,重庆人,硕士,讲师,研究方向为计算机网络和信息安全。
  • 基金资助:

    重庆市科委自然科学基金资助项目(2009BB2288)

A Rough Set Attribute Reduction Method Based on the Quantum Ant Colony Algorithm

YUAN Hao   

  1. (Laboratory of Electronic Commere and Modern Logistics,
    Chongqing University of Post and Telecommunications,Chongqing 400065,China)
  • Received:2009-11-15 Revised:2010-02-09 Online:2010-04-28 Published:2010-05-11
  • Contact: YUAN Hao E-mail:yln2446@21cn.com

摘要:

针对蚁群算法求取属性约简中存在的迭代次数多、收敛较慢甚至得不到最小约简的问题,提出了基于量子蚁群算法的粗糙集属性约简的方法。每只蚂蚁携带一组表示蚂蚁当前位置信息的量子比特;采用量子旋转门完成蚂蚁的移动;采用量子非门实现蚂蚁所在位置的变异。实验证明,该算法能快速有效地求解属性约简,同时又能找到许多次最小约简。可以很好地解决这一难题,它不仅能得到最小约简属性集,而且可以得到很多的约简属性集。

关键词: 属性约简, 粗糙集, 量子蚁群, 蚁群算法

Abstract:

As for the ant colony algorithm for attribute reduction which has the problems such as many iterationss, slow convergence obtaining no smallest reductions, this paper proposes the quantum ant colony for rough set attribute reduction. Each ant carries a group of ants which represent the current location information of quantum bits, uses  quantum revolving doors to complete the ant movement,and uses quantum gates to realize the nonant variation of the location. The experiments show that the algorithm can quickly and efficiently solve attribute reduction, and find the smallest reduction. It not only can get the smallest reduction attribute set, but also get a lot of reduction attribute set.

Key words: attribute reduction;rough set;quantum ant colony;ant colony algorithm

中图分类号: