计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (33): 49-51.

• 研究、探讨 • 上一篇    下一篇

基于自适应遗传算法的粗糙集属性约简算法

孙娓娓,王春生,姚云飞   

  1. 阜阳师范学院 数学与计算科学学院,安徽 阜阳 236041
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-11-21 发布日期:2011-11-21

Rough set attribute reduction algorithm based on adaptive genetic algorithm

SUN Weiwei,WANG Chunsheng,YAO Yunfei   

  1. School of Mathematics and Computational Science,Fuyang Teachers College,Fuyang,Anhui 236041,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-11-21 Published:2011-11-21

摘要: 为了获得有效的最小属性约简,提出了一种基于改进遗传算法的粗糙集属性约简算法。该算法将属性的相对核加入遗传算法的初始种群以提高算法的收敛速度。通过采用自适应交叉和变异、修剪相似个体、动态补充新个体等遗传操作,增加了群体的多样性,避免了“早熟”现象。仿真结果表明,算法在约简的效率和准确性方面都取得了较好的结果,是一种行之有效的属性约简算法。

关键词: 属性约简, 遗传算法, 相对核, 自适应, 修剪

Abstract: In order to get the reduction of attribute,a new rough set attribute reduction algorithm based on Improved Genetic Algorithm(IGA) is proposed.The relative core of attribute is joined initial population in IGA in order to improve the convergence rate.By using self-adaptive crossover and mutation,pruning similar individuals,supplying new individuals dynamically and other operations,the diversity of population is increased and the “premature” phenomenon is avoided.The simulation results show that this algorithm has achieved better results in the efficiency and accuracy of reduction.It is an effective attribute reduction algorithm.

Key words: attribute reduction, genetic algorithm, relative core, self-adaptive, pruning