二步式轮询多准则特征选择算法  

Poll multi-criteria feature selection algorithm based on two-step mode

作　　者：周頔[1] 李勇明[2] 

机构地区：[1]四川文理学院计算机科学系,达州四川635000 [2]重庆大学通信工程学院,重庆400030

出　　处：《计算机应用》2009年第1期132-135,154,共5页journal of Computer Applications

基　　金：国家自然科学基金资助项目(30570473);四川省教育厅2008年青年基金资助项目(07ZB074);重庆市自然科学基金资助项目(CSTC;2008BB2164);2008年重庆大学青年骨干教师创新能力培育基金资助项目(CDCX018)

摘　　要：针对filter模式下传统遗传算法特征选择精度不高,wrapper模式特征选择时间代价较高的缺点,提出了一种新的轮询多准则特征选择算法。该算法以搜索性能较好的链式智能体遗传算法为搜索算法,引入主准则分析方法确定评价准则的轮询次序,实现高性能的多准则特征选择。将该算法与filter模式和wrapper模式下特征选择算法以及顺序轮询式特征选择算法进行了比较。实验结果表明,该算法具有比filter模式下单评价准则选择精度更高,比wrapper模式所需时间代价更低等特点。For the low precision of feature selection under filter mode and high time cost of feature selection under wrapper mode, one new poll multi-criteria feature selection algorithm was proposed. This algorithm adopted chain-like agent genetic algorithm as searching algorithm, introduced principal criteria strategy to ensure the order of poll, thereby realizing multi-criteria feature selection algorithm. The experiments were conducted to compare this algorithm and several other feature selection algorithms. The experimental results show that this algorithm can obtain better precise selection resuh than several single evaluation criterion feature selection algorithms under filter mode, and less selection time cost than feature selection algorithm under wrapper mode.

关 键 词：特征选择 遗传算法 两步式 轮询式 多准则 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]