基于遗传算法的特征选择方法  

Research on Feature Selection Using Genetic Algorithms

作　　者：赵云[1] 刘惟一[1] 

机构地区：[1]云南大学信息学院计算机科学系,昆明650091

出　　处：《计算机工程与应用》2004年第15期52-54,共3页Computer Engineering and Applications

基　　金：国家自然科学基金(编号:60263006);云南省自然科学基金(编号:2002F0063M);科学院智能信息处理开放实验室基金(编号:IIP2002-2)

摘　　要：特征提取广泛应用于模式识别、知识发现、机器学习等诸多领域,并受到了越来越多的关注犤1犦。对于一个给定的待分类模式,特征提取要求人们从大量的特征中选取一个最优特征子集,以代表被分类的模式。该文对特征提取这一组合优化及多目标优化问题提出了基于遗传算法的解决方法,把遗传算法作为识别或分类系统的“前端”,找出代表问题空间的最优特征子集,以大大降低分类系统的搜索空间,从而提高搜索效率。Selecting a set of features which is optimal for a given task is a problem which plays an important role in a wide variety of contents including pattern recognition,knowledge discovery,and machine learning.These problems require selection of a subset of attributes or features(from a much larger set)to represent the patterns to be classified.This paper presents an approach to the combination optimization and multi-criteria optimization problem of feature selection using genetic algorithms.The approach described here involves the use of genetic algorithms as a″front end″to a classification or recognition system in order to find the best subset of features and reduce the number of features used to represent the problem spaces.

关 键 词：遗传算法 特征提取 最优特征子集 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]