[1]王艳丽,梁静,薛冰,等.基于进化计算的特征选择方法研究概述[J].郑州大学学报(工学版),2020,41(01):49-57.
 Research on Evolutionary Computation for Feature Selection[J].Journal of Zhengzhou University (Engineering Science),2020,41(01):49-57.
点击复制

基于进化计算的特征选择方法研究概述()
分享到:

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
41
期数:
2020年01期
页码:
49-57
栏目:
出版日期:
2020-03-10

文章信息/Info

Title:
Research on Evolutionary Computation for Feature Selection
作者:
王艳丽梁静薛冰岳彩通
关键词:
分类进化计算特征选择
Keywords:
classificationevolutionary computationfeature selecction
文献标志码:
A
摘要:
特征选择是数据挖掘和机器学习中的关键问题,特征选择结果的好坏直接影响分类器的分类精度和泛化性能. 然而,由于其搜索空间很大,特征选择仍是一个具有挑战性的工作. 解决特征选择问题的方法有许多,其中进化计算技术近年来受到广泛关注,并取得了一定的成功. 本文首先介绍了特征选择的基本框架;然后从进化计算特征选择方法的搜索机制、子集评价策略和目标数等方面进行了分析和总结;最后讨论了当前基于进化计算的特征选择方法面临的问题和挑战,以及未来进一步的研究方向.
Abstract:
Feature selection is a key issue in data mining and machine learning . The accuracy and generalization performance of a classifier are affected by the result of feature selection significantly. However, feature selection is a challenging task due mainly to the large search space. A variety of methods have been applied to solve feature selection problems, where evolutionary computation (EC) techniques have recently gained much attention and shown some success. This paper first introduces the basic framework of feature selection. Then the search mechanism, subset evaluation strategy and objective number of feature selection methods based on evolutionary computation are analyzed and summarized. Finally, current issues and challenges are also discussed to identify promising areas for future research
更新日期/Last Update: 2020-02-22