KDD中的特征选择

随着数据库、数据仓库技术的发展,各种数据处理和分析工具不断出现,数据库中的知识发现(简称KDD)就是现在受到研究人员和软件开发商广泛关注的一种数据分析方法。文章主要针对KDD的数据预处理阶段的一类重要问题———分类问题,描述了特征选择的概念,分析了它在KDD中应用的重要性和必要性,并针对KDD的特点介绍现有的特征选择的各种方法并进行归纳,为下一步的研究和开发提供一个有益的框架。

Feature Subset Selection for KDD

With the development of database and data warehous,many data processing and analysis tools have been developed.Knowledge discovery in database(KDD)is a method of data analysis which get a great deal of attention from researchers and software developers.In this paper,the authors attention converges to a very important aspect of data preprocessing,feature selection.Feature selection is mostly used in classification,an important task of KDD.In this paper the authors describe the definition of feature selection,analysis the significance and necessity of it's usage in KDD.They also introduce a great variety of feature selection methods that can adapt the circumstance of KDD and give a useful framework for the further research and development.