2.765

2022影响因子

(CJCR)

  • 中文核心
  • EI
  • 中国科技核心
  • Scopus
  • CSCD
  • 英国科学文摘

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

分类分析中基于信息论准则的特征选取

黄金杰 吕宁 李双全 蔡云泽

黄金杰, 吕宁, 李双全, 蔡云泽. 分类分析中基于信息论准则的特征选取. 自动化学报, 2008, 34(3): 383-392. doi: 10.3724/SP.J.1004.2008.00383
引用本文: 黄金杰, 吕宁, 李双全, 蔡云泽. 分类分析中基于信息论准则的特征选取. 自动化学报, 2008, 34(3): 383-392. doi: 10.3724/SP.J.1004.2008.00383
HUANG Jin-Jie, LV Ning, LI Shuang-Quan, CAI Yun-Ze. Feature Selection for Classifficatory Analysis Based on Information-theoretic Criteria. ACTA AUTOMATICA SINICA, 2008, 34(3): 383-392. doi: 10.3724/SP.J.1004.2008.00383
Citation: HUANG Jin-Jie, LV Ning, LI Shuang-Quan, CAI Yun-Ze. Feature Selection for Classifficatory Analysis Based on Information-theoretic Criteria. ACTA AUTOMATICA SINICA, 2008, 34(3): 383-392. doi: 10.3724/SP.J.1004.2008.00383

分类分析中基于信息论准则的特征选取

doi: 10.3724/SP.J.1004.2008.00383
详细信息
    通讯作者:

    黄金杰

Feature Selection for Classifficatory Analysis Based on Information-theoretic Criteria

More Information
    Corresponding author: HUANG Jin-Jie
  • 摘要: Feature selection aims to reduce the dimensionality of patterns for classificatory analysis by selecting the most informative instead of irrelevant and/or redundant features. In this study, two novel information-theoretic measures for feature ranking are presented: one is an improved formula to estimate the conditional mutual information between the candidate feature fi and the target class C given the subset of selected features S, i.e., I(C;fi|S), under the assumption that information of features is distributed uniformly; the other is a mutual information (MI) based constructive criterion that is able to capture both irrelevant and redundant input features under arbitrary distributions of information of features. With these two measures, two new feature selection algorithms, called the quadratic MI-based feature selection (QMIFS) approach and the MI-based constructive criterion (MICC) approach, respectively, are proposed, in which no parameters like β in Battiti's MIFS and (Kwak and Choi)'s MIFS-U methods need to be preset. Thus, the intractable problem of how to choose an appropriate value for β to do the tradeoff between the relevance to the target classes and the redundancy with the already-selected features is avoided completely. Experimental results demonstrate the good performances of QMIFS and MICC on both synthetic and benchmark data sets.
  • 加载中
计量
  • 文章访问数:  2708
  • HTML全文浏览量:  51
  • PDF下载量:  1487
  • 被引次数: 0
出版历程
  • 收稿日期:  2007-05-29
  • 修回日期:  2007-11-14
  • 刊出日期:  2008-03-20

目录

    /

    返回文章
    返回