Redundancy Is Not Necessarily Detrimental in Classification Problems

Author:

Grillo Sebastián AlbertoORCID,Noguera José Luis VázquezORCID,Mello Román Julio César MelloORCID,García-Torres MiguelORCID,Facon JacquesORCID,Pinto-Roa Diego P.ORCID,Salgueiro Romero Luis SalgueiroORCID,Gómez-Vela FranciscoORCID,Paniagua Laura Raquel BareiroORCID,Correa Deysi Natalia LeguizamonORCID

Abstract

In feature selection, redundancy is one of the major concerns since the removal of redundancy in data is connected with dimensionality reduction. Despite the evidence of such a connection, few works present theoretical studies regarding redundancy. In this work, we analyze the effect of redundant features on the performance of classification models. We can summarize the contribution of this work as follows: (i) develop a theoretical framework to analyze feature construction and selection, (ii) show that certain properly defined features are redundant but make the data linearly separable, and (iii) propose a formal criterion to validate feature construction methods. The results of experiments suggest that a large number of redundant features can reduce the classification error. The results imply that it is not enough to analyze features solely using criteria that measure the amount of information provided by such features.

Funder

Consejo Nacional de Ciencia y Tecnología

Publisher

MDPI AG

Subject

General Mathematics,Engineering (miscellaneous),Computer Science (miscellaneous)

Reference64 articles.

1. A review of feature selection methods based on mutual information

2. An introduction to variable and feature selection;Guyon;J. Mach. Learn. Res.,2003

3. Feature construction methods: A survey;Sondhi;Sifaka. Cs. Uiuc. Edu.,2009

4. IG-GA: A Hybrid Filter/Wrapper Method for Feature Selection of Microarray Data;Yang;J. Med. Biol. Eng.,2010

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3