Fuzzy kernel feature selection with multi-objective differential evolution algorithm

In this paper, we propose a multi-objective differential evolution-based filter approach for feature selection that interconnects fuzzy- and kernel-based information theory measures to find feature subsets that are optimal responses to the targets. In contrast to the existing filter approaches using...

Full description

Saved in:
Bibliographic Details
Main Author: Emrah Hancer
Format: Article
Language:English
Published: Taylor & Francis Group 2019-10-01
Series:Connection Science
Subjects:
Online Access:http://dx.doi.org/10.1080/09540091.2019.1639624
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850176603780284416
author Emrah Hancer
author_facet Emrah Hancer
author_sort Emrah Hancer
collection DOAJ
description In this paper, we propose a multi-objective differential evolution-based filter approach for feature selection that interconnects fuzzy- and kernel-based information theory measures to find feature subsets that are optimal responses to the targets. In contrast to the existing filter approaches using the principles of information theory and rough set theory, our approach can be applied to continuous datasets without discretisation. Moreover, our study is the first in the literature that employs fuzzy and kernel measures to form a filter criterion for feature selection, to our knowledge. We prove various favourable results using a variety of benchmark datasets and also demonstrate that our approach can better search the dimensionality space to reach maximum predictive of the response.
format Article
id doaj-art-c19447a085fc498ba1da77db5a134761
institution OA Journals
issn 0954-0091
1360-0494
language English
publishDate 2019-10-01
publisher Taylor & Francis Group
record_format Article
series Connection Science
spelling doaj-art-c19447a085fc498ba1da77db5a1347612025-08-20T02:19:12ZengTaylor & Francis GroupConnection Science0954-00911360-04942019-10-0131432334110.1080/09540091.2019.16396241639624Fuzzy kernel feature selection with multi-objective differential evolution algorithmEmrah Hancer0Mehmet Akif Ersoy UniversityIn this paper, we propose a multi-objective differential evolution-based filter approach for feature selection that interconnects fuzzy- and kernel-based information theory measures to find feature subsets that are optimal responses to the targets. In contrast to the existing filter approaches using the principles of information theory and rough set theory, our approach can be applied to continuous datasets without discretisation. Moreover, our study is the first in the literature that employs fuzzy and kernel measures to form a filter criterion for feature selection, to our knowledge. We prove various favourable results using a variety of benchmark datasets and also demonstrate that our approach can better search the dimensionality space to reach maximum predictive of the response.http://dx.doi.org/10.1080/09540091.2019.1639624kernel spacefuzzy information theorymulti-objective optimisationdifferential evolutionfeature selection
spellingShingle Emrah Hancer
Fuzzy kernel feature selection with multi-objective differential evolution algorithm
Connection Science
kernel space
fuzzy information theory
multi-objective optimisation
differential evolution
feature selection
title Fuzzy kernel feature selection with multi-objective differential evolution algorithm
title_full Fuzzy kernel feature selection with multi-objective differential evolution algorithm
title_fullStr Fuzzy kernel feature selection with multi-objective differential evolution algorithm
title_full_unstemmed Fuzzy kernel feature selection with multi-objective differential evolution algorithm
title_short Fuzzy kernel feature selection with multi-objective differential evolution algorithm
title_sort fuzzy kernel feature selection with multi objective differential evolution algorithm
topic kernel space
fuzzy information theory
multi-objective optimisation
differential evolution
feature selection
url http://dx.doi.org/10.1080/09540091.2019.1639624
work_keys_str_mv AT emrahhancer fuzzykernelfeatureselectionwithmultiobjectivedifferentialevolutionalgorithm