A feature ranking technique based on interclass separability for fuzzy modeling

D. Tikk, Kok Wai Wong

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper presents a modified feature ranking method based on interclass separability for fuzzy modeling. Existing feature selection/ranking techniques are mostly suitable for classification problems. These techniques result in a ranking of the input feature or variables. Our modification exploits an arbitrary fuzzy clustering of the model output data. Using these output clusters, similar feature ranking methods can be used as for classification, where the membership in a cluster (or class) will no longer be crisp, but a fuzzy value determined by the clustering. We propose an iterative algorithm to determine the feature ranking by means of different criterion functions. We examined the proposed method and the criterion functions through a comparative analysis.

Original languageEnglish
Title of host publicationICCC 2007 - 5th IEEE International Conference on Computational Cybernetics, Proceedings
Pages251-256
Number of pages6
DOIs
Publication statusPublished - 2007
EventICCC 2007 - 5th IEEE International Conference on Computational Cybernetics - Gammarth, Tunisia
Duration: Oct 19 2007Oct 21 2007

Other

OtherICCC 2007 - 5th IEEE International Conference on Computational Cybernetics
CountryTunisia
CityGammarth
Period10/19/0710/21/07

Fingerprint

Fuzzy clustering
Feature extraction

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Control and Systems Engineering

Cite this

Tikk, D., & Wong, K. W. (2007). A feature ranking technique based on interclass separability for fuzzy modeling. In ICCC 2007 - 5th IEEE International Conference on Computational Cybernetics, Proceedings (pp. 251-256). [4402044] https://doi.org/10.1109/ICCCYB.2007.4402044

A feature ranking technique based on interclass separability for fuzzy modeling. / Tikk, D.; Wong, Kok Wai.

ICCC 2007 - 5th IEEE International Conference on Computational Cybernetics, Proceedings. 2007. p. 251-256 4402044.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Tikk, D & Wong, KW 2007, A feature ranking technique based on interclass separability for fuzzy modeling. in ICCC 2007 - 5th IEEE International Conference on Computational Cybernetics, Proceedings., 4402044, pp. 251-256, ICCC 2007 - 5th IEEE International Conference on Computational Cybernetics, Gammarth, Tunisia, 10/19/07. https://doi.org/10.1109/ICCCYB.2007.4402044
Tikk D, Wong KW. A feature ranking technique based on interclass separability for fuzzy modeling. In ICCC 2007 - 5th IEEE International Conference on Computational Cybernetics, Proceedings. 2007. p. 251-256. 4402044 https://doi.org/10.1109/ICCCYB.2007.4402044
Tikk, D. ; Wong, Kok Wai. / A feature ranking technique based on interclass separability for fuzzy modeling. ICCC 2007 - 5th IEEE International Conference on Computational Cybernetics, Proceedings. 2007. pp. 251-256
@inproceedings{b9db7f42d68a4b07a5ca1dbda0bf789a,
title = "A feature ranking technique based on interclass separability for fuzzy modeling",
abstract = "This paper presents a modified feature ranking method based on interclass separability for fuzzy modeling. Existing feature selection/ranking techniques are mostly suitable for classification problems. These techniques result in a ranking of the input feature or variables. Our modification exploits an arbitrary fuzzy clustering of the model output data. Using these output clusters, similar feature ranking methods can be used as for classification, where the membership in a cluster (or class) will no longer be crisp, but a fuzzy value determined by the clustering. We propose an iterative algorithm to determine the feature ranking by means of different criterion functions. We examined the proposed method and the criterion functions through a comparative analysis.",
author = "D. Tikk and Wong, {Kok Wai}",
year = "2007",
doi = "10.1109/ICCCYB.2007.4402044",
language = "English",
isbn = "1424411467",
pages = "251--256",
booktitle = "ICCC 2007 - 5th IEEE International Conference on Computational Cybernetics, Proceedings",

}

TY - GEN

T1 - A feature ranking technique based on interclass separability for fuzzy modeling

AU - Tikk, D.

AU - Wong, Kok Wai

PY - 2007

Y1 - 2007

N2 - This paper presents a modified feature ranking method based on interclass separability for fuzzy modeling. Existing feature selection/ranking techniques are mostly suitable for classification problems. These techniques result in a ranking of the input feature or variables. Our modification exploits an arbitrary fuzzy clustering of the model output data. Using these output clusters, similar feature ranking methods can be used as for classification, where the membership in a cluster (or class) will no longer be crisp, but a fuzzy value determined by the clustering. We propose an iterative algorithm to determine the feature ranking by means of different criterion functions. We examined the proposed method and the criterion functions through a comparative analysis.

AB - This paper presents a modified feature ranking method based on interclass separability for fuzzy modeling. Existing feature selection/ranking techniques are mostly suitable for classification problems. These techniques result in a ranking of the input feature or variables. Our modification exploits an arbitrary fuzzy clustering of the model output data. Using these output clusters, similar feature ranking methods can be used as for classification, where the membership in a cluster (or class) will no longer be crisp, but a fuzzy value determined by the clustering. We propose an iterative algorithm to determine the feature ranking by means of different criterion functions. We examined the proposed method and the criterion functions through a comparative analysis.

UR - http://www.scopus.com/inward/record.url?scp=47349106388&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=47349106388&partnerID=8YFLogxK

U2 - 10.1109/ICCCYB.2007.4402044

DO - 10.1109/ICCCYB.2007.4402044

M3 - Conference contribution

AN - SCOPUS:47349106388

SN - 1424411467

SN - 9781424411467

SP - 251

EP - 256

BT - ICCC 2007 - 5th IEEE International Conference on Computational Cybernetics, Proceedings

ER -