A new nonlinear classifier with a penalized signed fuzzy measure using effective genetic algorithm

Hua Fang, Maria L. Rizzo, Honggang Wang, Kimberly Andrews Espy, Zhenyuan Wang

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

This paper proposes a new nonlinear classifier based on a generalized Choquet integral with signed fuzzy measures to enhance the classification accuracy and power by capturing all possible interactions among two or more attributes. This generalized approach was developed to address unsolved Choquet-integral classification issues such as allowing for flexible location of projection lines in n-dimensional space, automatic search for the least misclassification rate based on Choquet distance, and penalty on misclassified points. A special genetic algorithm is designed to implement this classification optimization with fast convergence. Both the numerical experiment and empirical case studies show that this generalized approach improves and extends the functionality of this Choquet nonlinear classification in more real-world multi-class multi-dimensional situations.

Original languageEnglish (US)
Pages (from-to)1393-1401
Number of pages9
JournalPattern Recognition
Volume43
Issue number4
DOIs
StatePublished - Apr 2010
Externally publishedYes

Fingerprint

Classifiers
Genetic algorithms
Experiments

Keywords

  • Choquet integral
  • Classification
  • Genetic algorithm
  • Optimization
  • Signed fuzzy measure

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

A new nonlinear classifier with a penalized signed fuzzy measure using effective genetic algorithm. / Fang, Hua; Rizzo, Maria L.; Wang, Honggang; Espy, Kimberly Andrews; Wang, Zhenyuan.

In: Pattern Recognition, Vol. 43, No. 4, 04.2010, p. 1393-1401.

Research output: Contribution to journalArticle

Fang, Hua ; Rizzo, Maria L. ; Wang, Honggang ; Espy, Kimberly Andrews ; Wang, Zhenyuan. / A new nonlinear classifier with a penalized signed fuzzy measure using effective genetic algorithm. In: Pattern Recognition. 2010 ; Vol. 43, No. 4. pp. 1393-1401.
@article{16804cd927bd49e4b5d3265bc2dfe366,
title = "A new nonlinear classifier with a penalized signed fuzzy measure using effective genetic algorithm",
abstract = "This paper proposes a new nonlinear classifier based on a generalized Choquet integral with signed fuzzy measures to enhance the classification accuracy and power by capturing all possible interactions among two or more attributes. This generalized approach was developed to address unsolved Choquet-integral classification issues such as allowing for flexible location of projection lines in n-dimensional space, automatic search for the least misclassification rate based on Choquet distance, and penalty on misclassified points. A special genetic algorithm is designed to implement this classification optimization with fast convergence. Both the numerical experiment and empirical case studies show that this generalized approach improves and extends the functionality of this Choquet nonlinear classification in more real-world multi-class multi-dimensional situations.",
keywords = "Choquet integral, Classification, Genetic algorithm, Optimization, Signed fuzzy measure",
author = "Hua Fang and Rizzo, {Maria L.} and Honggang Wang and Espy, {Kimberly Andrews} and Zhenyuan Wang",
year = "2010",
month = "4",
doi = "10.1016/j.patcog.2009.10.006",
language = "English (US)",
volume = "43",
pages = "1393--1401",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "4",

}

TY - JOUR

T1 - A new nonlinear classifier with a penalized signed fuzzy measure using effective genetic algorithm

AU - Fang, Hua

AU - Rizzo, Maria L.

AU - Wang, Honggang

AU - Espy, Kimberly Andrews

AU - Wang, Zhenyuan

PY - 2010/4

Y1 - 2010/4

N2 - This paper proposes a new nonlinear classifier based on a generalized Choquet integral with signed fuzzy measures to enhance the classification accuracy and power by capturing all possible interactions among two or more attributes. This generalized approach was developed to address unsolved Choquet-integral classification issues such as allowing for flexible location of projection lines in n-dimensional space, automatic search for the least misclassification rate based on Choquet distance, and penalty on misclassified points. A special genetic algorithm is designed to implement this classification optimization with fast convergence. Both the numerical experiment and empirical case studies show that this generalized approach improves and extends the functionality of this Choquet nonlinear classification in more real-world multi-class multi-dimensional situations.

AB - This paper proposes a new nonlinear classifier based on a generalized Choquet integral with signed fuzzy measures to enhance the classification accuracy and power by capturing all possible interactions among two or more attributes. This generalized approach was developed to address unsolved Choquet-integral classification issues such as allowing for flexible location of projection lines in n-dimensional space, automatic search for the least misclassification rate based on Choquet distance, and penalty on misclassified points. A special genetic algorithm is designed to implement this classification optimization with fast convergence. Both the numerical experiment and empirical case studies show that this generalized approach improves and extends the functionality of this Choquet nonlinear classification in more real-world multi-class multi-dimensional situations.

KW - Choquet integral

KW - Classification

KW - Genetic algorithm

KW - Optimization

KW - Signed fuzzy measure

UR - http://www.scopus.com/inward/record.url?scp=74449089238&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=74449089238&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2009.10.006

DO - 10.1016/j.patcog.2009.10.006

M3 - Article

VL - 43

SP - 1393

EP - 1401

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 4

ER -