Fuzzy canonical discriminant analysis: Theory and practice

Ben Chang Shia, Jianping Zhu, Kuangnan Fang, Shuangge Ma

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this article, we propose a new classification method called fuzzy canonical discriminant analysis (FCDA) based on the Fisher's canonical discriminant analysis (CDA) to deal with some vagueness in natural and social science and to improve its prediction accuracy. By establishing the fuzzy canonical discriminant function and triangular function transformation, we obtain the estimators of parameters. We also design an efficient algorithm for calculation of the parameters. We compare it with CDA using the original Iris data, samples of the Iris data, and seven other popular data sets. The results confirms that the FCDA is an effective tool in prediction and is better than the CDA.

Original languageEnglish
Pages (from-to)1526-1539
Number of pages14
JournalCommunications in Statistics: Simulation and Computation
Volume40
Issue number10
DOIs
Publication statusPublished - Nov 2011
Externally publishedYes

Fingerprint

Canonical Analysis
Discriminant analysis
Discriminant Analysis
Iris
Natural sciences
Discriminant Function
Social sciences
Vagueness
Prediction
Social Sciences
Triangular
Efficient Algorithms
Estimator

Keywords

  • Classification
  • Fuzzy canonical discriminant analysis
  • Fuzzy set theory

ASJC Scopus subject areas

  • Modelling and Simulation
  • Statistics and Probability

Cite this

Fuzzy canonical discriminant analysis : Theory and practice. / Shia, Ben Chang; Zhu, Jianping; Fang, Kuangnan; Ma, Shuangge.

In: Communications in Statistics: Simulation and Computation, Vol. 40, No. 10, 11.2011, p. 1526-1539.

Research output: Contribution to journalArticle

Shia, Ben Chang ; Zhu, Jianping ; Fang, Kuangnan ; Ma, Shuangge. / Fuzzy canonical discriminant analysis : Theory and practice. In: Communications in Statistics: Simulation and Computation. 2011 ; Vol. 40, No. 10. pp. 1526-1539.
@article{f4d83e7dfdc24544906054961657b547,
title = "Fuzzy canonical discriminant analysis: Theory and practice",
abstract = "In this article, we propose a new classification method called fuzzy canonical discriminant analysis (FCDA) based on the Fisher's canonical discriminant analysis (CDA) to deal with some vagueness in natural and social science and to improve its prediction accuracy. By establishing the fuzzy canonical discriminant function and triangular function transformation, we obtain the estimators of parameters. We also design an efficient algorithm for calculation of the parameters. We compare it with CDA using the original Iris data, samples of the Iris data, and seven other popular data sets. The results confirms that the FCDA is an effective tool in prediction and is better than the CDA.",
keywords = "Classification, Fuzzy canonical discriminant analysis, Fuzzy set theory",
author = "Shia, {Ben Chang} and Jianping Zhu and Kuangnan Fang and Shuangge Ma",
year = "2011",
month = "11",
doi = "10.1080/03610918.2011.589337",
language = "English",
volume = "40",
pages = "1526--1539",
journal = "Communications in Statistics Part B: Simulation and Computation",
issn = "0361-0918",
publisher = "Taylor and Francis Ltd.",
number = "10",

}

TY - JOUR

T1 - Fuzzy canonical discriminant analysis

T2 - Theory and practice

AU - Shia, Ben Chang

AU - Zhu, Jianping

AU - Fang, Kuangnan

AU - Ma, Shuangge

PY - 2011/11

Y1 - 2011/11

N2 - In this article, we propose a new classification method called fuzzy canonical discriminant analysis (FCDA) based on the Fisher's canonical discriminant analysis (CDA) to deal with some vagueness in natural and social science and to improve its prediction accuracy. By establishing the fuzzy canonical discriminant function and triangular function transformation, we obtain the estimators of parameters. We also design an efficient algorithm for calculation of the parameters. We compare it with CDA using the original Iris data, samples of the Iris data, and seven other popular data sets. The results confirms that the FCDA is an effective tool in prediction and is better than the CDA.

AB - In this article, we propose a new classification method called fuzzy canonical discriminant analysis (FCDA) based on the Fisher's canonical discriminant analysis (CDA) to deal with some vagueness in natural and social science and to improve its prediction accuracy. By establishing the fuzzy canonical discriminant function and triangular function transformation, we obtain the estimators of parameters. We also design an efficient algorithm for calculation of the parameters. We compare it with CDA using the original Iris data, samples of the Iris data, and seven other popular data sets. The results confirms that the FCDA is an effective tool in prediction and is better than the CDA.

KW - Classification

KW - Fuzzy canonical discriminant analysis

KW - Fuzzy set theory

UR - http://www.scopus.com/inward/record.url?scp=80051676861&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80051676861&partnerID=8YFLogxK

U2 - 10.1080/03610918.2011.589337

DO - 10.1080/03610918.2011.589337

M3 - Article

AN - SCOPUS:80051676861

VL - 40

SP - 1526

EP - 1539

JO - Communications in Statistics Part B: Simulation and Computation

JF - Communications in Statistics Part B: Simulation and Computation

SN - 0361-0918

IS - 10

ER -