Fuzzy c-means algorithms for data with tolerance using kernel functions

Yuchi Kanzawa, Yasunori Endo, Sadaaki Miyamoto

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

In this paper, two new clustering algorithms based on fuzzy c-means for data with tolerance using kernel functions are proposed. Kernel functions which map the data from the original space into higher dimensional feature space are introduced into the proposed algorithms. Nonlinear boundary of clusters can be easily found by using the kernel functions. First, two clustering algorithms for data with tolerance are introduced. One is based on standard method and the other is on entropy-based one. Second, the tolerance in feature space is discussed taking account into soft margin algorithm in Support Vector Machine. Third, two objective functions in feature space are shown corresponding to two methods, respectively. Fourth, Karush-Kuhn-Tucker conditions of two objective functions are considered, respectively, and these conditions are re-expressed with kernel functions as the representation of an inner product for mapping from the original pattern space into a higher dimensional feature space. Fifth, two iterative algorithms are proposed for the objective functions, respectively. Through some numerical experiments, the proposed algorithms are discussed.

Original languageEnglish
Pages (from-to)2520-2534
Number of pages15
JournalIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
VolumeE91-A
Issue number9
DOIs
Publication statusPublished - 2008 Sep

Fingerprint

Clustering algorithms
Support vector machines
Entropy

Keywords

  • Clustering
  • Fuzzy c-means
  • Kernel functions
  • Tolerance

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Graphics and Computer-Aided Design
  • Applied Mathematics
  • Signal Processing

Cite this

Fuzzy c-means algorithms for data with tolerance using kernel functions. / Kanzawa, Yuchi; Endo, Yasunori; Miyamoto, Sadaaki.

In: IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, Vol. E91-A, No. 9, 09.2008, p. 2520-2534.

Research output: Contribution to journalArticle

@article{e822b191a53d4dc4bb11b2a964866924,
title = "Fuzzy c-means algorithms for data with tolerance using kernel functions",
abstract = "In this paper, two new clustering algorithms based on fuzzy c-means for data with tolerance using kernel functions are proposed. Kernel functions which map the data from the original space into higher dimensional feature space are introduced into the proposed algorithms. Nonlinear boundary of clusters can be easily found by using the kernel functions. First, two clustering algorithms for data with tolerance are introduced. One is based on standard method and the other is on entropy-based one. Second, the tolerance in feature space is discussed taking account into soft margin algorithm in Support Vector Machine. Third, two objective functions in feature space are shown corresponding to two methods, respectively. Fourth, Karush-Kuhn-Tucker conditions of two objective functions are considered, respectively, and these conditions are re-expressed with kernel functions as the representation of an inner product for mapping from the original pattern space into a higher dimensional feature space. Fifth, two iterative algorithms are proposed for the objective functions, respectively. Through some numerical experiments, the proposed algorithms are discussed.",
keywords = "Clustering, Fuzzy c-means, Kernel functions, Tolerance",
author = "Yuchi Kanzawa and Yasunori Endo and Sadaaki Miyamoto",
year = "2008",
month = "9",
doi = "10.1093/ietfec/e91-a.9.2520",
language = "English",
volume = "E91-A",
pages = "2520--2534",
journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",
issn = "0916-8508",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "9",

}

TY - JOUR

T1 - Fuzzy c-means algorithms for data with tolerance using kernel functions

AU - Kanzawa, Yuchi

AU - Endo, Yasunori

AU - Miyamoto, Sadaaki

PY - 2008/9

Y1 - 2008/9

N2 - In this paper, two new clustering algorithms based on fuzzy c-means for data with tolerance using kernel functions are proposed. Kernel functions which map the data from the original space into higher dimensional feature space are introduced into the proposed algorithms. Nonlinear boundary of clusters can be easily found by using the kernel functions. First, two clustering algorithms for data with tolerance are introduced. One is based on standard method and the other is on entropy-based one. Second, the tolerance in feature space is discussed taking account into soft margin algorithm in Support Vector Machine. Third, two objective functions in feature space are shown corresponding to two methods, respectively. Fourth, Karush-Kuhn-Tucker conditions of two objective functions are considered, respectively, and these conditions are re-expressed with kernel functions as the representation of an inner product for mapping from the original pattern space into a higher dimensional feature space. Fifth, two iterative algorithms are proposed for the objective functions, respectively. Through some numerical experiments, the proposed algorithms are discussed.

AB - In this paper, two new clustering algorithms based on fuzzy c-means for data with tolerance using kernel functions are proposed. Kernel functions which map the data from the original space into higher dimensional feature space are introduced into the proposed algorithms. Nonlinear boundary of clusters can be easily found by using the kernel functions. First, two clustering algorithms for data with tolerance are introduced. One is based on standard method and the other is on entropy-based one. Second, the tolerance in feature space is discussed taking account into soft margin algorithm in Support Vector Machine. Third, two objective functions in feature space are shown corresponding to two methods, respectively. Fourth, Karush-Kuhn-Tucker conditions of two objective functions are considered, respectively, and these conditions are re-expressed with kernel functions as the representation of an inner product for mapping from the original pattern space into a higher dimensional feature space. Fifth, two iterative algorithms are proposed for the objective functions, respectively. Through some numerical experiments, the proposed algorithms are discussed.

KW - Clustering

KW - Fuzzy c-means

KW - Kernel functions

KW - Tolerance

UR - http://www.scopus.com/inward/record.url?scp=77953388380&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953388380&partnerID=8YFLogxK

U2 - 10.1093/ietfec/e91-a.9.2520

DO - 10.1093/ietfec/e91-a.9.2520

M3 - Article

VL - E91-A

SP - 2520

EP - 2534

JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

SN - 0916-8508

IS - 9

ER -