Robust kernel fuzzy clustering

Weiwei Du, Kohei Inoue, Kiichi Urahama

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

We present a method for extracting arbitrarily shaped clusters buried in uniform noise data. The popular k-means algorithm is firstly fuzzified with addition of entropic terms to the objective function of data partitioning problem. This fuzzy clustering is then kernelized for adapting to the arbitrary shape of clusters. Finally, the Euclidean distance in this kernelized fuzzy clustering is modified to a robust one for avoiding the influence of noisy background data. This robust kernel fuzzy clustering method is shown to outperform every its predecessor: fuzzified k-means, robust fuzzified k-means and kernel fuzzified k-means algorithms.

Original languageEnglish
Pages (from-to)454-461
Number of pages8
JournalUnknown Journal
Volume3613
Issue numberPART I
Publication statusPublished - 2005

Fingerprint

Fuzzy clustering
partitioning
method

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture

Cite this

Du, W., Inoue, K., & Urahama, K. (2005). Robust kernel fuzzy clustering. Unknown Journal, 3613(PART I), 454-461.

Robust kernel fuzzy clustering. / Du, Weiwei; Inoue, Kohei; Urahama, Kiichi.

In: Unknown Journal, Vol. 3613, No. PART I, 2005, p. 454-461.

Research output: Contribution to journalArticle

Du, W, Inoue, K & Urahama, K 2005, 'Robust kernel fuzzy clustering', Unknown Journal, vol. 3613, no. PART I, pp. 454-461.
Du W, Inoue K, Urahama K. Robust kernel fuzzy clustering. Unknown Journal. 2005;3613(PART I):454-461.
Du, Weiwei ; Inoue, Kohei ; Urahama, Kiichi. / Robust kernel fuzzy clustering. In: Unknown Journal. 2005 ; Vol. 3613, No. PART I. pp. 454-461.
@article{9bc3d0afbd114dab8c522ef5f79dbc8a,
title = "Robust kernel fuzzy clustering",
abstract = "We present a method for extracting arbitrarily shaped clusters buried in uniform noise data. The popular k-means algorithm is firstly fuzzified with addition of entropic terms to the objective function of data partitioning problem. This fuzzy clustering is then kernelized for adapting to the arbitrary shape of clusters. Finally, the Euclidean distance in this kernelized fuzzy clustering is modified to a robust one for avoiding the influence of noisy background data. This robust kernel fuzzy clustering method is shown to outperform every its predecessor: fuzzified k-means, robust fuzzified k-means and kernel fuzzified k-means algorithms.",
author = "Weiwei Du and Kohei Inoue and Kiichi Urahama",
year = "2005",
language = "English",
volume = "3613",
pages = "454--461",
journal = "Quaternary International",
issn = "1040-6182",
publisher = "Elsevier Limited",
number = "PART I",

}

TY - JOUR

T1 - Robust kernel fuzzy clustering

AU - Du, Weiwei

AU - Inoue, Kohei

AU - Urahama, Kiichi

PY - 2005

Y1 - 2005

N2 - We present a method for extracting arbitrarily shaped clusters buried in uniform noise data. The popular k-means algorithm is firstly fuzzified with addition of entropic terms to the objective function of data partitioning problem. This fuzzy clustering is then kernelized for adapting to the arbitrary shape of clusters. Finally, the Euclidean distance in this kernelized fuzzy clustering is modified to a robust one for avoiding the influence of noisy background data. This robust kernel fuzzy clustering method is shown to outperform every its predecessor: fuzzified k-means, robust fuzzified k-means and kernel fuzzified k-means algorithms.

AB - We present a method for extracting arbitrarily shaped clusters buried in uniform noise data. The popular k-means algorithm is firstly fuzzified with addition of entropic terms to the objective function of data partitioning problem. This fuzzy clustering is then kernelized for adapting to the arbitrary shape of clusters. Finally, the Euclidean distance in this kernelized fuzzy clustering is modified to a robust one for avoiding the influence of noisy background data. This robust kernel fuzzy clustering method is shown to outperform every its predecessor: fuzzified k-means, robust fuzzified k-means and kernel fuzzified k-means algorithms.

UR - http://www.scopus.com/inward/record.url?scp=26944455171&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=26944455171&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:26944455171

VL - 3613

SP - 454

EP - 461

JO - Quaternary International

JF - Quaternary International

SN - 1040-6182

IS - PART I

ER -