A maximizing model of spherical Bezdek-type fuzzy multi-medoids clustering

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

This paper proposes three modifications for the maximizing model of spherical Bezdek-type fuzzy c-means clustering (msbFCM). First, we use multi-medoids instead of centroids (msbFMMdd), which is similar to modifying fuzzy c-means to fuzzy multi-medoids. Second, we kernelize msbFMMdd (K-msbFMMdd). msbFMMdd can only be applied to objects in the first quadrant of the unit hypersphere, whereas its kernelized form can be applied to a wider class of objects. The third modification is a spectral clustering approach to K-msbFMMdd using a certain assumption. This approach improves the local convergence problem in the original algorithm. Numerical examples demonstrate that the proposed methods can produce good results for clusters with nonlinear borders when an adequate parameter value is selected.

Original languageEnglish
Pages (from-to)738-746
Number of pages9
JournalJournal of Advanced Computational Intelligence and Intelligent Informatics
Volume19
Issue number6
Publication statusPublished - 2015

Keywords

  • Kernelization
  • Multi-medoids
  • Spectral clustering
  • Spherical clustering

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction

Cite this

@article{31ec96bc393c40adb1996d624243dec1,
title = "A maximizing model of spherical Bezdek-type fuzzy multi-medoids clustering",
abstract = "This paper proposes three modifications for the maximizing model of spherical Bezdek-type fuzzy c-means clustering (msbFCM). First, we use multi-medoids instead of centroids (msbFMMdd), which is similar to modifying fuzzy c-means to fuzzy multi-medoids. Second, we kernelize msbFMMdd (K-msbFMMdd). msbFMMdd can only be applied to objects in the first quadrant of the unit hypersphere, whereas its kernelized form can be applied to a wider class of objects. The third modification is a spectral clustering approach to K-msbFMMdd using a certain assumption. This approach improves the local convergence problem in the original algorithm. Numerical examples demonstrate that the proposed methods can produce good results for clusters with nonlinear borders when an adequate parameter value is selected.",
keywords = "Kernelization, Multi-medoids, Spectral clustering, Spherical clustering",
author = "Yuchi Kanzawa",
year = "2015",
language = "English",
volume = "19",
pages = "738--746",
journal = "Journal of Advanced Computational Intelligence and Intelligent Informatics",
issn = "1343-0130",
publisher = "Fuji Technology Press",
number = "6",

}

TY - JOUR

T1 - A maximizing model of spherical Bezdek-type fuzzy multi-medoids clustering

AU - Kanzawa, Yuchi

PY - 2015

Y1 - 2015

N2 - This paper proposes three modifications for the maximizing model of spherical Bezdek-type fuzzy c-means clustering (msbFCM). First, we use multi-medoids instead of centroids (msbFMMdd), which is similar to modifying fuzzy c-means to fuzzy multi-medoids. Second, we kernelize msbFMMdd (K-msbFMMdd). msbFMMdd can only be applied to objects in the first quadrant of the unit hypersphere, whereas its kernelized form can be applied to a wider class of objects. The third modification is a spectral clustering approach to K-msbFMMdd using a certain assumption. This approach improves the local convergence problem in the original algorithm. Numerical examples demonstrate that the proposed methods can produce good results for clusters with nonlinear borders when an adequate parameter value is selected.

AB - This paper proposes three modifications for the maximizing model of spherical Bezdek-type fuzzy c-means clustering (msbFCM). First, we use multi-medoids instead of centroids (msbFMMdd), which is similar to modifying fuzzy c-means to fuzzy multi-medoids. Second, we kernelize msbFMMdd (K-msbFMMdd). msbFMMdd can only be applied to objects in the first quadrant of the unit hypersphere, whereas its kernelized form can be applied to a wider class of objects. The third modification is a spectral clustering approach to K-msbFMMdd using a certain assumption. This approach improves the local convergence problem in the original algorithm. Numerical examples demonstrate that the proposed methods can produce good results for clusters with nonlinear borders when an adequate parameter value is selected.

KW - Kernelization

KW - Multi-medoids

KW - Spectral clustering

KW - Spherical clustering

UR - http://www.scopus.com/inward/record.url?scp=84954320199&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84954320199&partnerID=8YFLogxK

M3 - Article

VL - 19

SP - 738

EP - 746

JO - Journal of Advanced Computational Intelligence and Intelligent Informatics

JF - Journal of Advanced Computational Intelligence and Intelligent Informatics

SN - 1343-0130

IS - 6

ER -