Q-divergence-based relational fuzzy C-means clustering

Research output: Contribution to journalArticle

Abstract

In this paper, a clustering algorithm for relational data based on q-divergence between memberships and variables that control cluster sizes is proposed. A conventional method for vectorial data is first presented for interpretation as the regularization of another conventional method with q-divergence. With this interpretation, a clustering algorithm for relational data, based on q-divergence, is then derived from an optimization problem built by regularizing the conventional method with q-divergence. A theoretical discussion reveals the property of the proposed method. Numerical results are presented that substantiate this property and show that the proposed method outperforms two conventional methods in terms of accuracy.

Original languageEnglish
Pages (from-to)34-43
Number of pages10
JournalJournal of Advanced Computational Intelligence and Intelligent Informatics
Volume22
Issue number1
DOIs
Publication statusPublished - 2018 Jan 1

Fingerprint

Clustering algorithms

Keywords

  • Fuzzy clustering
  • Q-divergence
  • Relational data

ASJC Scopus subject areas

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

Cite this

Q-divergence-based relational fuzzy C-means clustering. / Kanzawa, Yuchi.

In: Journal of Advanced Computational Intelligence and Intelligent Informatics, Vol. 22, No. 1, 01.01.2018, p. 34-43.

Research output: Contribution to journalArticle

@article{da4f0f3ba6af4e5994e456ac6a3e19fb,
title = "Q-divergence-based relational fuzzy C-means clustering",
abstract = "In this paper, a clustering algorithm for relational data based on q-divergence between memberships and variables that control cluster sizes is proposed. A conventional method for vectorial data is first presented for interpretation as the regularization of another conventional method with q-divergence. With this interpretation, a clustering algorithm for relational data, based on q-divergence, is then derived from an optimization problem built by regularizing the conventional method with q-divergence. A theoretical discussion reveals the property of the proposed method. Numerical results are presented that substantiate this property and show that the proposed method outperforms two conventional methods in terms of accuracy.",
keywords = "Fuzzy clustering, Q-divergence, Relational data",
author = "Yuchi Kanzawa",
year = "2018",
month = "1",
day = "1",
doi = "10.20965/jaciii.2018.p0034",
language = "English",
volume = "22",
pages = "34--43",
journal = "Journal of Advanced Computational Intelligence and Intelligent Informatics",
issn = "1343-0130",
publisher = "Fuji Technology Press",
number = "1",

}

TY - JOUR

T1 - Q-divergence-based relational fuzzy C-means clustering

AU - Kanzawa, Yuchi

PY - 2018/1/1

Y1 - 2018/1/1

N2 - In this paper, a clustering algorithm for relational data based on q-divergence between memberships and variables that control cluster sizes is proposed. A conventional method for vectorial data is first presented for interpretation as the regularization of another conventional method with q-divergence. With this interpretation, a clustering algorithm for relational data, based on q-divergence, is then derived from an optimization problem built by regularizing the conventional method with q-divergence. A theoretical discussion reveals the property of the proposed method. Numerical results are presented that substantiate this property and show that the proposed method outperforms two conventional methods in terms of accuracy.

AB - In this paper, a clustering algorithm for relational data based on q-divergence between memberships and variables that control cluster sizes is proposed. A conventional method for vectorial data is first presented for interpretation as the regularization of another conventional method with q-divergence. With this interpretation, a clustering algorithm for relational data, based on q-divergence, is then derived from an optimization problem built by regularizing the conventional method with q-divergence. A theoretical discussion reveals the property of the proposed method. Numerical results are presented that substantiate this property and show that the proposed method outperforms two conventional methods in terms of accuracy.

KW - Fuzzy clustering

KW - Q-divergence

KW - Relational data

UR - http://www.scopus.com/inward/record.url?scp=85041111577&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041111577&partnerID=8YFLogxK

U2 - 10.20965/jaciii.2018.p0034

DO - 10.20965/jaciii.2018.p0034

M3 - Article

AN - SCOPUS:85041111577

VL - 22

SP - 34

EP - 43

JO - Journal of Advanced Computational Intelligence and Intelligent Informatics

JF - Journal of Advanced Computational Intelligence and Intelligent Informatics

SN - 1343-0130

IS - 1

ER -