A unified approach to c-means clustering models

László Szilágyi, Sándor M. Szilágyi, Z. Benyó

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

In order to improve the accuracy, robustness, and computational load of c-means clustering models, a series of hybrid solutions have been proposed. Mixtures of fuzzy (FCM) and possibilistic c-means (PCM) clustering generally attempted to avoid the noise sensitivity of the former and the coincident clusters of the latter. On the other hand, mixtures of fuzzy and hard c-means (HCM) have been proposed to speed up fuzzy clustering without losing the quality of its partitions. In this paper, a novel hybrid c-means algorithmic scheme is proposed that unifies the objective functions of all three conventional clustering models. The strength of each component within the mixture is controlled by two tradeoff parameters. The optimization of the proposed objective function is achieved using the alternating optimization derived from zero gradient conditions and Lagrange multipliers. The novel hybrid's behavior is evaluated in terms of classification accuracy, cluster validity and execution time, using the IRIS data set. Suitably chosen tradeoff parameters enable the proposed algorithm to achieve better accuracy than previous models, while performing less computations.

Original languageEnglish
Title of host publicationIEEE International Conference on Fuzzy Systems
Pages456-461
Number of pages6
DOIs
Publication statusPublished - 2009
Event2009 IEEE International Conference on Fuzzy Systems - Jeju Island, Korea, Republic of
Duration: Aug 20 2009Aug 24 2009

Other

Other2009 IEEE International Conference on Fuzzy Systems
CountryKorea, Republic of
CityJeju Island
Period8/20/098/24/09

Fingerprint

Clustering
Fuzzy clustering
Objective function
Lagrange multipliers
Trade-offs
Cluster Validity
Optimization
Coincident
Fuzzy Clustering
Model
Execution Time
Speedup
Partition
Gradient
Robustness
Series
Zero

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Applied Mathematics
  • Theoretical Computer Science

Cite this

Szilágyi, L., Szilágyi, S. M., & Benyó, Z. (2009). A unified approach to c-means clustering models. In IEEE International Conference on Fuzzy Systems (pp. 456-461). [5277132] https://doi.org/10.1109/FUZZY.2009.5277132

A unified approach to c-means clustering models. / Szilágyi, László; Szilágyi, Sándor M.; Benyó, Z.

IEEE International Conference on Fuzzy Systems. 2009. p. 456-461 5277132.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Szilágyi, L, Szilágyi, SM & Benyó, Z 2009, A unified approach to c-means clustering models. in IEEE International Conference on Fuzzy Systems., 5277132, pp. 456-461, 2009 IEEE International Conference on Fuzzy Systems, Jeju Island, Korea, Republic of, 8/20/09. https://doi.org/10.1109/FUZZY.2009.5277132
Szilágyi L, Szilágyi SM, Benyó Z. A unified approach to c-means clustering models. In IEEE International Conference on Fuzzy Systems. 2009. p. 456-461. 5277132 https://doi.org/10.1109/FUZZY.2009.5277132
Szilágyi, László ; Szilágyi, Sándor M. ; Benyó, Z. / A unified approach to c-means clustering models. IEEE International Conference on Fuzzy Systems. 2009. pp. 456-461
@inproceedings{eb22a9e12cc548b7aeec7f765e2645d2,
title = "A unified approach to c-means clustering models",
abstract = "In order to improve the accuracy, robustness, and computational load of c-means clustering models, a series of hybrid solutions have been proposed. Mixtures of fuzzy (FCM) and possibilistic c-means (PCM) clustering generally attempted to avoid the noise sensitivity of the former and the coincident clusters of the latter. On the other hand, mixtures of fuzzy and hard c-means (HCM) have been proposed to speed up fuzzy clustering without losing the quality of its partitions. In this paper, a novel hybrid c-means algorithmic scheme is proposed that unifies the objective functions of all three conventional clustering models. The strength of each component within the mixture is controlled by two tradeoff parameters. The optimization of the proposed objective function is achieved using the alternating optimization derived from zero gradient conditions and Lagrange multipliers. The novel hybrid's behavior is evaluated in terms of classification accuracy, cluster validity and execution time, using the IRIS data set. Suitably chosen tradeoff parameters enable the proposed algorithm to achieve better accuracy than previous models, while performing less computations.",
author = "L{\'a}szl{\'o} Szil{\'a}gyi and Szil{\'a}gyi, {S{\'a}ndor M.} and Z. Beny{\'o}",
year = "2009",
doi = "10.1109/FUZZY.2009.5277132",
language = "English",
isbn = "9781424435975",
pages = "456--461",
booktitle = "IEEE International Conference on Fuzzy Systems",

}

TY - GEN

T1 - A unified approach to c-means clustering models

AU - Szilágyi, László

AU - Szilágyi, Sándor M.

AU - Benyó, Z.

PY - 2009

Y1 - 2009

N2 - In order to improve the accuracy, robustness, and computational load of c-means clustering models, a series of hybrid solutions have been proposed. Mixtures of fuzzy (FCM) and possibilistic c-means (PCM) clustering generally attempted to avoid the noise sensitivity of the former and the coincident clusters of the latter. On the other hand, mixtures of fuzzy and hard c-means (HCM) have been proposed to speed up fuzzy clustering without losing the quality of its partitions. In this paper, a novel hybrid c-means algorithmic scheme is proposed that unifies the objective functions of all three conventional clustering models. The strength of each component within the mixture is controlled by two tradeoff parameters. The optimization of the proposed objective function is achieved using the alternating optimization derived from zero gradient conditions and Lagrange multipliers. The novel hybrid's behavior is evaluated in terms of classification accuracy, cluster validity and execution time, using the IRIS data set. Suitably chosen tradeoff parameters enable the proposed algorithm to achieve better accuracy than previous models, while performing less computations.

AB - In order to improve the accuracy, robustness, and computational load of c-means clustering models, a series of hybrid solutions have been proposed. Mixtures of fuzzy (FCM) and possibilistic c-means (PCM) clustering generally attempted to avoid the noise sensitivity of the former and the coincident clusters of the latter. On the other hand, mixtures of fuzzy and hard c-means (HCM) have been proposed to speed up fuzzy clustering without losing the quality of its partitions. In this paper, a novel hybrid c-means algorithmic scheme is proposed that unifies the objective functions of all three conventional clustering models. The strength of each component within the mixture is controlled by two tradeoff parameters. The optimization of the proposed objective function is achieved using the alternating optimization derived from zero gradient conditions and Lagrange multipliers. The novel hybrid's behavior is evaluated in terms of classification accuracy, cluster validity and execution time, using the IRIS data set. Suitably chosen tradeoff parameters enable the proposed algorithm to achieve better accuracy than previous models, while performing less computations.

UR - http://www.scopus.com/inward/record.url?scp=71249121037&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=71249121037&partnerID=8YFLogxK

U2 - 10.1109/FUZZY.2009.5277132

DO - 10.1109/FUZZY.2009.5277132

M3 - Conference contribution

AN - SCOPUS:71249121037

SN - 9781424435975

SP - 456

EP - 461

BT - IEEE International Conference on Fuzzy Systems

ER -