A Self-tuning Possibilistic c-Means Clustering Algorithm

László Szilágyi; Szidónia Lefkovits; Zsolt Levente Kucsván

doi:10.1007/978-3-030-00202-2_21

A Self-tuning Possibilistic c-Means Clustering Algorithm

László Szilágyi^*
, Szidónia Lefkovits
, Zsolt Levente Kucsván

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

1 Citation (Scopus)

Abstract

Most c-means clustering models have serious difficulties when facing clusters of different sizes and severely outlier data. The possibilistic c-means (PCM) algorithm can handle both problems to some extent. However, its recommended initialization using a terminal partition produced by the probabilistic fuzzy c-means does not work when severe outliers are present. This paper proposes a possibilistic c-means clustering model that uses only three parameters independently of the number of clusters, which is able to more robustly handle the above mentioned obstacles. Numerical evaluation involving synthetic and standard test data sets prove the advantages of the proposed clustering model.

Original language	English
Title of host publication	Modeling Decisions for Artificial Intelligence
Subtitle of host publication	15th International Conference, MDAI 2018, Mallorca, Spain, October 15–18, 2018, Proceedings
Editors	Vicenc Torra, Yasuo Narukawa, Manuel González-Hidalgo, Isabel Aguilo
Place of Publication	Cham
Publisher	Springer
Pages	255-266
Number of pages	12
ISBN (Electronic)	978-3-030-00202-2
ISBN (Print)	978-3-030-00201-5
DOIs	https://doi.org/10.1007/978-3-030-00202-2_21
Publication status	Published - 2018
Externally published	Yes
Event	15th International Conference on Modeling Decisions for Artificial Intelligence, MDAI 2018 - Palma de Mallorce, Spain Duration: 15 Oct 2018 → 18 Oct 2018 Conference number: 15

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	11144
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	15th International Conference on Modeling Decisions for Artificial Intelligence, MDAI 2018
Abbreviated title	MDAI 2018
Country/Territory	Spain
City	Palma de Mallorce
Period	15/10/18 → 18/10/18

Keywords

Cluster size sensitivity
Fuzzy c-means clustering
Outlier data
Possibilistic c-means clustering
n/a OA procedure

Access to Document

10.1007/978-3-030-00202-2_21

Cite this

Szilágyi, L., Lefkovits, S., & Kucsván, Z. L. (2018). A Self-tuning Possibilistic c-Means Clustering Algorithm. In V. Torra, Y. Narukawa, M. González-Hidalgo, & I. Aguilo (Eds.), Modeling Decisions for Artificial Intelligence: 15th International Conference, MDAI 2018, Mallorca, Spain, October 15–18, 2018, Proceedings (pp. 255-266). (Lecture Notes in Computer Science; Vol. 11144). Springer. https://doi.org/10.1007/978-3-030-00202-2_21

Szilágyi, László ; Lefkovits, Szidónia ; Kucsván, Zsolt Levente. / A Self-tuning Possibilistic c-Means Clustering Algorithm. Modeling Decisions for Artificial Intelligence: 15th International Conference, MDAI 2018, Mallorca, Spain, October 15–18, 2018, Proceedings. editor / Vicenc Torra ; Yasuo Narukawa ; Manuel González-Hidalgo ; Isabel Aguilo. Cham : Springer, 2018. pp. 255-266 (Lecture Notes in Computer Science).

@inproceedings{16d358fec23c46e795e4ce821e57f41d,

title = "A Self-tuning Possibilistic c-Means Clustering Algorithm",

abstract = "Most c-means clustering models have serious difficulties when facing clusters of different sizes and severely outlier data. The possibilistic c-means (PCM) algorithm can handle both problems to some extent. However, its recommended initialization using a terminal partition produced by the probabilistic fuzzy c-means does not work when severe outliers are present. This paper proposes a possibilistic c-means clustering model that uses only three parameters independently of the number of clusters, which is able to more robustly handle the above mentioned obstacles. Numerical evaluation involving synthetic and standard test data sets prove the advantages of the proposed clustering model.",

keywords = "Cluster size sensitivity, Fuzzy c-means clustering, Outlier data, Possibilistic c-means clustering, n/a OA procedure",

author = "L{\'a}szl{\'o} Szil{\'a}gyi and Szid{\'o}nia Lefkovits and Kucsv{\'a}n, \{Zsolt Levente\}",

note = "Publisher Copyright: {\textcopyright} Springer Nature Switzerland AG 2018.; 15th International Conference on Modeling Decisions for Artificial Intelligence, MDAI 2018, MDAI 2018 ; Conference date: 15-10-2018 Through 18-10-2018",

year = "2018",

doi = "10.1007/978-3-030-00202-2\_21",

language = "English",

isbn = "978-3-030-00201-5",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "255--266",

editor = "Vicenc Torra and Yasuo Narukawa and Manuel Gonz{\'a}lez-Hidalgo and Isabel Aguilo",

booktitle = "Modeling Decisions for Artificial Intelligence",

address = "Germany",

}

Szilágyi, L, Lefkovits, S & Kucsván, ZL 2018, A Self-tuning Possibilistic c-Means Clustering Algorithm. in V Torra, Y Narukawa, M González-Hidalgo & I Aguilo (eds), Modeling Decisions for Artificial Intelligence: 15th International Conference, MDAI 2018, Mallorca, Spain, October 15–18, 2018, Proceedings. Lecture Notes in Computer Science, vol. 11144, Springer, Cham, pp. 255-266, 15th International Conference on Modeling Decisions for Artificial Intelligence, MDAI 2018, Palma de Mallorce, Spain, 15/10/18. https://doi.org/10.1007/978-3-030-00202-2_21

A Self-tuning Possibilistic c-Means Clustering Algorithm. / Szilágyi, László; Lefkovits, Szidónia; Kucsván, Zsolt Levente.
Modeling Decisions for Artificial Intelligence: 15th International Conference, MDAI 2018, Mallorca, Spain, October 15–18, 2018, Proceedings. ed. / Vicenc Torra; Yasuo Narukawa; Manuel González-Hidalgo; Isabel Aguilo. Cham: Springer, 2018. p. 255-266 (Lecture Notes in Computer Science; Vol. 11144).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - A Self-tuning Possibilistic c-Means Clustering Algorithm

AU - Szilágyi, László

AU - Lefkovits, Szidónia

AU - Kucsván, Zsolt Levente

N1 - Conference code: 15

PY - 2018

Y1 - 2018

N2 - Most c-means clustering models have serious difficulties when facing clusters of different sizes and severely outlier data. The possibilistic c-means (PCM) algorithm can handle both problems to some extent. However, its recommended initialization using a terminal partition produced by the probabilistic fuzzy c-means does not work when severe outliers are present. This paper proposes a possibilistic c-means clustering model that uses only three parameters independently of the number of clusters, which is able to more robustly handle the above mentioned obstacles. Numerical evaluation involving synthetic and standard test data sets prove the advantages of the proposed clustering model.

AB - Most c-means clustering models have serious difficulties when facing clusters of different sizes and severely outlier data. The possibilistic c-means (PCM) algorithm can handle both problems to some extent. However, its recommended initialization using a terminal partition produced by the probabilistic fuzzy c-means does not work when severe outliers are present. This paper proposes a possibilistic c-means clustering model that uses only three parameters independently of the number of clusters, which is able to more robustly handle the above mentioned obstacles. Numerical evaluation involving synthetic and standard test data sets prove the advantages of the proposed clustering model.

KW - Cluster size sensitivity

KW - Fuzzy c-means clustering

KW - Outlier data

KW - Possibilistic c-means clustering

KW - n/a OA procedure

UR - https://www.scopus.com/pages/publications/85055702704

U2 - 10.1007/978-3-030-00202-2_21

DO - 10.1007/978-3-030-00202-2_21

M3 - Conference contribution

AN - SCOPUS:85055702704

SN - 978-3-030-00201-5

T3 - Lecture Notes in Computer Science

SP - 255

EP - 266

BT - Modeling Decisions for Artificial Intelligence

A2 - Torra, Vicenc

A2 - Narukawa, Yasuo

A2 - González-Hidalgo, Manuel

A2 - Aguilo, Isabel

PB - Springer

CY - Cham

T2 - 15th International Conference on Modeling Decisions for Artificial Intelligence, MDAI 2018

Y2 - 15 October 2018 through 18 October 2018

ER -

Szilágyi L, Lefkovits S, Kucsván ZL. A Self-tuning Possibilistic c-Means Clustering Algorithm. In Torra V, Narukawa Y, González-Hidalgo M, Aguilo I, editors, Modeling Decisions for Artificial Intelligence: 15th International Conference, MDAI 2018, Mallorca, Spain, October 15–18, 2018, Proceedings. Cham: Springer. 2018. p. 255-266. (Lecture Notes in Computer Science). doi: 10.1007/978-3-030-00202-2_21

A Self-tuning Possibilistic c-Means Clustering Algorithm

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this