On hard and fuzzy c-means clustering with conditionally positive definite kernel

Yuchi Kanzawa, Yasunori Endo, Sadaaki Miyamoto

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

Abstract

In this paper, we investigate three types of c-means clustering algorithms with a conditionally positive definite kernel. One is based on hard c-means, and the others are based on standard and entropy-regularized fuzzy c-means. First, based on a conditionally positive definite kernel describing a squared Euclidean distance between data in the feature space, these algorithms are derived from revised optimization problems of the conventional kernel c-means. Next, based on the relationship between the positive definite kernel and conditionally positive definite kernel, the revised dissimilarity between a datum and a cluster center in the feature space is shown. Finally, it is shown that a conditionally positive definite kernel c-means algorithm and a kernel c-means algorithm with a positive definite kernel derived from the conditionally positive definite kernel are essentially identical to each other. An explicit mapping for a conditionally positive definite kernel is also described geometrically.

Original languageEnglish
Title of host publicationIEEE International Conference on Fuzzy Systems
Pages816-820
Number of pages5
DOIs
Publication statusPublished - 2011
Event2011 IEEE International Conference on Fuzzy Systems, FUZZ 2011 - Taipei
Duration: 2011 Jun 272011 Jun 30

Other

Other2011 IEEE International Conference on Fuzzy Systems, FUZZ 2011
CityTaipei
Period11/6/2711/6/30

Fingerprint

Clustering algorithms
Entropy

Keywords

  • Clustering
  • Conditionally positive definite kernel
  • Fuzzy c-means

ASJC Scopus subject areas

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

Cite this

Kanzawa, Y., Endo, Y., & Miyamoto, S. (2011). On hard and fuzzy c-means clustering with conditionally positive definite kernel. In IEEE International Conference on Fuzzy Systems (pp. 816-820). [6007431] https://doi.org/10.1109/FUZZY.2011.6007431

On hard and fuzzy c-means clustering with conditionally positive definite kernel. / Kanzawa, Yuchi; Endo, Yasunori; Miyamoto, Sadaaki.

IEEE International Conference on Fuzzy Systems. 2011. p. 816-820 6007431.

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

Kanzawa, Y, Endo, Y & Miyamoto, S 2011, On hard and fuzzy c-means clustering with conditionally positive definite kernel. in IEEE International Conference on Fuzzy Systems., 6007431, pp. 816-820, 2011 IEEE International Conference on Fuzzy Systems, FUZZ 2011, Taipei, 11/6/27. https://doi.org/10.1109/FUZZY.2011.6007431
Kanzawa Y, Endo Y, Miyamoto S. On hard and fuzzy c-means clustering with conditionally positive definite kernel. In IEEE International Conference on Fuzzy Systems. 2011. p. 816-820. 6007431 https://doi.org/10.1109/FUZZY.2011.6007431
Kanzawa, Yuchi ; Endo, Yasunori ; Miyamoto, Sadaaki. / On hard and fuzzy c-means clustering with conditionally positive definite kernel. IEEE International Conference on Fuzzy Systems. 2011. pp. 816-820
@inproceedings{a9f21ac5a57e4903830fcd46f97df177,
title = "On hard and fuzzy c-means clustering with conditionally positive definite kernel",
abstract = "In this paper, we investigate three types of c-means clustering algorithms with a conditionally positive definite kernel. One is based on hard c-means, and the others are based on standard and entropy-regularized fuzzy c-means. First, based on a conditionally positive definite kernel describing a squared Euclidean distance between data in the feature space, these algorithms are derived from revised optimization problems of the conventional kernel c-means. Next, based on the relationship between the positive definite kernel and conditionally positive definite kernel, the revised dissimilarity between a datum and a cluster center in the feature space is shown. Finally, it is shown that a conditionally positive definite kernel c-means algorithm and a kernel c-means algorithm with a positive definite kernel derived from the conditionally positive definite kernel are essentially identical to each other. An explicit mapping for a conditionally positive definite kernel is also described geometrically.",
keywords = "Clustering, Conditionally positive definite kernel, Fuzzy c-means",
author = "Yuchi Kanzawa and Yasunori Endo and Sadaaki Miyamoto",
year = "2011",
doi = "10.1109/FUZZY.2011.6007431",
language = "English",
isbn = "9781424473175",
pages = "816--820",
booktitle = "IEEE International Conference on Fuzzy Systems",

}

TY - GEN

T1 - On hard and fuzzy c-means clustering with conditionally positive definite kernel

AU - Kanzawa, Yuchi

AU - Endo, Yasunori

AU - Miyamoto, Sadaaki

PY - 2011

Y1 - 2011

N2 - In this paper, we investigate three types of c-means clustering algorithms with a conditionally positive definite kernel. One is based on hard c-means, and the others are based on standard and entropy-regularized fuzzy c-means. First, based on a conditionally positive definite kernel describing a squared Euclidean distance between data in the feature space, these algorithms are derived from revised optimization problems of the conventional kernel c-means. Next, based on the relationship between the positive definite kernel and conditionally positive definite kernel, the revised dissimilarity between a datum and a cluster center in the feature space is shown. Finally, it is shown that a conditionally positive definite kernel c-means algorithm and a kernel c-means algorithm with a positive definite kernel derived from the conditionally positive definite kernel are essentially identical to each other. An explicit mapping for a conditionally positive definite kernel is also described geometrically.

AB - In this paper, we investigate three types of c-means clustering algorithms with a conditionally positive definite kernel. One is based on hard c-means, and the others are based on standard and entropy-regularized fuzzy c-means. First, based on a conditionally positive definite kernel describing a squared Euclidean distance between data in the feature space, these algorithms are derived from revised optimization problems of the conventional kernel c-means. Next, based on the relationship between the positive definite kernel and conditionally positive definite kernel, the revised dissimilarity between a datum and a cluster center in the feature space is shown. Finally, it is shown that a conditionally positive definite kernel c-means algorithm and a kernel c-means algorithm with a positive definite kernel derived from the conditionally positive definite kernel are essentially identical to each other. An explicit mapping for a conditionally positive definite kernel is also described geometrically.

KW - Clustering

KW - Conditionally positive definite kernel

KW - Fuzzy c-means

UR - http://www.scopus.com/inward/record.url?scp=80053085614&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053085614&partnerID=8YFLogxK

U2 - 10.1109/FUZZY.2011.6007431

DO - 10.1109/FUZZY.2011.6007431

M3 - Conference contribution

AN - SCOPUS:80053085614

SN - 9781424473175

SP - 816

EP - 820

BT - IEEE International Conference on Fuzzy Systems

ER -