Initialization method for multi-type prototype fuzzy clustering

Xinbo Gao; Zhong Xue; Jie Li; Weixin Xie

Initialization method for multi-type prototype fuzzy clustering

Xinbo Gao, Zhong Xue, Jie Li, Weixin Xie

Research output: Chapter in Book/Report/Conference proceeding › Chapter

Abstract

Fuzzy clustering is an important branch of unsupervised classification, and has been widely used in pattern recognition and image processing. However, most of existing fuzzy clustering algorithms are sensitive to initialization, and strongly depend on the number of clusters, which limits their applications. Moreover, it also needs to know the type and number of prototypes in advance in multi-type prototype fuzzy clustering. To overcome these limitations, a method for acquiring a priori knowledge about clustering prototype is proposed in this paper, which obtain better performance in initializing multi-type prototype fuzzy clustering.

Original language	English
Title of host publication	International Conference on Signal Processing Proceedings, ICSP
Place of Publication	Piscataway, NJ, United States
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1205-1208
Number of pages	4
Volume	2
State	Published - Dec 1 1998
Event	Proceedings of the 1998 4th International Conference on Signal Processing Proceedings, ICSP '98 - Beijing, China Duration: Oct 12 1998 → Oct 16 1998

Other

Other	Proceedings of the 1998 4th International Conference on Signal Processing Proceedings, ICSP '98
City	Beijing, China
Period	10/12/98 → 10/16/98

ASJC Scopus subject areas

Signal Processing

Cite this

Gao, X, Xue, Z, Li, J & Xie, W 1998, Initialization method for multi-type prototype fuzzy clustering. in International Conference on Signal Processing Proceedings, ICSP. vol. 2, Institute of Electrical and Electronics Engineers Inc., Piscataway, NJ, United States, pp. 1205-1208, Proceedings of the 1998 4th International Conference on Signal Processing Proceedings, ICSP '98, Beijing, China, 10/12/98.

@inbook{042da11158a1486996509619d3cd9d25,

title = "Initialization method for multi-type prototype fuzzy clustering",

abstract = "Fuzzy clustering is an important branch of unsupervised classification, and has been widely used in pattern recognition and image processing. However, most of existing fuzzy clustering algorithms are sensitive to initialization, and strongly depend on the number of clusters, which limits their applications. Moreover, it also needs to know the type and number of prototypes in advance in multi-type prototype fuzzy clustering. To overcome these limitations, a method for acquiring a priori knowledge about clustering prototype is proposed in this paper, which obtain better performance in initializing multi-type prototype fuzzy clustering.",

author = "Xinbo Gao and Zhong Xue and Jie Li and Weixin Xie",

year = "1998",

month = dec,

day = "1",

language = "English",

volume = "2",

pages = "1205--1208",

booktitle = "International Conference on Signal Processing Proceedings, ICSP",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "null ; Conference date: 12-10-1998 Through 16-10-1998",

}

TY - CHAP

T1 - Initialization method for multi-type prototype fuzzy clustering

AU - Gao, Xinbo

AU - Xue, Zhong

AU - Li, Jie

AU - Xie, Weixin

PY - 1998/12/1

Y1 - 1998/12/1

N2 - Fuzzy clustering is an important branch of unsupervised classification, and has been widely used in pattern recognition and image processing. However, most of existing fuzzy clustering algorithms are sensitive to initialization, and strongly depend on the number of clusters, which limits their applications. Moreover, it also needs to know the type and number of prototypes in advance in multi-type prototype fuzzy clustering. To overcome these limitations, a method for acquiring a priori knowledge about clustering prototype is proposed in this paper, which obtain better performance in initializing multi-type prototype fuzzy clustering.

AB - Fuzzy clustering is an important branch of unsupervised classification, and has been widely used in pattern recognition and image processing. However, most of existing fuzzy clustering algorithms are sensitive to initialization, and strongly depend on the number of clusters, which limits their applications. Moreover, it also needs to know the type and number of prototypes in advance in multi-type prototype fuzzy clustering. To overcome these limitations, a method for acquiring a priori knowledge about clustering prototype is proposed in this paper, which obtain better performance in initializing multi-type prototype fuzzy clustering.

UR - http://www.scopus.com/inward/record.url?scp=0032262317&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032262317&partnerID=8YFLogxK

M3 - Chapter

AN - SCOPUS:0032262317

VL - 2

SP - 1205

EP - 1208

BT - International Conference on Signal Processing Proceedings, ICSP

PB - Institute of Electrical and Electronics Engineers Inc.

CY - Piscataway, NJ, United States

Y2 - 12 October 1998 through 16 October 1998

ER -

Initialization method for multi-type prototype fuzzy clustering

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this