Global optimization in clustering using hyperbolic cross points

Y. K. Hu; Y. P. Hu

doi:10.1016/j.patcog.2006.11.005

Global optimization in clustering using hyperbolic cross points

Y. K. Hu, Y. P. Hu

Emeriti, Retired & In Memoriam (COSM)

Research output: Contribution to journal › Article › peer-review

6 Scopus citations

Abstract

Erich Novak and Klaus Ritter developed in 1996 a global optimization algorithm that uses hyperbolic cross points (HCPs). In this paper we develop a hybrid algorithm for clustering called CMHCP that uses a modified version of this HCP algorithm for global search and the alternating optimization for local search. The program has been tested extensively with very promising results and high efficiency. This provides a nice addition to the arsenal of global optimization in clustering. In the process, we also analyze the smoothness of some reformulated objective functions.

Original language	English
Pages (from-to)	1722-1733
Number of pages	12
Journal	Pattern Recognition
Volume	40
Issue number	6
DOIs	https://doi.org/10.1016/j.patcog.2006.11.005
State	Published - Jun 2007

Scopus Subject Areas

Software
Signal Processing
Computer Vision and Pattern Recognition
Artificial Intelligence

Keywords

Clustering
Fuzzy c-means
Genetic algorithms
Global optimization
Hard c-means
Hyperbolic cross points

Access to Document

10.1016/j.patcog.2006.11.005

Cite this

@article{591dd3220c5142f5be4898e3831158e4,

title = "Global optimization in clustering using hyperbolic cross points",

abstract = "Erich Novak and Klaus Ritter developed in 1996 a global optimization algorithm that uses hyperbolic cross points (HCPs). In this paper we develop a hybrid algorithm for clustering called CMHCP that uses a modified version of this HCP algorithm for global search and the alternating optimization for local search. The program has been tested extensively with very promising results and high efficiency. This provides a nice addition to the arsenal of global optimization in clustering. In the process, we also analyze the smoothness of some reformulated objective functions.",

keywords = "Clustering, Fuzzy c-means, Genetic algorithms, Global optimization, Hard c-means, Hyperbolic cross points",

author = "Hu, {Y. K.} and Hu, {Y. P.}",

year = "2007",

month = jun,

doi = "10.1016/j.patcog.2006.11.005",

language = "English",

volume = "40",

pages = "1722--1733",

journal = "Pattern Recognition",

issn = "0031-3203",

publisher = "Elsevier Ltd",

number = "6",

}

TY - JOUR

T1 - Global optimization in clustering using hyperbolic cross points

AU - Hu, Y. K.

AU - Hu, Y. P.

PY - 2007/6

Y1 - 2007/6

N2 - Erich Novak and Klaus Ritter developed in 1996 a global optimization algorithm that uses hyperbolic cross points (HCPs). In this paper we develop a hybrid algorithm for clustering called CMHCP that uses a modified version of this HCP algorithm for global search and the alternating optimization for local search. The program has been tested extensively with very promising results and high efficiency. This provides a nice addition to the arsenal of global optimization in clustering. In the process, we also analyze the smoothness of some reformulated objective functions.

AB - Erich Novak and Klaus Ritter developed in 1996 a global optimization algorithm that uses hyperbolic cross points (HCPs). In this paper we develop a hybrid algorithm for clustering called CMHCP that uses a modified version of this HCP algorithm for global search and the alternating optimization for local search. The program has been tested extensively with very promising results and high efficiency. This provides a nice addition to the arsenal of global optimization in clustering. In the process, we also analyze the smoothness of some reformulated objective functions.

KW - Clustering

KW - Fuzzy c-means

KW - Genetic algorithms

KW - Global optimization

KW - Hard c-means

KW - Hyperbolic cross points

UR - http://www.scopus.com/inward/record.url?scp=33947182396&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2006.11.005

DO - 10.1016/j.patcog.2006.11.005

M3 - Article

AN - SCOPUS:33947182396

SN - 0031-3203

VL - 40

SP - 1722

EP - 1733

JO - Pattern Recognition

JF - Pattern Recognition

IS - 6

ER -

Global optimization in clustering using hyperbolic cross points

Abstract

Scopus Subject Areas

Keywords

Access to Document

Other files and links

Fingerprint

Cite this