Ensemble clustering based on weighted co-association matrices

Standard

Ensemble clustering based on weighted co-association matrices : Error bound and convergence properties. / Berikov, Vladimir; Pestunov, Igor.

In: Pattern Recognition, Vol. 63, 01.03.2017, p. 427-436.

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

BibTeX

@article{b36f5607cf5e4ceab7c18f29db1c9aa8,

title = "Ensemble clustering based on weighted co-association matrices: Error bound and convergence properties",

abstract = "We consider an approach to ensemble clustering based on weighted co-association matrices, where the weights are determined with some evaluation functions. Using a latent variable model of clustering ensemble, it is proved that, under certain assumptions, the clustering quality is improved with an increase in the ensemble size and the expectation of evaluation function. Analytical dependencies between the ensemble size and quality estimates are derived. Theoretical results are supported with numerical examples using Monte-Carlo modeling and segmentation of a real hyperspectral image under presence of noise channels.",

keywords = "Cluster validity index, Co-association matrix, Ensemble size, Error bound, Hyperspectral image segmentation, Latent variable model, Weighted clustering ensemble",

author = "Vladimir Berikov and Igor Pestunov",

note = "Publisher Copyright: {\textcopyright} 2016 Elsevier Ltd",

year = "2017",

month = mar,

day = "1",

doi = "10.1016/j.patcog.2016.10.017",

language = "English",

volume = "63",

pages = "427--436",

journal = " Pattern Recognition",

issn = "0031-3203",

publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - Ensemble clustering based on weighted co-association matrices

T2 - Error bound and convergence properties

AU - Berikov, Vladimir

AU - Pestunov, Igor

PY - 2017/3/1

Y1 - 2017/3/1

N2 - We consider an approach to ensemble clustering based on weighted co-association matrices, where the weights are determined with some evaluation functions. Using a latent variable model of clustering ensemble, it is proved that, under certain assumptions, the clustering quality is improved with an increase in the ensemble size and the expectation of evaluation function. Analytical dependencies between the ensemble size and quality estimates are derived. Theoretical results are supported with numerical examples using Monte-Carlo modeling and segmentation of a real hyperspectral image under presence of noise channels.

AB - We consider an approach to ensemble clustering based on weighted co-association matrices, where the weights are determined with some evaluation functions. Using a latent variable model of clustering ensemble, it is proved that, under certain assumptions, the clustering quality is improved with an increase in the ensemble size and the expectation of evaluation function. Analytical dependencies between the ensemble size and quality estimates are derived. Theoretical results are supported with numerical examples using Monte-Carlo modeling and segmentation of a real hyperspectral image under presence of noise channels.

KW - Cluster validity index

KW - Co-association matrix

KW - Ensemble size

KW - Error bound

KW - Hyperspectral image segmentation

KW - Latent variable model

KW - Weighted clustering ensemble

UR - http://www.scopus.com/inward/record.url?scp=84998679702&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2016.10.017

DO - 10.1016/j.patcog.2016.10.017

M3 - Article

AN - SCOPUS:84998679702

VL - 63

SP - 427

EP - 436

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

ER -

ID: 10318627

Ensemble clustering based on weighted co-association matrices: Error bound and convergence properties

Standard

Harvard

APA

Vancouver

Author

BibTeX

RIS