Random walk distances in data clustering and applications

Sijia Liu; Anastasios Matzavinos; Sunder Sethuraman

doi:10.1007/s11634-013-0125-7

Random walk distances in data clustering and applications

Sijia Liu
, Anastasios Matzavinos
, Sunder Sethuraman

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

6 Scopus citations

Abstract

In this paper, we develop a family of data clustering algorithms that combine the strengths of existing spectral approaches to clustering with various desirable properties of fuzzy methods. In particular, we show that the developed method "Fuzzy-RW," outperforms other frequently used algorithms in data sets with different geometries. As applications, we discuss data clustering of biological and face recognition benchmarks such as the IRIS and YALE face data sets.

Original language	English (US)
Pages (from-to)	83-108
Number of pages	26
Journal	Advances in Data Analysis and Classification
Volume	7
Issue number	1
DOIs	https://doi.org/10.1007/s11634-013-0125-7
State	Published - Mar 2013
Externally published	Yes

Keywords

Face identification
Fuzzy clustering methods
Graph Laplacian
Mahalanobis
Random walks
Spectral clustering

ASJC Scopus subject areas

Computer Science Applications
Applied Mathematics

Access to Document

10.1007/s11634-013-0125-7

Cite this

@article{8bd3ce05affa420bb474f9c5f7500cac,

title = "Random walk distances in data clustering and applications",

abstract = "In this paper, we develop a family of data clustering algorithms that combine the strengths of existing spectral approaches to clustering with various desirable properties of fuzzy methods. In particular, we show that the developed method {"}Fuzzy-RW,{"} outperforms other frequently used algorithms in data sets with different geometries. As applications, we discuss data clustering of biological and face recognition benchmarks such as the IRIS and YALE face data sets.",

keywords = "Face identification, Fuzzy clustering methods, Graph Laplacian, Mahalanobis, Random walks, Spectral clustering",

author = "Sijia Liu and Anastasios Matzavinos and Sunder Sethuraman",

note = "Funding Information: Acknowledgments The research of SL has been supported in part by an Alberta Wolfe Research Fellowship from the Iowa State University Mathematics department. The research of AM has been supported in part by the Mathematical Biosciences Institute and the National Science Foundation under Grant DMS 0931642. The research of SS is supported in part by NSF DMS-1159026.",

year = "2013",

month = mar,

doi = "10.1007/s11634-013-0125-7",

language = "English (US)",

volume = "7",

pages = "83--108",

journal = "Advances in Data Analysis and Classification",

issn = "1862-5347",

publisher = "Springer Science and Business Media Deutschland GmbH",

number = "1",

}

TY - JOUR

T1 - Random walk distances in data clustering and applications

AU - Liu, Sijia

AU - Matzavinos, Anastasios

AU - Sethuraman, Sunder

N1 - Funding Information: Acknowledgments The research of SL has been supported in part by an Alberta Wolfe Research Fellowship from the Iowa State University Mathematics department. The research of AM has been supported in part by the Mathematical Biosciences Institute and the National Science Foundation under Grant DMS 0931642. The research of SS is supported in part by NSF DMS-1159026.

PY - 2013/3

Y1 - 2013/3

N2 - In this paper, we develop a family of data clustering algorithms that combine the strengths of existing spectral approaches to clustering with various desirable properties of fuzzy methods. In particular, we show that the developed method "Fuzzy-RW," outperforms other frequently used algorithms in data sets with different geometries. As applications, we discuss data clustering of biological and face recognition benchmarks such as the IRIS and YALE face data sets.

AB - In this paper, we develop a family of data clustering algorithms that combine the strengths of existing spectral approaches to clustering with various desirable properties of fuzzy methods. In particular, we show that the developed method "Fuzzy-RW," outperforms other frequently used algorithms in data sets with different geometries. As applications, we discuss data clustering of biological and face recognition benchmarks such as the IRIS and YALE face data sets.

KW - Face identification

KW - Fuzzy clustering methods

KW - Graph Laplacian

KW - Mahalanobis

KW - Random walks

KW - Spectral clustering

UR - https://www.scopus.com/pages/publications/84875380640

UR - https://www.scopus.com/pages/publications/84875380640#tab=citedBy

U2 - 10.1007/s11634-013-0125-7

DO - 10.1007/s11634-013-0125-7

M3 - Article

AN - SCOPUS:84875380640

SN - 1862-5347

VL - 7

SP - 83

EP - 108

JO - Advances in Data Analysis and Classification

JF - Advances in Data Analysis and Classification

IS - 1

ER -

Random walk distances in data clustering and applications

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this