Probabilistic distance clustering: Algorithm and applications

C. Iyigun; A. Ben-Israel

Probabilistic distance clustering: Algorithm and applications

C. Iyigun, A. Ben-Israel

Rutgers Business School, Management & Information Systems

Rutgers, The State University

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

Abstract

The probabilistic distance clustering method of the authors [2, 8], assumes the cluster membership probabilities given in terms of the distances of the data points from the cluster centers, and the cluster sizes. A resulting extremal principle is then used to update the cluster centers (as convex combinations of the data points), and the cluster sizes (if not given.) Progress is monitored by the joint distance function (JDF), a weighted harmonic mean of the above distances, that approximates the data by capturing the data points in its lowest contours. The method is described, and applied to clustering, location problems, and mixtures of distributions, where it is a viable alternative to the Expectation-Maximization (EM) method. The JDF also helps to determine the "right" number of clusters for a given data set.

Original language	American English
Title of host publication	Clustering Challenges in Biological Networks
Pages	29-52
Number of pages	24
State	Published - 2013
Event	DIMACS Workshop on Clustering Problems in Biological Networks 2009 - Piscataway, NJ, United States Duration: May 9 2006 → May 11 2006

Publication series

Name	Clustering Challenges in Biological Networks

Other

Other	DIMACS Workshop on Clustering Problems in Biological Networks 2009
Country/Territory	United States
City	Piscataway, NJ
Period	5/9/06 → 5/11/06

ASJC Scopus subject areas

Nuclear and High Energy Physics

Cite this

@inproceedings{42aee847268d41f7a585fdd911c286cf,

title = "Probabilistic distance clustering: Algorithm and applications",

abstract = "The probabilistic distance clustering method of the authors [2, 8], assumes the cluster membership probabilities given in terms of the distances of the data points from the cluster centers, and the cluster sizes. A resulting extremal principle is then used to update the cluster centers (as convex combinations of the data points), and the cluster sizes (if not given.) Progress is monitored by the joint distance function (JDF), a weighted harmonic mean of the above distances, that approximates the data by capturing the data points in its lowest contours. The method is described, and applied to clustering, location problems, and mixtures of distributions, where it is a viable alternative to the Expectation-Maximization (EM) method. The JDF also helps to determine the {"}right{"} number of clusters for a given data set.",

author = "C. Iyigun and A. Ben-Israel",

year = "2013",

language = "American English",

isbn = "9812771654",

series = "Clustering Challenges in Biological Networks",

pages = "29--52",

booktitle = "Clustering Challenges in Biological Networks",

note = "DIMACS Workshop on Clustering Problems in Biological Networks 2009 ; Conference date: 09-05-2006 Through 11-05-2006",

}

TY - GEN

T1 - Probabilistic distance clustering

T2 - DIMACS Workshop on Clustering Problems in Biological Networks 2009

AU - Iyigun, C.

AU - Ben-Israel, A.

PY - 2013

Y1 - 2013

N2 - The probabilistic distance clustering method of the authors [2, 8], assumes the cluster membership probabilities given in terms of the distances of the data points from the cluster centers, and the cluster sizes. A resulting extremal principle is then used to update the cluster centers (as convex combinations of the data points), and the cluster sizes (if not given.) Progress is monitored by the joint distance function (JDF), a weighted harmonic mean of the above distances, that approximates the data by capturing the data points in its lowest contours. The method is described, and applied to clustering, location problems, and mixtures of distributions, where it is a viable alternative to the Expectation-Maximization (EM) method. The JDF also helps to determine the "right" number of clusters for a given data set.

AB - The probabilistic distance clustering method of the authors [2, 8], assumes the cluster membership probabilities given in terms of the distances of the data points from the cluster centers, and the cluster sizes. A resulting extremal principle is then used to update the cluster centers (as convex combinations of the data points), and the cluster sizes (if not given.) Progress is monitored by the joint distance function (JDF), a weighted harmonic mean of the above distances, that approximates the data by capturing the data points in its lowest contours. The method is described, and applied to clustering, location problems, and mixtures of distributions, where it is a viable alternative to the Expectation-Maximization (EM) method. The JDF also helps to determine the "right" number of clusters for a given data set.

UR - http://www.scopus.com/inward/record.url?scp=84891324885&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84891324885&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9812771654

SN - 9789812771650

T3 - Clustering Challenges in Biological Networks

SP - 29

EP - 52

BT - Clustering Challenges in Biological Networks

Y2 - 9 May 2006 through 11 May 2006

ER -

Probabilistic distance clustering: Algorithm and applications

Abstract

Publication series

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this