K-means clustering with multiresolution peak detection

Guanshan Yu, Leen-Kiat Soh, Alan Bond

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Clustering is a practical data mining approach of pattern detection. Because of the sensitivity of initial conditions, k-means clustering often suffers from low clustering performance. We present a procedure to refine initial conditions of k-means clustering by analyzing density distributions of a data set before estimating the number of clusters k necessary for the data set, as well as the positions of the initial centroids of the clusters. We demonstrate that this approach indeed improves the accuracy and performance of k-means clustering measured by average intra to interclustering error ratio. This method is applied to the virtual ecology project to design a virtual blue jay system.

Original languageEnglish (US)
Title of host publication2005 IEEE International Conference on Electro Information Technology
StatePublished - Dec 1 2005
Event2005 IEEE International Conference on Electro Information Technology - Lincoln, NE, United States
Duration: May 22 2005May 25 2005

Publication series

Name2005 IEEE International Conference on Electro Information Technology
Volume2005

Conference

Conference2005 IEEE International Conference on Electro Information Technology
CountryUnited States
CityLincoln, NE
Period5/22/055/25/05

Fingerprint

Ecology
Data mining

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Yu, G., Soh, L-K., & Bond, A. (2005). K-means clustering with multiresolution peak detection. In 2005 IEEE International Conference on Electro Information Technology [1626978] (2005 IEEE International Conference on Electro Information Technology; Vol. 2005).

K-means clustering with multiresolution peak detection. / Yu, Guanshan; Soh, Leen-Kiat; Bond, Alan.

2005 IEEE International Conference on Electro Information Technology. 2005. 1626978 (2005 IEEE International Conference on Electro Information Technology; Vol. 2005).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yu, G, Soh, L-K & Bond, A 2005, K-means clustering with multiresolution peak detection. in 2005 IEEE International Conference on Electro Information Technology., 1626978, 2005 IEEE International Conference on Electro Information Technology, vol. 2005, 2005 IEEE International Conference on Electro Information Technology, Lincoln, NE, United States, 5/22/05.
Yu G, Soh L-K, Bond A. K-means clustering with multiresolution peak detection. In 2005 IEEE International Conference on Electro Information Technology. 2005. 1626978. (2005 IEEE International Conference on Electro Information Technology).
Yu, Guanshan ; Soh, Leen-Kiat ; Bond, Alan. / K-means clustering with multiresolution peak detection. 2005 IEEE International Conference on Electro Information Technology. 2005. (2005 IEEE International Conference on Electro Information Technology).
@inproceedings{9b6c1ad63f784af185a991d5094ba717,
title = "K-means clustering with multiresolution peak detection",
abstract = "Clustering is a practical data mining approach of pattern detection. Because of the sensitivity of initial conditions, k-means clustering often suffers from low clustering performance. We present a procedure to refine initial conditions of k-means clustering by analyzing density distributions of a data set before estimating the number of clusters k necessary for the data set, as well as the positions of the initial centroids of the clusters. We demonstrate that this approach indeed improves the accuracy and performance of k-means clustering measured by average intra to interclustering error ratio. This method is applied to the virtual ecology project to design a virtual blue jay system.",
author = "Guanshan Yu and Leen-Kiat Soh and Alan Bond",
year = "2005",
month = "12",
day = "1",
language = "English (US)",
isbn = "0780392329",
series = "2005 IEEE International Conference on Electro Information Technology",
booktitle = "2005 IEEE International Conference on Electro Information Technology",

}

TY - GEN

T1 - K-means clustering with multiresolution peak detection

AU - Yu, Guanshan

AU - Soh, Leen-Kiat

AU - Bond, Alan

PY - 2005/12/1

Y1 - 2005/12/1

N2 - Clustering is a practical data mining approach of pattern detection. Because of the sensitivity of initial conditions, k-means clustering often suffers from low clustering performance. We present a procedure to refine initial conditions of k-means clustering by analyzing density distributions of a data set before estimating the number of clusters k necessary for the data set, as well as the positions of the initial centroids of the clusters. We demonstrate that this approach indeed improves the accuracy and performance of k-means clustering measured by average intra to interclustering error ratio. This method is applied to the virtual ecology project to design a virtual blue jay system.

AB - Clustering is a practical data mining approach of pattern detection. Because of the sensitivity of initial conditions, k-means clustering often suffers from low clustering performance. We present a procedure to refine initial conditions of k-means clustering by analyzing density distributions of a data set before estimating the number of clusters k necessary for the data set, as well as the positions of the initial centroids of the clusters. We demonstrate that this approach indeed improves the accuracy and performance of k-means clustering measured by average intra to interclustering error ratio. This method is applied to the virtual ecology project to design a virtual blue jay system.

UR - http://www.scopus.com/inward/record.url?scp=33947162363&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33947162363&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:33947162363

SN - 0780392329

SN - 9780780392328

T3 - 2005 IEEE International Conference on Electro Information Technology

BT - 2005 IEEE International Conference on Electro Information Technology

ER -