Incremental procedures for partitioning highly intermixed multi-class datasets into hyper-spherical and hyper-ellipsoidal clusters

Qinglu Kong, Qiuming Zhu

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Two procedures for partitioning large collections of highly intermixed datasets of different classes into a number of hyper-spherical or hyper-ellipsoidal clusters are presented. The incremental procedures are to generate a minimum numbers of hyper-spherical or hyper-ellipsoidal clusters with each cluster containing a maximum number of data points of the same class. The procedures extend the move-to-front algorithms originally designed for construction of minimum sized enclosing balls or ellipsoids for dataset of a single class. The resulting clusters of the dataset can be used for data modeling, outlier detection, discrimination analysis, and knowledge discovery.

Original languageEnglish (US)
Pages (from-to)457-477
Number of pages21
JournalData and Knowledge Engineering
Volume63
Issue number2
DOIs
StatePublished - Nov 1 2007

Fingerprint

Data mining
Data structures
Partitioning
Incremental

Keywords

  • Data clustering
  • Data models
  • Geometrical approximation
  • Knowledge discovery
  • Mini-max partition

ASJC Scopus subject areas

  • Information Systems and Management

Cite this

@article{42558371ab6e477a96b44532c2c37c0b,
title = "Incremental procedures for partitioning highly intermixed multi-class datasets into hyper-spherical and hyper-ellipsoidal clusters",
abstract = "Two procedures for partitioning large collections of highly intermixed datasets of different classes into a number of hyper-spherical or hyper-ellipsoidal clusters are presented. The incremental procedures are to generate a minimum numbers of hyper-spherical or hyper-ellipsoidal clusters with each cluster containing a maximum number of data points of the same class. The procedures extend the move-to-front algorithms originally designed for construction of minimum sized enclosing balls or ellipsoids for dataset of a single class. The resulting clusters of the dataset can be used for data modeling, outlier detection, discrimination analysis, and knowledge discovery.",
keywords = "Data clustering, Data models, Geometrical approximation, Knowledge discovery, Mini-max partition",
author = "Qinglu Kong and Qiuming Zhu",
year = "2007",
month = "11",
day = "1",
doi = "10.1016/j.datak.2007.03.006",
language = "English (US)",
volume = "63",
pages = "457--477",
journal = "Data and Knowledge Engineering",
issn = "0169-023X",
publisher = "Elsevier",
number = "2",

}

TY - JOUR

T1 - Incremental procedures for partitioning highly intermixed multi-class datasets into hyper-spherical and hyper-ellipsoidal clusters

AU - Kong, Qinglu

AU - Zhu, Qiuming

PY - 2007/11/1

Y1 - 2007/11/1

N2 - Two procedures for partitioning large collections of highly intermixed datasets of different classes into a number of hyper-spherical or hyper-ellipsoidal clusters are presented. The incremental procedures are to generate a minimum numbers of hyper-spherical or hyper-ellipsoidal clusters with each cluster containing a maximum number of data points of the same class. The procedures extend the move-to-front algorithms originally designed for construction of minimum sized enclosing balls or ellipsoids for dataset of a single class. The resulting clusters of the dataset can be used for data modeling, outlier detection, discrimination analysis, and knowledge discovery.

AB - Two procedures for partitioning large collections of highly intermixed datasets of different classes into a number of hyper-spherical or hyper-ellipsoidal clusters are presented. The incremental procedures are to generate a minimum numbers of hyper-spherical or hyper-ellipsoidal clusters with each cluster containing a maximum number of data points of the same class. The procedures extend the move-to-front algorithms originally designed for construction of minimum sized enclosing balls or ellipsoids for dataset of a single class. The resulting clusters of the dataset can be used for data modeling, outlier detection, discrimination analysis, and knowledge discovery.

KW - Data clustering

KW - Data models

KW - Geometrical approximation

KW - Knowledge discovery

KW - Mini-max partition

UR - http://www.scopus.com/inward/record.url?scp=34447284783&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34447284783&partnerID=8YFLogxK

U2 - 10.1016/j.datak.2007.03.006

DO - 10.1016/j.datak.2007.03.006

M3 - Article

AN - SCOPUS:34447284783

VL - 63

SP - 457

EP - 477

JO - Data and Knowledge Engineering

JF - Data and Knowledge Engineering

SN - 0169-023X

IS - 2

ER -