Spatial Clustering in Large Databases Using Packed X-tree

Research output: Contribution to journalArticle

Abstract

In this paper, we are proposing a new algorithm that improves the performance of the DBSCAN clustering algorithm using a packed X-tree. The proposed algorithm does not require the minpoints and eps values. We have extensively described how the system is achieved and we have also proposed a new effective method for finding the k-nearest neighbours of spatial objects in a large database. The study shows that the proposed method is very efficient and will greatly accelerate the operations of density based clustering in large dataset as against the existing methods.
LanguageEnglish
Pages68-79
Number of pages12
JournalEgyptian Computer Science Journal
Volume42
Issue number2
Publication statusPublished - May 2018

Fingerprint

Trees (mathematics)
Clustering algorithms

Cite this

@article{aee02f6869094e0fbaf641998de2c24b,
title = "Spatial Clustering in Large Databases Using Packed X-tree",
abstract = "In this paper, we are proposing a new algorithm that improves the performance of the DBSCAN clustering algorithm using a packed X-tree. The proposed algorithm does not require the minpoints and eps values. We have extensively described how the system is achieved and we have also proposed a new effective method for finding the k-nearest neighbours of spatial objects in a large database. The study shows that the proposed method is very efficient and will greatly accelerate the operations of density based clustering in large dataset as against the existing methods.",
author = "Grace Samson and Zhongyu Lou",
year = "2018",
month = "5",
language = "English",
volume = "42",
pages = "68--79",
journal = "Egyptian Computer Science Journal",
issn = "1110-2586",
number = "2",

}

Spatial Clustering in Large Databases Using Packed X-tree. / Samson, Grace; Lou, Zhongyu.

In: Egyptian Computer Science Journal, Vol. 42, No. 2, 05.2018, p. 68-79.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Spatial Clustering in Large Databases Using Packed X-tree

AU - Samson, Grace

AU - Lou, Zhongyu

PY - 2018/5

Y1 - 2018/5

N2 - In this paper, we are proposing a new algorithm that improves the performance of the DBSCAN clustering algorithm using a packed X-tree. The proposed algorithm does not require the minpoints and eps values. We have extensively described how the system is achieved and we have also proposed a new effective method for finding the k-nearest neighbours of spatial objects in a large database. The study shows that the proposed method is very efficient and will greatly accelerate the operations of density based clustering in large dataset as against the existing methods.

AB - In this paper, we are proposing a new algorithm that improves the performance of the DBSCAN clustering algorithm using a packed X-tree. The proposed algorithm does not require the minpoints and eps values. We have extensively described how the system is achieved and we have also proposed a new effective method for finding the k-nearest neighbours of spatial objects in a large database. The study shows that the proposed method is very efficient and will greatly accelerate the operations of density based clustering in large dataset as against the existing methods.

M3 - Article

VL - 42

SP - 68

EP - 79

JO - Egyptian Computer Science Journal

T2 - Egyptian Computer Science Journal

JF - Egyptian Computer Science Journal

SN - 1110-2586

IS - 2

ER -