DGCL: An Efficient Density and Grid Based Clustering Algorithm for Large Spatial Database

Spatial clustering, which groups similar objects based on their distance, connectivity, or their relative density in space, is an important component of spatial data mining. Clustering large data sets has always been a serious challenge for clustering algorithms, because huge data set makes the clus...

Full description

Saved in:
Bibliographic Details
Published inAdvances in Web-Age Information Management pp. 362 - 371
Main Authors Kim, Ho Seok, Gao, Song, Xia, Ying, Kim, Gyoung Bae, Bae, Hae Young
Format Book Chapter Conference Proceeding
LanguageEnglish
Published Berlin, Heidelberg Springer Berlin Heidelberg 2006
Springer
SeriesLecture Notes in Computer Science
Subjects
Applied sciences
Base Cluster Algorithm
Cluster Algorithm
Computer science; control theory; systems
Computer systems and distributed systems. User interface
Data processing. List processing. Character string processing
Exact sciences and technology
Information systems. Data bases
Memory organisation. Data processing
Software
Spatial Data
Spatial Data Mining
Spatial Database
Cluster analysis
Spatial data structures
Data analysis
Grid
Very large databases
Information extraction
Data mining
Outlier
Classification
Object oriented
Internet
Database management system
Spatial database
Online AccessGet full text

Cover

More Information
Summary:Spatial clustering, which groups similar objects based on their distance, connectivity, or their relative density in space, is an important component of spatial data mining. Clustering large data sets has always been a serious challenge for clustering algorithms, because huge data set makes the clustering process extremely costly. In this paper, we propose DGCL, an enhanced Density-Grid based Clustering algorithm for Large spatial database. The characteristics of dense area can be enhanced by considering the affection of the surrounding area. Dense areas are analytically identified as clusters by removing sparse area or outliers with the help of a density threshold. Synthetic datasets are used for testing and the result shows the superiority of our approach.
Bibliography:This research was supported by the MIC (Ministry of Information and Communication),Korea, under the ITRC (Information Technology Research Center) support program supervised by the IITA (Institute of Information Technology Assessment).
ISBN:9783540352259
3540352252
ISSN:0302-9743
1611-3349
DOI:10.1007/11775300_31