Fast k nearest neighbour search for R-tree family
Fast k nearest neighbour search for R-tree family
A simplified k nearest neighbour (knn) search for the R-tree family is proposed in this paper. This method is modified from the technique developed by Roussopoulos et al. The main approach aims to eliminate redundant searches when the data is highly correlated. We also describe how MINMAXDIST calculations can be avoided using MINDIST as the only distance metric which gives a significant speed up. Our method is compared with Roussopoulos et al.'s knn search on Hilbert R-trees in different dimensions, and shows that an improvement can be achieved on clustered image databases which have large numbers of data objects very close to each other. However, our method only achieved a marginally better performance of pages accessed on randomly distributed databases and random queries far from clustered objects, but has less computation intensity.
924--928
Kuan, Joseph K. P.
441cb534-30bf-4193-90cb-2a33d37c335a
Lewis, Paul H.
7aa6c6d9-bc69-4e19-b2ac-a6e20558c020
September 1997
Kuan, Joseph K. P.
441cb534-30bf-4193-90cb-2a33d37c335a
Lewis, Paul H.
7aa6c6d9-bc69-4e19-b2ac-a6e20558c020
Kuan, Joseph K. P. and Lewis, Paul H.
(1997)
Fast k nearest neighbour search for R-tree family.
In Proceedings on First International Conf. on Information, Communications, and Signal Processing. Singapore..
.
Record type:
Conference or Workshop Item
(Other)
Abstract
A simplified k nearest neighbour (knn) search for the R-tree family is proposed in this paper. This method is modified from the technique developed by Roussopoulos et al. The main approach aims to eliminate redundant searches when the data is highly correlated. We also describe how MINMAXDIST calculations can be avoided using MINDIST as the only distance metric which gives a significant speed up. Our method is compared with Roussopoulos et al.'s knn search on Hilbert R-trees in different dimensions, and shows that an improvement can be achieved on clustered image databases which have large numbers of data objects very close to each other. However, our method only achieved a marginally better performance of pages accessed on randomly distributed databases and random queries far from clustered objects, but has less computation intensity.
Other
kuan1997a.ps
- Other
Archive
archive-250841
- Other
More information
Published date: September 1997
Venue - Dates:
In Proceedings on First International Conf. on Information, Communications, and Signal Processing. Singapore., 1997-09-01
Organisations:
Web & Internet Science
Identifiers
Local EPrints ID: 250841
URI: http://eprints.soton.ac.uk/id/eprint/250841
PURE UUID: 30020e74-9fe4-4233-8a0f-1b4258e6a71e
Catalogue record
Date deposited: 16 Sep 1999
Last modified: 14 Mar 2024 05:01
Export record
Contributors
Author:
Joseph K. P. Kuan
Author:
Paul H. Lewis
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics