Please use this identifier to cite or link to this item:
Title: The Effects of Dimensionality Curse in High Dimensional kNN Search
Authors: Kouiroukidis, Nikolaos
Evangelidis, Georgios
Type: Conference Paper
Subjects: FRASCATI::Natural sciences::Computer and information sciences
Keywords: high dimensional point indexing
index performance comparison
kNN search
Issue Date: 2011
First Page: 41
Last Page: 45
Volume Title: 2011 15th Panhellenic Conference on Informatics
Abstract: The dimensionality curse phenomenon states that in high dimensional spaces distances between nearest and farthest points from query points become almost equal. Therefore, nearest neighbor calculations cannot discriminate candidate points. Many indexing methods that try to cope with the dimensionality curse in high dimensional spaces have been proposed, but, usually these methods end up behaving like the sequential scan over the database in terms of accessed pages when queries like k-Nearest Neighbors are examined. In this paper, we experiment with state of the art multi-attribute indexing methods and try to investigate when these methods reach their limits, namely, at what dimensionality a kNN query requires visiting all the data pages. In our experiments we compare the Hybrid Tree, the R*-tree, and, the iDistance Method.
ISBN: 978-1-61284-962-1
Other Identifiers: 10.1109/PCI.2011.45
Appears in Collections:Department of Applied Informatics

Files in This Item:
File Description SizeFormat 
2011_PCI_KE.pdf152,14 kBAdobe PDFView/Open

This item is licensed under a Creative Commons License Creative Commons