23
IRUS Total
Downloads

STATS - A Point Access Method for Multidimensional Clusters.

File Description SizeFormat 
stats_point_access_cropped(1).pdfAccepted version368.28 kBAdobe PDFView/Open
Title: STATS - A Point Access Method for Multidimensional Clusters.
Authors: Evagorou, G
Heinis, T
Item Type: Conference Paper
Abstract: The ubiquity of high-dimensional data in machine learning and data mining applications makes its efficient indexing and retrieval from main memory crucial. Frequently, these machine learning algorithms need to query specific characteristics of single multidimensional points. For example, given a clustered dataset, the cluster membership (CM) query retrieves the cluster to which an object belongs. To efficiently answer this type of query we have developed STATS, a novel main-memory index which scales to answer CM queries on increasingly big datasets. Current indexing methods are oblivious to the structure of clusters in the data, and we thus, develop STATS around the key insight that exploiting the cluster information when indexing and preserving it in the index will accelerate look up. We show experimentally that STATS outperforms known methods in regards to retrieval time and scales well with dataset size for any number of dimensions.
Editors: Benslimane, D
Damiani, E
Grosky, WI
Hameurlain, A
Sheth, AP
Wagner, RR
Issue Date: 1-Aug-2017
Date of Acceptance: 1-Aug-2017
URI: http://hdl.handle.net/10044/1/59708
ISBN: 978-3-319-64467-7
ISSN: 0302-9743
Publisher: Springer Verlag
Start Page: 352
End Page: 361
Journal / Book Title: Lecture Notes in Computer Science
Copyright Statement: © 2017 Springer International Publishing AG.
Sponsor/Funder: Engineering & Physical Science Research Council (E
European Research Office
Funder's Grant Number: EP/N023242/1
720270
Conference Name: DEXA 2017: Database and Expert Systems Applications
Keywords: 08 Information And Computing Sciences
Artificial Intelligence & Image Processing
Publication Status: Published
Start Date: 2017-08-28
Finish Date: 2017-08-31
Conference Place: Lyon, France
Online Publication Date: 2017-08-01
Appears in Collections:Computing
Faculty of Engineering