Efficient subsequence matching in time series databases under time and amplitude transformations

Argyros, T; Ermopoulos, C

dc.contributor.author	Argyros, T	en
dc.contributor.author	Ermopoulos, C	en
dc.date.accessioned	2014-03-01T02:42:15Z
dc.date.available	2014-03-01T02:42:15Z
dc.date.issued	2003	en
dc.identifier.issn	15504786	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/30888
dc.subject	Efficient Algorithm	en
dc.subject	Time Series	en
dc.title	Efficient subsequence matching in time series databases under time and amplitude transformations	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ICDM.2003.1250957	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ICDM.2003.1250957	en
heal.publicationDate	2003	en
heal.abstract	Subsequence matching in large time series databases has attracted a lot of interest and many methods have been proposed that cope with this problem in an adequate extend. However, locating subsequence matches of arbitrary length, under time and amplitude transformations, has received far less attention and is still an open problem. In this paper we present an efficient algorithm for variable-length subsequence matching under transformations that guarantees no false dismissals. Further, this algorithm uses a novel similarity criterion for determining similarity under amplitude transformations in a most efficient way. Finally, our algorithm has been tested in various experiments on real data, resulting in a running time improvement of one order of magnitude compared to the naive approach. © 2003 IEEE.	en
heal.journalName	Proceedings - IEEE International Conference on Data Mining, ICDM	en
dc.identifier.doi	10.1109/ICDM.2003.1250957	en
dc.identifier.spage	481	en
dc.identifier.epage	484	en