Discovery of cross-similarity in data streams

In this paper, we focus on the problem of finding partial similarity between data streams. Our solution relies on dynamic time warping (DTW) as a similarity measure, which computes the distance between sequences whose lengths and/or sampling rates are different. Instead of straightforwardly using DT...

Full description

Saved in:
Bibliographic Details
Published in2010 IEEE 26th International Conference on Data Engineering (ICDE 2010) pp. 101 - 104
Main Authors Toyoda, Machiko, Sakurai, Yasushi
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.01.2010
Subjects
Computational efficiency
Data analysis
Information science
Laboratories
Length measurement
Monitoring
Object detection
Robustness
Sampling methods
Time measurement
Online AccessGet full text

Cover

More Information
Summary:In this paper, we focus on the problem of finding partial similarity between data streams. Our solution relies on dynamic time warping (DTW) as a similarity measure, which computes the distance between sequences whose lengths and/or sampling rates are different. Instead of straightforwardly using DTW that requires a high computation cost, we propose a streaming method that efficiently detects partial similarity between sequences. Our experiments demonstrate that our method detects pairs of optimal subsequences correctly and that it significantly reduces resources in terms of time and space.
ISBN:142445445X
9781424454457
ISSN:1063-6382
2375-026X
DOI:10.1109/ICDE.2010.5447927