EA DTW: Early Abandon to Accelerate Exactly Warping Matching of Time Series

DOI

10.2991/iske.2007.205How to use a DOI?

Keywords

Data mining, Time series, Similarity

Abstract

Dynamic Time Warping(DTW) is one of the important distance measures in similarity search of time series, however, the exact calculation of DTW has become a bottleneck. We propose an approach, named Early Abandon DTW(EA_DTW) to accelerate the calculation of DTW. The method checks if value of cells in the cumulative distance matrix exceed the threshold, and if so, it will terminate the calculation of other related cells. We demonstrate the idea of early abandon on DTW by theoretical analysis, and show the utilities of EA_DTW by thorough empirical experiments performed both on synthetic datasets and real datasets. The results show, EA_DTW outperforms the dynamic DTW calculation in the light of process time, and is much better when the threshold is below the real DTW distance

Copyright

© 2007, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Junkui Li
AU  - Yuanzhen Wang
PY  - 2007/10
DA  - 2007/10
TI  - EA DTW: Early Abandon to Accelerate Exactly Warping Matching of Time Series
BT  - Proceedings of the 2007 International Conference on Intelligent Systems and Knowledge Engineering (ISKE 2007)
PB  - Atlantis Press
SP  - 1200
EP  - 1207
SN  - 1951-6851
UR  - https://doi.org/10.2991/iske.2007.205
DO  - 10.2991/iske.2007.205
ID  - Li2007/10
ER  -