SparseDTW

A novel approach to speed up dynamic time warping

Ghazi Al-Naymat, Sanjay Chawla, Javid Taheri

Research output: Chapter in Book/Report/Conference proceedingChapter

46 Citations (Scopus)

Abstract

We present a new space-efficient approach, (SparseDTW), to compute the Dynamic Time Warping (DTW) distance between two time series that always yields the optimal result. This is in contrast to other known approaches which typically sacrifice optimality to attain space efficiency. The main idea behind our approach is to dynamically exploit the existence of similarity and/or correlation between the time series. The more the similarity between the time series the less space required to compute the DTW between them. To the best of our knowledge, all other techniques to speedup DTW, impose apriori constraints and do not exploit similarity characteristics that may be present in the data. We conduct experiments and demonstrate that SparseDTW outperforms previous approaches.

Original languageEnglish
Title of host publicationConferences in Research and Practice in Information Technology Series
Pages117-127
Number of pages11
Volume101
Publication statusPublished - 2009
Externally publishedYes
Event8th Australasian Data Mining Conference, AusDM 2009 - Melbourne, VIC
Duration: 1 Dec 20094 Dec 2009

Other

Other8th Australasian Data Mining Conference, AusDM 2009
CityMelbourne, VIC
Period1/12/094/12/09

Fingerprint

Time series
Experiments

Keywords

  • Data mining
  • Dynamic time warping
  • Similarity measures
  • Time series

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications
  • Hardware and Architecture
  • Information Systems
  • Software

Cite this

Al-Naymat, G., Chawla, S., & Taheri, J. (2009). SparseDTW: A novel approach to speed up dynamic time warping. In Conferences in Research and Practice in Information Technology Series (Vol. 101, pp. 117-127)

SparseDTW : A novel approach to speed up dynamic time warping. / Al-Naymat, Ghazi; Chawla, Sanjay; Taheri, Javid.

Conferences in Research and Practice in Information Technology Series. Vol. 101 2009. p. 117-127.

Research output: Chapter in Book/Report/Conference proceedingChapter

Al-Naymat, G, Chawla, S & Taheri, J 2009, SparseDTW: A novel approach to speed up dynamic time warping. in Conferences in Research and Practice in Information Technology Series. vol. 101, pp. 117-127, 8th Australasian Data Mining Conference, AusDM 2009, Melbourne, VIC, 1/12/09.
Al-Naymat G, Chawla S, Taheri J. SparseDTW: A novel approach to speed up dynamic time warping. In Conferences in Research and Practice in Information Technology Series. Vol. 101. 2009. p. 117-127
Al-Naymat, Ghazi ; Chawla, Sanjay ; Taheri, Javid. / SparseDTW : A novel approach to speed up dynamic time warping. Conferences in Research and Practice in Information Technology Series. Vol. 101 2009. pp. 117-127
@inbook{c3f3d4b4af8e42c28e2caa5aa1d5ff0c,
title = "SparseDTW: A novel approach to speed up dynamic time warping",
abstract = "We present a new space-efficient approach, (SparseDTW), to compute the Dynamic Time Warping (DTW) distance between two time series that always yields the optimal result. This is in contrast to other known approaches which typically sacrifice optimality to attain space efficiency. The main idea behind our approach is to dynamically exploit the existence of similarity and/or correlation between the time series. The more the similarity between the time series the less space required to compute the DTW between them. To the best of our knowledge, all other techniques to speedup DTW, impose apriori constraints and do not exploit similarity characteristics that may be present in the data. We conduct experiments and demonstrate that SparseDTW outperforms previous approaches.",
keywords = "Data mining, Dynamic time warping, Similarity measures, Time series",
author = "Ghazi Al-Naymat and Sanjay Chawla and Javid Taheri",
year = "2009",
language = "English",
isbn = "9781920682828",
volume = "101",
pages = "117--127",
booktitle = "Conferences in Research and Practice in Information Technology Series",

}

TY - CHAP

T1 - SparseDTW

T2 - A novel approach to speed up dynamic time warping

AU - Al-Naymat, Ghazi

AU - Chawla, Sanjay

AU - Taheri, Javid

PY - 2009

Y1 - 2009

N2 - We present a new space-efficient approach, (SparseDTW), to compute the Dynamic Time Warping (DTW) distance between two time series that always yields the optimal result. This is in contrast to other known approaches which typically sacrifice optimality to attain space efficiency. The main idea behind our approach is to dynamically exploit the existence of similarity and/or correlation between the time series. The more the similarity between the time series the less space required to compute the DTW between them. To the best of our knowledge, all other techniques to speedup DTW, impose apriori constraints and do not exploit similarity characteristics that may be present in the data. We conduct experiments and demonstrate that SparseDTW outperforms previous approaches.

AB - We present a new space-efficient approach, (SparseDTW), to compute the Dynamic Time Warping (DTW) distance between two time series that always yields the optimal result. This is in contrast to other known approaches which typically sacrifice optimality to attain space efficiency. The main idea behind our approach is to dynamically exploit the existence of similarity and/or correlation between the time series. The more the similarity between the time series the less space required to compute the DTW between them. To the best of our knowledge, all other techniques to speedup DTW, impose apriori constraints and do not exploit similarity characteristics that may be present in the data. We conduct experiments and demonstrate that SparseDTW outperforms previous approaches.

KW - Data mining

KW - Dynamic time warping

KW - Similarity measures

KW - Time series

UR - http://www.scopus.com/inward/record.url?scp=84870547164&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84870547164&partnerID=8YFLogxK

M3 - Chapter

SN - 9781920682828

VL - 101

SP - 117

EP - 127

BT - Conferences in Research and Practice in Information Technology Series

ER -