Knowledge and Information Systems

, Volume 47, Issue 1, pp 1–26

Faster and more accurate classification of time series by exploiting a novel dynamic time warping averaging algorithm

  • François Petitjean
  • Germain Forestier
  • Geoffrey I. Webb
  • Ann E. Nicholson
  • Yanping Chen
  • Eamonn Keogh
Regular Paper

DOI: 10.1007/s10115-015-0878-8

Cite this article as:
Petitjean, F., Forestier, G., Webb, G.I. et al. Knowl Inf Syst (2016) 47: 1. doi:10.1007/s10115-015-0878-8

Abstract

A concerted research effort over the past two decades has heralded significant improvements in both the efficiency and effectiveness of time series classification. The consensus that has emerged in the community is that the best solution is a surprisingly simple one. In virtually all domains, the most accurate classifier is the nearest neighbor algorithm with dynamic time warping as the distance measure. The time complexity of dynamic time warping means that successful deployments on resource-constrained devices remain elusive. Moreover, the recent explosion of interest in wearable computing devices, which typically have limited computational resources, has greatly increased the need for very efficient classification algorithms. A classic technique to obtain the benefits of the nearest neighbor algorithm, without inheriting its undesirable time and space complexity, is to use the nearest centroid algorithm. Unfortunately, the unique properties of (most) time series data mean that the centroid typically does not resemble any of the instances, an unintuitive and underappreciated fact. In this paper we demonstrate that we can exploit a recent result by Petitjean et al. to allow meaningful averaging of “warped” time series, which then allows us to create super-efficient nearest “centroid” classifiers that are at least as accurate as their more computationally challenged nearest neighbor relatives. We demonstrate empirically the utility of our approach by comparing it to all the appropriate strawmen algorithms on the ubiquitous UCR Benchmarks and with a case study in supporting insect classification on resource-constrained sensors.

Keywords

Time series Averaging Dynamic time warping Classification Data mining 

Funding information

Funder NameGrant NumberFunding Note
Australian Research Council
  • DP120100553
Australian Research Council
  • DP140100087
National Science Foundation
  • IIS-1161997
Bill and Melinda Gates Foundation
    Vodafone
    • Wireless Innovation Project
    French-Australia Science Innovation Collaboration
    • 32571NA
    Air Force Office of Scientific Research
    • FA2386-15-1-4007
    Air Force Office of Scientific Research
    • FA2386-15-1-4017

    Copyright information

    © Springer-Verlag London (outside the USA) 2015

    Authors and Affiliations

    • François Petitjean
      • 1
    • Germain Forestier
      • 2
    • Geoffrey I. Webb
      • 1
    • Ann E. Nicholson
      • 1
    • Yanping Chen
      • 3
    • Eamonn Keogh
      • 3
    1. 1.Faculty of ITMonash UniversityMelbourneVIC, Australia
    2. 2.MIPS (EA 2332)Université de Haute AlsaceMulhouseFrance
    3. 3.Computer Science and Engineering DepartmentUniversity of CaliforniaRiversideUSA

    Personalised recommendations