Skip to content

Scalable learning of time series classifiers

Times series classification is an important data analysis task.  The largest dataset in the standard set of benchmark time-series classification tasks, the UCR respository, contains approximately 10,000 series. We are working with the French Space agency on classifying land usage from satellite images.  This task requires learning from many millions of time series and classifying many billions.  The preexisting state-of-the-art does not scale to these magnitudes.  We are developing new time series classification technologies that will.

The TSI software for the SDM 2017 paper can be downloaded here: https://github.com/ChangWeiTan/TSI

Slides for the SDM paper can be downloaded here: http://francois-petitjean.com/Research/SDM17-slides.pdf

The following is a blog post on the use of Barycentric averaging in time series classification: http://www.kdnuggets.com/2014/12/averaging-improves-accuracy-speed-time-series-classification.html

The code can be downloaded here: http://francois-petitjean.com/Research/ICDM2014-DTW/index.php

The slides for the ICDM 2014 paper can be downloaded here: http://francois-petitjean.com/Research/ICDM2014-DTW/Slides.pdf

Publications

Indexing and classifying gigabytes of time series under time warping.
Tan, C. W., Webb, G. I., & Petitjean, F.
Proceedings of the 2017 SIAM International Conference on Data Mining, pp. 282-290, 2017.
[PDF] [DOI] [Bibtex]

@InProceedings{TanEtAl17a,
Title = {Indexing and classifying gigabytes of time series under time warping},
Author = {Tan, Chang Wei and Webb, Geoffrey I and Petitjean, Fran{\c{c}}ois},
Booktitle = {Proceedings of the 2017 SIAM International Conference on Data Mining},
Year = {2017},
Organization = {SIAM},
Pages = {282-290},
Doi = {10.1137/1.9781611974973.32},
Keywords = {time series},
Related = {scalable-time-series-classifiers}
}
ABSTRACT 

Faster and more accurate classification of time series by exploiting a novel dynamic time warping averaging algorithm.
Petitjean, F., Forestier, G., Webb, G. I., Nicholson, A. E., Chen, Y., & Keogh, E.
Knowledge and Information Systems, 47(1), 1-26, 2016.
[PDF] [URL] [Bibtex]

ABSTRACT 

Dynamic Time Warping Averaging of Time Series Allows Faster and More Accurate Classification.
Petitjean, F., Forestier, G., Webb, G. I., Nicholson, A., Chen, Y., & Keogh, E.
Proceedings of the 14th IEEE International Conference on Data Mining, pp. 470-479, 2014.
[PDF] [URL] [Bibtex] [Abstract]

@InProceedings{PetitjeanEtAl14b,
Title = {Dynamic Time Warping Averaging of Time Series Allows Faster and More Accurate Classification},
Author = {F. Petitjean and G. Forestier and G.I. Webb and A. Nicholson and Y. Chen and E. Keogh},
Booktitle = {Proceedings of the 14th {IEEE} International Conference on Data Mining},
Year = {2014},
Pages = {470-479},
Abstract = {Recent years have seen significant progress in improving both the efficiency and effectiveness of time series classification. However, because the best solution is typically the Nearest Neighbor algorithm with the relatively expensive Dynamic Time Warping as the distance measure, successful deployments on resource constrained devices remain elusive. Moreover, the recent explosion of interest in wearable devices, which typically have limited computational resources, has created a growing need for very efficient classification algorithms. A commonly used technique to glean the benefits of the Nearest Neighbor algorithm, without inheriting its undesirable time complexity, is to use the Nearest Centroid algorithm. However, because of the unique properties of (most) time series data, the centroid typically does not resemble any of the instances, an unintuitive and underappreciated fact. In this work we show that we can exploit a recent result to allow meaningful averaging of 'warped' times series, and that this result allows us to create ultra-efficient Nearest 'Centroid' classifiers that are at least as accurate as their more lethargic Nearest Neighbor cousins.},
Comment = {One of nine papers invited to Knowledge and Information Systems journal ICDM-14 special issue},
Keywords = {time series},
Related = {scalable-time-series-classifiers},
Url = {http://dx.doi.org/10.1109/ICDM.2014.27}
}
ABSTRACT Recent years have seen significant progress in improving both the efficiency and effectiveness of time series classification. However, because the best solution is typically the Nearest Neighbor algorithm with the relatively expensive Dynamic Time Warping as the distance measure, successful deployments on resource constrained devices remain elusive. Moreover, the recent explosion of interest in wearable devices, which typically have limited computational resources, has created a growing need for very efficient classification algorithms. A commonly used technique to glean the benefits of the Nearest Neighbor algorithm, without inheriting its undesirable time complexity, is to use the Nearest Centroid algorithm. However, because of the unique properties of (most) time series data, the centroid typically does not resemble any of the instances, an unintuitive and underappreciated fact. In this work we show that we can exploit a recent result to allow meaningful averaging of 'warped' times series, and that this result allows us to create ultra-efficient Nearest 'Centroid' classifiers that are at least as accurate as their more lethargic Nearest Neighbor cousins.