Time Series Retrieval Using DTW-Preserving Shapelets
Dynamic Time Warping (DTW) is a very popular similarity measure used for time series classification, retrieval or clustering. DTW is, however, a costly measure, and its application on numerous and/or very long time series is difficult in practice. This paper proposes a new approach for time series retrieval: time series are embedded into another space where the search procedure is less computationally demanding, while still accurate. This approach is based on transforming time series into high-dimensional vectors using DTW-preserving shapelets. That transform is such that the relative distance between the vectors in the Euclidean transformed space well reflects the corresponding DTW measurements in the original space. We also propose strategies for selecting a subset of shapelets in the transformed space, resulting in a trade-off between the complexity of the transformation and the accuracy of the retrieval. Experimental results using the well known UCR time series demonstrate the importance of this trade-off.
The current work has been performed with the support of CNPq (Conselho Nacional de Desenvolvimento Científico e Tecnológico), Brazil (Process number 233209/2014–0). The authors are grateful to the TRANSFORM project funded by STIC-AMSUD (18-STIC-09) for the partial financial support to this work.
- 2.Chen, Y., et al.: The UCR time series classification archive, July 2015. www.cs.ucr.edu/~eamonn/time_series_data/
- 3.Ding, H., Trajcevski, G., Scheuermann, P., Wang, X., Keogh, E.J.: Querying and mining of time series data: experimental comparison of representations and distance measures. PVLDB 1(2), 1542–1552 (2008)Google Scholar
- 5.Grabocka, J., Schilling, N., Wistuba, M., Schmidt-Thieme, L.: Learning time-series shapelets. In: KDD, pp. 392–401. ACM (2014)Google Scholar
- 12.Moradi, P., Rostami, M.: A graph theoretic approach for unsupervised feature selection. Eng. Appl. AI 44, 33–45 (2015)Google Scholar
- 14.Rakthanmanon, T., et al.: Searching and mining trillions of time series subsequences under DTW. In: KDD, pp. 262–270. ACM (2012)Google Scholar
- 17.Shieh, J., Keogh, E.J.: iSAX: indexing and mining terabyte sized time series. In: KDD, pp. 623–631. ACM (2008)Google Scholar
- 19.Tavenard, R.: tslearn: a machine learning toolkit dedicated to time-series data (2017). https://github.com/rtavenar/tslearn
- 21.Ye, L., Keogh, E.J.: Time series shapelets: a new primitive for data mining. In: KDD, pp. 947–956. ACM (2009)Google Scholar
- 22.Yi, B., Faloutsos, C.: Fast time sequence indexing for arbitrary Lp norms. In: VLDB, pp. 385–394. Morgan Kaufmann, Burlington (2000)Google Scholar
- 23.Zakaria, J., Mueen, A., Keogh, E.J.: Clustering time series using unsupervised-shapelets. In: ICDM, pp. 785–794. IEEE Computer Society (2012)Google Scholar