Abstract
Shapelets have recently been proposed as a new primitive for time series classification. Shapelets are subseries of series that best split the data into its classes. In the original research, shapelets were found recursively within a decision tree through enumeration of the search space. Subsequent research indicated that using shapelets as the basis for transforming datasets leads to more accurate classifiers. Both these approaches evaluate how well a shapelet splits all the classes. However, often a shapelet is most useful in distinguishing between members of the class of the series it was drawn from against all others. To assess this conjecture, we evaluate a one vs all encoding scheme. This technique simplifies the quality assessment calculations, speeds up the execution through facilitating more frequent early abandon and increases accuracy for multi-class problems. We also propose an alternative shapelet evaluation scheme which we demonstrate significantly speeds up the full search.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ye, L., Keogh, E.: Time series shapelets: a novel technique that allows accurate, interpretable and fast classification. Data Min. Knowl. Disc. 22(1–2), 149–182 (2011)
Hills, J., Lines, J., Baranauskas, E., Mapp, J., Bagnall, A.: Classification of time series by shapelet transformation. Data Min. Knowl. Disc. 28(4), 851–881 (2014)
Mueen, A., Keogh, E., Young, N.: Logical-shapelets: an expressive primitive for time series classification. In: Proceeding 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2011)
Rakthanmanon, T., Keogh, E.: Fast-shapelets: a fast algorithm for discovering robust time series shapelets. In: Proceeding 13th SIAM International Conference on Data Mining (SDM) (2013)
Grabocka, J., Schilling, N., Wistuba, M., Schmidt-Thieme, L.: Learning time-series shapelets. In: Proceeding 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2014)
Gordon, D., Hendler, D., Rokach, L.: Fast randomized model generation for shapelet-based time series classification. arXiv preprint arXiv:1209.5038 (2012)
Lines, J., Bagnall, A.: Alternative quality measures for time series shapelets. In: Yin, H., Costa, J.A.F., Barreto, G. (eds.) IDEAL 2012. LNCS, vol. 7435, pp. 475–483. Springer, Heidelberg (2012). doi:10.1007/978-3-642-32639-4_58
Hills, J.: Mining time-series data using discriminative subsequences. PhD thesis, School of Computing Sciences, University of East Anglia (2015)
Rakthanmanon, T., Bilson, J., Campana, L., Mueen, A., Batista, G., Westover, B., Zhu, Q., Zakaria, J., Keogh, E.: Addressing big data time series: mining trillions of time series subsequences under dynamic time warping. ACM Trans. Knowl. Disc. Data, 7(3) (2013)
Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.: The WEKA data mining software: an update. SIGKDD Explor. 11(1), 10–18 (2009)
Quinlan, J.R., et al.: Bagging, boosting, and c4.5. In: AAAI/IAAI, vol. 1, pp. 725–730 (1996)
Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Rodriguez, J.J., Kuncheva, L.I., Alonso, C.J.: Rotation forest: a new classifier ensemble method. IEEE Trans. Pattern Anal. Mach. Intell. 28(10), 1619–1630 (2006)
Lines, J., Davis, L., Hills, J., Bagnall, A.: A shapelet transform for time series classification. In: Proceeding of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2012)
Lin, J., Keogh, E., Li, W., Lonardi, S.: Experiencing SAX: a novel symbolic representation of time series. Data Min. Knowl. Disc. 15(2), 107–144 (2007)
Chen, Y., Keogh, E., Hu, B., Begum, N., Bagnall, A., Mueen, A., Batista, G.: The UCR time series classification archive (2015). http://www.cs.ucr.edu/~eamonn/time_series_data/
Bagnall, A., Lines, J., Bostrom, A., Keogh, E.: The UCR/UEA TSC archive. http://timeseriesclassification.com
Bagnall, A., Bostrom, A., Lines, J.: The UEA TSC codebase. https://bitbucket.org/TonyBagnall/time-series-classification
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer-Verlag GmbH Germany
About this chapter
Cite this chapter
Bostrom, A., Bagnall, A. (2017). Binary Shapelet Transform for Multiclass Time Series Classification. In: Hameurlain, A., Küng, J., Wagner, R., Madria, S., Hara, T. (eds) Transactions on Large-Scale Data- and Knowledge-Centered Systems XXXII. Lecture Notes in Computer Science(), vol 10420. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-55608-5_2
Download citation
DOI: https://doi.org/10.1007/978-3-662-55608-5_2
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-55607-8
Online ISBN: 978-3-662-55608-5
eBook Packages: Computer ScienceComputer Science (R0)