Abstract
Real-world time series classification applications often involve positive unlabeled (PU) training data, where there are only a small set PL of positive labeled examples and a large set U of unlabeled ones. Most existing time series PU classification methods utilize all readings in the time series, making them sensitive to non-characteristic readings. Characteristic patterns named shapelets present a promising solution to this problem, yet discovering shapelets under PU settings is not easy. In this paper, we take on the challenging task of shapelet discovery with PU data. We propose a novel pattern ensemble technique utilizing both characteristic and non-characteristic patterns to rank U examples by their possibilities of being positive. We also present a novel stopping criterion to estimate the number of positive examples in U. These enable us to effectively label all U training examples and conduct supervised shapelet discovery. The shapelets are then used to build a one-nearest-neighbor classifier for online classification. Extensive experiments demonstrate the effectiveness of our method.
This work is funded by NSFC grants 61672161 and 61332013. We sincerely thank Dr. Nurjahan Begum and Dr. Anthony Bagnall for granting us access to the code of [3] and [7], and all our colleagues who have contributed valuable suggestions to this work.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The term positive unlabeled can be confusing, where positive actually means positive labeled. In this paper, we still use positive unlabeled (PU) to refer to what is actually positive-labeled unlabeled. However, in other cases, we use positive/negative to refer to all positive/negative examples, regardless of whether they are labeled or not. Positive examples that are labeled will be explicitly referred to as being positive labeled (PL).
- 2.
In this paper, we use the terms subsequence and pattern interchangeably.
References
PU-Shapelets source code. https://github.com/sliang11/PU-Shapelets
Bagnall, A., Lines, J., Bostrom, A., Large, J., Keogh, E.: The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances. Data Min. Knowl. Discov. 31(3), 606–660 (2017)
Begum, N., Hu, B., Rakthanmanon, T., Keogh, E.: Towards a minimum description length based stopping criterion for semi-supervised time series classification. In: 2013 IEEE 14th International Conference on Information Reuse Integration, pp. 333–340 (2013)
Chen, Y., Hu, B., Keogh, E., Batista, G.: DTW-D: time series semi-supervised learning from a single example. In: Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 383–391 (2013)
Chen, Y., et al.: The UCR time series classification archive, July 2015. www.cs.ucr.edu/~eamonn/time_series_data/
González, M., Bergmeir, C., Triguero, I., RodrÃguez, Y., BenÃtez, J.: On the stopping criteria for k-nearest neighbor in positive unlabeled time series classification problems. Inf. Sci. 328, 42–59 (2016)
Hills, J., Lines, J., Baranauskas, E., Mapp, J., Bagnall, A.: Classification of time series by shapelet transformation. Data Min. Knowl. Discov. 28(4), 851–881 (2014)
Li, X.-L., Liu, B.: Learning from positive and unlabeled examples with different data distributions. In: Gama, J., Camacho, R., Brazdil, P.B., Jorge, A.M., Torgo, L. (eds.) ECML 2005. LNCS (LNAI), vol. 3720, pp. 218–229. Springer, Heidelberg (2005). https://doi.org/10.1007/11564096_24
Ma, J., Sun, L., Wang, H., Zhang, Y., Aickelin, W.: Supervised anomaly detection in uncertain pseudoperiodic data streams. ACM Trans. Internet Technol. 16(1), 4:1–4:20 (2016)
Mueen, A., Keogh, E., Young, N.: Logical-shapelets: an expressive primitive for time series classification. In: Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1154–1162 (2011)
Nguyen, M.N., Li, X., Ng, S.: Positive unlabeled learning for time series classification. In: Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, pp. 1421–1426 (2011)
Nguyen, M.N., Li, X.-L., Ng, S.-K.: Ensemble based positive unlabeled learning for time series classification. In: Lee, S., Peng, Z., Zhou, X., Moon, Y.-S., Unland, R., Yoo, J. (eds.) DASFAA 2012. LNCS, vol. 7238, pp. 243–257. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-29038-1_19
Ratanamahatana, C.A., Wanichsan, D.: Stopping criterion selection for efficient semi-supervised time series classification. In: Lee, R. (ed.) Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing. SCI, vol. 149, pp. 1–14. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-70560-4_1
Sart, D., Mueen, A., Najjar, W., Keogh, E., Niennattrakul, V.: Accelerating dynamic time warping subsequence search with GPUs and FPGAs. In: 2010 IEEE 10th International Conference on Data Mining, pp. 1001–1006 (2010)
Ulanova, L., Begum, N., Keogh, E.: Scalable clustering of time series with U-shapelets. In: Proceedings of the 2015 SIAM International Conference on Data Mining, pp. 900–908 (2015)
Vinh, V.T., Anh, D.T.: Two novel techniques to improve MDL-based semi-supervised classification of time series. In: Nguyen, N.T., Kowalczyk, R., Orłowski, C., Ziółkowski, A. (eds.) Transactions on Computational Collective Intelligence XXV. LNCS, vol. 9990, pp. 127–147. Springer, Heidelberg (2016). https://doi.org/10.1007/978-3-662-53580-6_8
Wei, L., Keogh, E.: Semi-supervised time series classification. In: Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 748–753 (2006)
Ye, L., Keogh, E.: Time series shapelets: a novel technique that allows accurate, interpretable and fast classification. Data Min. Knowl. Discov. 22(1–2), 149–182 (2011)
Zakaria, J., Mueen, A., Keogh, E.: Clustering time series using unsupervised-shapelets. In: 2012 IEEE 12th International Conference on Data Mining, pp. 785–794 (2012)
Zhou, J., Zhu, S., Huang, X., Zhang, Y.: Enhancing time series clustering by incorporating multiple distance measures with semi-supervised learning. J. Comput. Sci. Technol. 30(4), 859–873 (2015)
Zhu, X., Goldberg, A.B.: Introduction to semi-supervised learning. In: Synthesis Lectures on Artificial Intelligence and Machine Learning, vol. 3, no. 1, pp. 1–130 (2009)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Liang, S., Zhang, Y., Ma, J. (2019). PU-Shapelets: Towards Pattern-Based Positive Unlabeled Classification of Time Series. In: Li, G., Yang, J., Gama, J., Natwichai, J., Tong, Y. (eds) Database Systems for Advanced Applications. DASFAA 2019. Lecture Notes in Computer Science(), vol 11446. Springer, Cham. https://doi.org/10.1007/978-3-030-18576-3_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-18576-3_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-18575-6
Online ISBN: 978-3-030-18576-3
eBook Packages: Computer ScienceComputer Science (R0)