Abstract
Many real-world applications in time series classification fall into the class of positive and unlabeled (PU) learning. Furthermore, in many of these applications, not only are the negative examples absent, the positive examples available for learning can also be rather limited. As such, several PU learning algorithms for time series classification have recently been developed to learn from a small set P of labeled seed positive examples augmented with a set U of unlabeled examples. The key to these algorithms is to accurately identify the likely positive and negative examples from U, but it has remained a challenge, especially for those uncertain examples located near the class boundary. This paper presents a novel ensemble based approach that restarts the detection phase several times to probabilistically label these uncertain examples more robustly so that a reliable classifier can be built from the limited positive training examples. Experimental results on time series data from different domains demonstrate that the new method outperforms existing state-of-the art methods significantly.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Olszewski, R.T.: Generalized Feature Extraction for Structural Pattern Recognition in Time-Series Data, PhD thesis, Carnegie Mellon University, Pittsburgh, PA (2001)
Rath, T.M., Manmatha, R.: Word image matching using dynamic time warping. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. II-521–II-527 (2003)
Xi, X., Keogh, E., Shelton, C., Wei, L., Ratanamahatana, C.A.: Fast time series classification using numerosity reduction. In: Proceedings of the 23rd International Conference on Machine Learning. ACM, Pittsburgh (2006)
Chapelle, O., Scholkopf, B., Zien, A.: Semi-Supervised Learning. MIT Press (2006) (in Press)
Li, M., Zhou, Z.-H.: SETRED: Self-Training with Editing. In: Ho, T.-B., Cheung, D., Liu, H. (eds.) PAKDD 2005. LNCS (LNAI), vol. 3518, pp. 611–621. Springer, Heidelberg (2005)
Zhu, X.: Semi-supervised learning literature survey, Technical report, no.1530, Computer Sciences, University of Wisconsin-Madison (2008)
Liu, T., Du, X., Xu, Y., Li, M.-H., Wang, X.: Partially Supervised Text Classification with Multi-Level Examples. In: AAAI (2011)
Gabriel Pui Cheong, F., Yu, J.X., Hongjun, L., Yu, P.S.: Text classification without negative examples revisit. IEEE Transactions on Knowledge and Data Engineering 18, 6–20 (2006)
Li, X., Liu, B.: Learning to classify texts using positive and unlabeled data. In: Proceedings of the 18th International Joint Conference on Artificial Intelligence. Morgan Kaufmann Publishers Inc., Acapulco (2003)
Li, X., Liu, B., Ng, S.-K.: Learning to Identify Unexpected Instances in the Test Set. In: Proceedings of Twentieth International Joint Conference on Artificial Intelligence, India (IJCAI 2007), pp. 2802–2807 (2007)
Li, X., Yu, P., Liu, B., Ng, S.-K.: Positive Unlabeled Learning for Data Stream Classification. In: SDM, pp. 257–268 (2009)
Liu, B., Lee, W.S., Yu, P.S., Li, X.: Partially Supervised Classification of Text Documents. In: ICML (2002)
Elkan, C., Noto, K.: Learning Classifiers from Only Positive and Unlabeled Data. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2008)
Wei, L., Keogh, E.: Semi-supervised time series classification. In: Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, Philadelphia (2006)
Ratanamahatana, C., Wanichsan, D.: Stopping Criterion Selection for Efficient Semi-supervised Time Series Classification. In: Lee, R. (ed.) Soft. Eng., Arti. Intel., Net. & Para./Distri. Comp. SCI, vol. 149, pp. 1–14. Springer, Heidelberg (2008)
Nguyen, M.N., Li, X., Ng, S.-K.: Positive Unlabeled Learning for Time Series Classification. In: Proceedings of International Joint Conference on Artificial Intelligence, IJCAI (2011)
Kanungo, T., Mount, D.M., Netanyahu, N.S., Piatko, C.D., Silverman, R., Wu, A.Y.: An efficient k-means clustering algorithm: analysis and implementation. IEEE Transactions on Pattern Analysis and Machine Intelligence 24, 881–892 (2002)
Keogh, E., Kasetty, S.: On the Need for Time Series Data Mining Benchmarks: A Survey and Empirical Demonstration. Data Mining and Knowledge Discovery 7, 349–371 (2003)
Yoon, H., Yang, K., Shahabi, C.: Feature subset selection and feature ranking for multivariate time series. IEEE Transactions on Knowledge and Data Engineering 17, 1186–1198 (2005)
Wilson, D.L.: Asymptotic Properties of Nearest Neighbor Rules Using Edited Data. IEEE Transactions on Systems, Man and Cybernetics 2, 408–421 (1972)
Wei, L.: Self Training dataset (2007), http://alumni.cs.ucr.edu/~wli/selfTraining/
Keogh, E.: The UCR Time Series Classification/Clustering Homepage (2008), http://www.cs.ucr.edu/~eamonn/time_series_data/
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Nguyen, M.N., Li, XL., Ng, SK. (2012). Ensemble Based Positive Unlabeled Learning for Time Series Classification. In: Lee, Sg., Peng, Z., Zhou, X., Moon, YS., Unland, R., Yoo, J. (eds) Database Systems for Advanced Applications. DASFAA 2012. Lecture Notes in Computer Science, vol 7238. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-29038-1_19
Download citation
DOI: https://doi.org/10.1007/978-3-642-29038-1_19
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-29037-4
Online ISBN: 978-3-642-29038-1
eBook Packages: Computer ScienceComputer Science (R0)