Unsupervised Interpretable Pattern Discovery in Time Series Using Autoencoders

  • Kevin Bascol
  • Rémi Emonet
  • Elisa FromontEmail author
  • Jean-Marc Odobez
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10029)


We study the use of feed-forward convolutional neural networks for the unsupervised problem of mining recurrent temporal patterns mixed in multivariate time series. Traditional convolutional autoencoders lack interpretability for two main reasons: the number of patterns corresponds to the manually-fixed number of convolution filters, and the patterns are often redundant and correlated. To recover clean patterns, we introduce different elements in the architecture, including an adaptive rectified linear unit function that improves patterns interpretability, and a group-lasso regularizer that helps automatically finding the relevant number of patterns. We illustrate the necessity of these elements on synthetic data and real data in the context of activity mining in videos.


Mean Square Error Multivariate Time Series Stochastic Gradient Descent Restrict Boltzmann Machine Suppression Layer 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



This work has been supported by the ANR project SoLStiCe (ANR-13-BS02-0002-01).


  1. 1.
    Baccouche, M., Mamalet, F., Wolf, C., Garcia, C., Baskurt, A.: Spatio-temporal convolutional sparse auto-encoder for sequence classification. In: British Machine Vision Conference (BMVC) (2012)Google Scholar
  2. 2.
    Chockalingam, T., Emonet, R., Odobez, J.-M.: Localized anomaly detection via hierarchical integrated activity discovery. In: AVSS (2013)Google Scholar
  3. 3.
    Darken, C., Moody, J.E.: Note on learning rate schedules for stochastic optimization. In: NIPS, pp. 832–838 (1990)Google Scholar
  4. 4.
    Du, X., Jin, R., Ding, l., Lee, V.E., Thornton, J.H.: Migration motif: a spatial- temporal pattern mining approach for nancial markets. In: KDD, pp. 1135–1144. ACM (2009)Google Scholar
  5. 5.
    Emonet, R., Varadarajan, J., Odobez, J.-M.: Multi-camera open space human activity discovery for anomaly detection. In: IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS), Klagenfurt, Austria, August 2011Google Scholar
  6. 6.
    Emonet, R., Varadarajan, J., Odobez, J.-M.: Temporal analysis of motif mixtures using dirichlet processes. IEEE PAMI 36(1), 140–156 (2014)CrossRefGoogle Scholar
  7. 7.
    Marwah, M., Shao, H., Ramakrishnan, N.: A temporal motif mining approach to unsupervised energy disaggregation: applications to residential and commercial buildings. In: Proceedings of the 27th AAAI Conference (2013)Google Scholar
  8. 8.
    Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)MathSciNetCrossRefzbMATHGoogle Scholar
  9. 9.
    Hospedales, T., Gong, S., Xiang, T.: A Markov clustering topic model for mining behavior in video. In: ICCV (2009)Google Scholar
  10. 10.
    Kolter, J.Z., Jaakkola, T.: Approximate inference in additive factorial HMMs with application to energy disaggregation. In: Proceedings of AISTATS Conference (2012)Google Scholar
  11. 11.
    Karlsson, L., Längkvist, M., Loutfi, A.: A review of unsupervised feature learning and deep learning for time-series modeling. Pattern Recognit. Lett. 42, 11–24 (2014)CrossRefGoogle Scholar
  12. 12.
    Masci, J., Meier, U., Cireşan, D., Schmidhuber, J.: Stacked convolutional auto-encoders for hierarchical feature extraction. In: Honkela, T., Duch, W., Girolami, M., Kaski, S. (eds.) ICANN 2011. LNCS, vol. 6791, pp. 52–59. Springer, Heidelberg (2011). doi: 10.1007/978-3-642-21735-7_7 CrossRefGoogle Scholar
  13. 13.
    Mehta, N.A., Gray, A.G.: Funcica for time series pattern discovery. In: Proceedings of the SIAM International Conference on Data Mining, pp. 73–84 (2009)Google Scholar
  14. 14.
    Memisevic, R., Hinton, G.E.: Unsupervised learning of image transformations. In: Computer Vision and Pattern Recognition (CVPR) (2007)Google Scholar
  15. 15.
    Mooney, C.H., Roddick, J.F.: Sequential pattern mining - approaches, algorithms. ACM Comput. Surv. 45(2), 19:1–19:39 (2013)CrossRefzbMATHGoogle Scholar
  16. 16.
    Oates, T.: PERUSE: an unsupervised algorithm for finding recurring patterns in time series. In: ICDM (2002)Google Scholar
  17. 17.
    Ranzato, M., Poultney, C., Chopra, S., LeCun, Y.: Efficient learning of sparse representations with an energy-based model. In: NIPS. MIT Press (2006)Google Scholar
  18. 18.
    Sallaberry, A., Pecheur, N., Bringay, S., Roche, M., Teisseire, M.: Sequential patterns mining and gene sequence visualization to discover novelty from microarray data. J. Biomed. Inform. 44(5), 760–774 (2011)CrossRefGoogle Scholar
  19. 19.
    Tavenard, R., Emonet, R., Odobez, J.-M.: Time-sensitive topic models for action recognition in videos. In: International Conference on Image Processing (ICIP), Melbourne (2013)Google Scholar
  20. 20.
    Varadarajan, J., Emonet, R., Odobez, J.-M.: A sparsity constraint for topic models - application to temporal activity mining. In: NIPS Workshop on Practical Applications of Sparse Modeling: Open Issues and New Directions (2010)Google Scholar
  21. 21.
    Varadarajan, J., Emonet, R., Odobez, J.-M.: A sequential topic model for mining recurrent activities from long term video logs. Int. J. Comput. Vis. 103(1), 100–126 (2013)MathSciNetCrossRefzbMATHGoogle Scholar
  22. 22.
    Chu, W.-S., Zhou, F., Torre, F.: Unsupervised temporal commonality discovery. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7575, pp. 373–387. Springer, Heidelberg (2012). doi: 10.1007/978-3-642-33765-9_27 CrossRefGoogle Scholar
  23. 23.
    Peng, W.-C., Chen, Y.-C., Lee, S.-Y.: Mining temporal patterns in time interval-based data. IEEE Trans. Knowl. Data Eng. 27(12), 3318–3331 (2015)CrossRefGoogle Scholar
  24. 24.
    Yuan, M., Lin, Y.: Model selection and estimation in regression with grouped variables. J. R. Stat. Soc. (B) 68(1), 49–67 (2006)MathSciNetCrossRefzbMATHGoogle Scholar
  25. 25.
    Zheng, Y.: Trajectory data mining: an overview. ACM Trans. Intell. Syst. Technol. 6(3), 29:1–29:41 (2015)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Kevin Bascol
    • 1
  • Rémi Emonet
    • 1
  • Elisa Fromont
    • 1
    Email author
  • Jean-Marc Odobez
    • 2
  1. 1.Univ Lyon, UJM-Saint-Etienne, CNRS, Institut d’Optique Graduate School, Laboratoire Hubert Curien UMR 5516Saint-EtienneFrance
  2. 2.Idiap Research InstituteMartignySwitzerland

Personalised recommendations