Advertisement

Time Series Classification with Shallow Learning Shepard Interpolation Neural Networks

  • Kaleb E. SmithEmail author
  • Phillip Williams
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10884)

Abstract

Time series classification (TSC) has been an ongoing machine learning problem with countless proposed algorithms spanning a multitude of fields. Whole series, intervals, shapelet, dictionary-based, and model-based are all different past approaches to solving TSC. Then there’s deep learning approaches that try to utilize all the success demonstrated by neural network’s (NN) architecture in image classification to TSC. Deep learning typically requires vast amounts of training data and computational power to have meaningful results. But, what if there was a network inspired not by a biological brain, but that of mathematics proven in theory? Or better yet, what if that network was not as computationally expensive as deep learning networks, which have billions of parameters and need a surplus of training data? This desired network is exactly what the Shepard Interpolation Neural Networks (SINN) provide - a shallow learning approach with minimal training samples needed and a foundation on a statistical interpolation technique to achieve great results. These networks learn metric features which can be more mathematically explained and understood. In this paper, we leverage the novel SINN architecture on a popular benchmark TSC data set achieving state-of-the-art accuracy on several of its test sets while being competitive against the other established algorithms. We also demonstrate that even when there is a lack of training data, the SINN outperforms other deep learning algorithms.

References

  1. 1.
    Bagnall, A., Lines, J., Hills, J., Bostrom, A.: Time-series classification with cote: the collective of transformation-based ensembles. IEEE Trans. Knowl. Data Eng. 27(9), 2522–2535 (2015)CrossRefGoogle Scholar
  2. 2.
    Bagnil, A.: The UEA & UCR time series classification repository. www.timeseriesclassification.com
  3. 3.
    Baydogan, M.G., Runger, G., Tuv, E.: A bag-of-features framework to classify time series. IEEE Trans. Pattern Anal. Mach. Intell. 35(11), 2796–2802 (2013)CrossRefGoogle Scholar
  4. 4.
    Berndt, D.J., Clifford, J.: Using dynamic time warping to find patterns in time series. In: KDD Workshop, vol. 10, pp. 359–370, Seattle, WA (1994)Google Scholar
  5. 5.
    Cetin, M.S., Mueen, A., Calhoun, V.D.: Shapelet ensemble for multi-dimensional time series. In: Proceedings of the 2015 SIAM International Conference on Data Mining, pp. 307–315. SIAM (2015)CrossRefGoogle Scholar
  6. 6.
    Funahashi, K.-I.: On the approximate realization of continuous mappings by neural networks. Neural Netw. 2(3), 183–192 (1989)CrossRefGoogle Scholar
  7. 7.
    Williams, P., Smith, K.E.: Deep convolutional-shepard interpolation neural networks for image classification tasks. In: International Conference Image Analysis Recognition. Springer, Cham (2018)Google Scholar
  8. 8.
    Karim, F., Majumdar, S., Darabi, H., Chen, S.: LSTM fully convolutional networks for time series classification (2017) arXiv preprint arXiv:1709.05206
  9. 9.
    Lines, J., Bagnall, A.: Time series classification with ensembles of elastic distance measures. Data Min. Knowl. Discovery 29(3), 565–592 (2015)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Nanopoulos, A., Alcock, R., Manolopoulos, Y.: Feature-based classification of time-series data. Int. J. Comput. Res. 10(3), 49–61 (2001)Google Scholar
  11. 11.
    Park, J., Sandberg, I.W.: Universal approximation using radialbasis-function networks. Neural Comput. 3(2), 246–257 (1991)CrossRefGoogle Scholar
  12. 12.
    Ren, J.S.J., Xu, L., Yan, Q., Sun, W.: Shepard convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 901–909 (2015)Google Scholar
  13. 13.
    Schäfer, P.: The boss is concerned with time series classification in the presence of noise. Data Min. Knowl. Discovery 29(6), 1505–1530 (2015)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Shepard, D.: A two-dimensional interpolation function for irregularly-spaced data. In: Proceedings of the 1968 23rd ACM National Conference, pp. 517–524. ACM (1968)Google Scholar
  15. 15.
    Wang, Z., Yan, W., Oates, T.: Time series classification from scratch with deep neural networks: a strong baseline. In: 2017 International Joint Conference on Neural Networks (IJCNN), pp. 1578–1585. IEEE (2017)Google Scholar
  16. 16.
    Williams, P.: SINN: shepard interpolation neural networks. In: Bebis, G., et al. (eds.) ISVC 2016. LNCS, vol. 10073, pp. 349–358. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-50832-0_34CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Florida Institute of TechnologyMelbourneUSA
  2. 2.University of OttawaOttawaCanada

Personalised recommendations