Advertisement

Bag of recurrence patterns representation for time-series classification

  • Nima Hatami
  • Yann Gavet
  • Johan Debayle
Theoretical Advances
First Online:
Received:
Accepted:

Abstract

Time-series classification (TSC) has attracted a lot of attention in pattern recognition, because wide range of applications from different domains such as finance and health informatics deal with time-series signals. Bag-of-features (BoF) model has achieved a great success in TSC task by summarizing signals according to the frequencies of “feature words” of a data-learned dictionary. This paper proposes embedding the recurrence plots (RP), a visualization technique for analysis of dynamic systems, in the BoF model for TSC. While the traditional BoF approach extracts features from 1D signal segments, this paper uses the RP to transform time-series into 2D texture images and then applies the BoF on them. Image representation of time-series enables us to explore different visual descriptors that are not available for 1D signals and to treat TSC task as a texture recognition problem. Experimental results on the UCI time-series classification archive demonstrates a significant accuracy boost by the proposed bag of recurrence patterns, compared not only to the existing BoF models, but also to the state-of-the art algorithms.

Keywords

Time-series classification (TSC) Bag of features (BoF) representation Visual words Dictionary Recurrence plots (RP) 
This is a preview of subscription content, log in to check access.

Notes

Acknowledgements

This research is partially supported by the French national research agency (ANR) under the PANDORE Grant with reference number ANR-14-CE28-0027.

N. Hatami also acknowledges support of the LABEX PRIMES (ANR-11-LABX-0063) of Université de Lyon, within the program “Investissements d’Avenir” (ANR-11-IDEX-0007) operated by the ANR.

References

  1. 1.
    Acharya U, Sree S, Chattopadhyay S, Yu W, Ang P (2011) Application of recurrence quantification analysis for the automated identification of epileptic EEG signals. Int J Neural Syst 21(03):199–211CrossRefGoogle Scholar
  2. 2.
    Allili M (2012) Wavelet modeling using finite mixtures of generalized Gaussian distributions: application to texture discrimination and retrieval. IEEE Trans Image Process 21(4):1452–1464MathSciNetCrossRefzbMATHGoogle Scholar
  3. 3.
    Armano G, Chira C, Hatami N (2012) Error-correcting output codes for multi-label text categorization. In: 3rd Italian information retrieval workshop (IIR), pp 26–37Google Scholar
  4. 4.
    Bailly A, Malinowski S, Tavenard R, Guyet T, Chapel L (2015) Bag-of-temporal-sift-words for time series classification. In: ECML/PKDD workshop on advanced analytics and learning on temporal dataGoogle Scholar
  5. 5.
    Bailly A, Malinowski S, Tavenard R, Guyet T, Chapel L (2016) Dense bag-of-temporal-sift-words for time series classification. Lecture Notes in Artificial IntelligenceGoogle Scholar
  6. 6.
    Baydogan M, Runger G (2016) Time series representation and similarity based on local auto patterns. Data Min Knowl Discov 30(2):476–509MathSciNetCrossRefGoogle Scholar
  7. 7.
    Baydogan M, Runger G, Tuv E (2013) A bag-of-features framework to classify time series. IEEE Trans PAMI 35(11):2796–2802CrossRefGoogle Scholar
  8. 8.
    Bromuri S, Zufferey D, Hennebert J, Schumacher M (2014) Multi-label classification of chronically ill patients with bag of words and supervised dimensionality reduction algorithms. J Biomed Inform 51:165–175CrossRefGoogle Scholar
  9. 9.
    Chang C, Lin C (2011) Libsvm: a library for support vector machines. ACM Trans Intell Syst Technol 2(3):27CrossRefGoogle Scholar
  10. 10.
    Chen Y, Keogh E, Hu B, Begum N, Bagnall A, Mueen A, Batista G (2015) The ucr time series classification archiveGoogle Scholar
  11. 11.
    Chen Y, Yang H (2012) Multiscale recurrence analysis of long-term nonlinear and nonstationary time series. Chaos Solitons Fractals 45(7):978–987CrossRefGoogle Scholar
  12. 12.
    Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. CVPR, San DiegoCrossRefGoogle Scholar
  13. 13.
    Dong Y, Feng J, Liang L, Zheng L (2017) Multiscale Sampling Based Texture Image Classification. IEEE Signal Process Lett 24(5):614–618CrossRefGoogle Scholar
  14. 14.
    Dong Y, Tao D, Li X, Ma J, Pu J (2015) Texture classification and retrieval using shearlets and linear regression. IEEE Trans Cybern 45(3):358–369CrossRefGoogle Scholar
  15. 15.
    Eads D, Glocer K, Perkins S, Theiler J (2005) Grammar-guided feature extraction for time series classification. NIPSGoogle Scholar
  16. 16.
    Eckmann JP, Kamphorst SO, Ruelle D (1987) Recurrence plots of dynamical systems. Europhys Lett 4(9):973–977CrossRefGoogle Scholar
  17. 17.
    Fu Z, Lu G, Ting K, Zhang D (2011) Music classification via the bag-of-features approach. Pattern Recognit Lett 32(14):1768–1777CrossRefGoogle Scholar
  18. 18.
    Geurts P (2009) Pattern extraction for time series classification. In: 5th EU conference principles of data mining and knowledge discovery, pp 115–127Google Scholar
  19. 19.
    Grabocka J, Wistuba M, Schmidt-Thieme L (2015) Scalable classification of repetitive time series through frequencies of local polynomials. IEEE Trans Knowl Data Eng 27(6):1683–1695CrossRefGoogle Scholar
  20. 20.
    Hatami N, Gavet Y, Debayle J (2017) Classification of time-series images using deep convolutional neural networks. In: International conference on machine vision (ICMV)Google Scholar
  21. 21.
    Hatami N (2008) Thinned ecoc decomposition for gene expression based cancer classification. In: 8th IEEE Conference on intelligent systems design and applications, pp 216–221Google Scholar
  22. 22.
    Hatami N (2012a) Some proposals for combining ensemble classifiers. Ph.D. thesis, University of CagliariGoogle Scholar
  23. 23.
    Hatami N (2012b) Thinned-ecoc ensemble based on sequential code shrinking. Expert Syst Appl 39(1):936–947CrossRefGoogle Scholar
  24. 24.
    Hatami N, Chira C (2013) Classifiers with a reject option for early time-series classification. In: IEEE symposium on computational intelligence and ensemble learning (CIEL), pp 9–16Google Scholar
  25. 25.
    Hatami N, Ebrahimpour R, Ghaderi R (2008) Ecoc-based training of neural networks for face recognition. In: IEEE conference on cybernetics and intelligent systems, pp 450–454Google Scholar
  26. 26.
    Jeong Y, Jeong M, Omitaomu O (2011) Weighted dynamic time warping for time series classification. Pattern Recognit 44(9):2231–2240CrossRefGoogle Scholar
  27. 27.
    Keogh E, Kasetty S (2003) On the need for time series data mining benchmarks: a survey and empirical demonstration. Data Min Knowl Discov 7(4):349–371MathSciNetCrossRefGoogle Scholar
  28. 28.
    Kumar N, Lolla V, Keogh E, Lonardi S, Ratanamahatana C, Wei L (2005) Time-series bitmaps: a practical visualization tool for working with large time series databases. In SIAM international conference on data mining, pp 531–535Google Scholar
  29. 29.
    Lategahn H, Gross S, Stehle T, Aach T (2010) Texture classification by modeling joint distributions of local patterns with Gaussian mixtures. IEEE Trans image Process 19(6):1548–1557MathSciNetCrossRefzbMATHGoogle Scholar
  30. 30.
    Lin J, Khade R, Li Y (2012) Rotation-invariant similarity in time series using bag-of-patterns representation. J Intell Inf Syst 39(2):287–315CrossRefGoogle Scholar
  31. 31.
    Lowe D (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110CrossRefGoogle Scholar
  32. 32.
    Marwan N, Romano MC, Thiel M, Kurths J (2007) Recurrence plots for the analysis of complex systems. Phys Rep 438(5–6):237–329MathSciNetCrossRefGoogle Scholar
  33. 33.
    Marwan N, Wessel N, Meyerfeldt U, Schirdewan A, Kurths J (2002) Recurrence plot based measures of complexity and its application to heart rate variability data. Phys Rev E 66(2):026702CrossRefzbMATHGoogle Scholar
  34. 34.
    Marwan N, Kurths J (2009) Comment on stochastic analysis of recurrence plots with applications to the detection of deterministic signals by rohde et al.[physica d 237 (2008) 619629]</CHECK>. Physica D 238:1711–1715CrossRefzbMATHGoogle Scholar
  35. 35.
    Mehta R, Eguiazarian K (2016) Texture classification using dense micro-block difference. IEEE Trans Image Process 25(4):1604–1616MathSciNetCrossRefGoogle Scholar
  36. 36.
    Nanopoulos A, Alcock R, Manolopoulos Y (2001) Feature-based classification of time-series data. Int J Comput Res 10:49–61Google Scholar
  37. 37.
    Ojala T, Pietikainen M, Maenpaa T (2002) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. TPAMI 7(24):971–987CrossRefzbMATHGoogle Scholar
  38. 38.
    Ratanamahatana C, Keogh E (2004) Making time-series classification more accurate using learned constraints. In: Proceedings of SIAM International Conference on Data Mining, pp 11–22Google Scholar
  39. 39.
    Rodriguez J, Alonso C (2004) Interval and dynamic time warping-based decision trees. In: ACM symposium on applied computing, pp 548–552Google Scholar
  40. 40.
    Rodriguez J, Alonso C, Maestro J (2005) Support vector machines of interval-based features for time series classification. Knowl Based Syst 18:171–178CrossRefGoogle Scholar
  41. 41.
    Rohde G, Nichols J, Dissinger B, Bucholtz F (2008) Stochastic analysis of recurrence plots with applications to the detection of deterministic signals. Phys D Nonlinear Phenom 237(5):619–629MathSciNetCrossRefzbMATHGoogle Scholar
  42. 42.
    Roma G, Nogueira W, Herrera P, de Boronat R (2013) Recurrence quantification analysis features for auditory scene classification. In: IEEE AASP challenge on detection and classification of acoustic scenes and eventsGoogle Scholar
  43. 43.
    Schafer P (2015) The boss is concerned with time series classification in the presence of noise. Data Min Knowl Discov 29(6):1505–1530MathSciNetCrossRefGoogle Scholar
  44. 44.
    Senin P, Malinchik S (2013) Sax-vsm: Interpretable time series classification using sax and vector space model. In: IEEE 13th international conference on data mining (ICDM), pp 1175–1180Google Scholar
  45. 45.
    Souza V, Silva D, Batista G (2013) Time series classification using compression distance of recurrence plots. In: IEEE 13th international conference on data mining, pp 687–696Google Scholar
  46. 46.
    Souza V, Silva D, Batista G (2014) Extracting texture features for time series classification. In: 22nd international conference on pattern recognition (ICPR), pp 1425–1430Google Scholar
  47. 47.
    Thiel M, Romano MC, Kurths J (2003) Analytical description of recurrence plots of white noise and chaotic processes,.arXiv:nlin/0301027Google Scholar
  48. 48.
    Ueno K, Xi X, Keogh E, Lee D (2007) Anytime classification using the nearest neighbour algorithm with applications to stream mining. In: IEEE international conference on data mining, pp 623–632Google Scholar
  49. 49.
    Wang J, Liu P, She M, Nahavandi S, Kouzani A (2013) Bag-of-words representation for biomedical time series classification. Biomed Signal Process Control 8(6):634–644CrossRefGoogle Scholar
  50. 50.
    Wang J, Yang J, Yu K, Lv F, Huang T, Gong Y (2010) Locality-constrained linear coding for image classification. In: CVPR, pp 3360–3367Google Scholar
  51. 51.
    Wang Z, Oates T (2014) Time warping symbolic aggregation approximation with bag-of-patterns representation for time series classification. In: 13th international conference on machine learning and applications (ICMLA), pp 270–275Google Scholar
  52. 52.
    Wang Z, Oates T (2015) Pooling sax-bop approaches with boosting to classify multivariate synchronous physiological time series data. In: FLAIRS conference, pp 335–341Google Scholar
  53. 53.
    Xing Z, Pei J, Yu P (2011) Early prediction on time series: a nearest neighbor approach. Int Joint Conf Artif Intell 2168:1297–1302Google Scholar
  54. 54.
    Yang J, Yu K, Gong Y, Huang T (2009) Linear spatial pyramid matching using sparse coding for image classification. In: CVPR, pp 1794–1801Google Scholar
  55. 55.
    Yang H (2011) Multiscale recurrence quantification analysis of spatial cardiac vectorcardiogram signals. IEEE Trans Biomed Eng 58(2):339–347CrossRefGoogle Scholar
  56. 56.
    Zbilut JP, Webber CL Jr (1992) Embeddings and delays as derived from quantification of recurrence plots. Phys Lett A 171(3–4):199–203CrossRefGoogle Scholar
  57. 57.
    Zhang M, Sawchuk A (2012) Motion primitive-based human activity recognition using a bag-of-features approach. In: ACM SIGHIT symposium on international health informatics (IHI), pp 631–640Google Scholar
  58. 58.
    Zhao J, Itti L (2016) Classifying time series using local descriptors with hybrid sampling. IEEE Trans Knowl Data Eng 28:623–637CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2018

Authors and Affiliations

  1. 1.The SPIN center, École Nationale Supérieure des Mines de Saint-ÉtienneSaint-ÉtienneFrance
  2. 2.CREATIS centerINSA-Lyon and University of LyonLyonFrance

Personalised recommendations

Cite article

Buy options