1d-SAX: A Novel Symbolic Representation for Time Series

  • Simon Malinowski
  • Thomas Guyet
  • René Quiniou
  • Romain Tavenard
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8207)

Abstract

SAX (Symbolic Aggregate approXimation) is one of the main symbolization techniques for time series. A well-known limitation of SAX is that trends are not taken into account in the symbolization. This paper proposes 1d-SAX a method to represent a time series as a sequence of symbols that each contain information about the average and the trend of the series on a segment. We compare the efficiency of SAX and 1d-SAX in terms of goodness-of-fit, retrieval and classification performance for querying a time series database with an asymmetric scheme. The results show that 1d-SAX improves performance using equal quantity of information, especially when the compression rate increases.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Esling, P., Agon, C.: Time-series data mining. ACM Comput. Surv. 45(1), 1–34 (2012)CrossRefGoogle Scholar
  2. 2.
    Esmael, B., Arnaout, A., Fruhwirth, R.K., Thonhauser, G.: Multivariate time series classification by combining trend-based and value-based approximations. In: Murgante, B., Gervasi, O., Misra, S., Nedjah, N., Rocha, A.M.A.C., Taniar, D., Apduhan, B.O. (eds.) ICCSA 2012, Part IV. LNCS, vol. 7336, pp. 392–403. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  3. 3.
    Hung, N.Q.V., Anh, D.T.: Combining SAX and Piecewise Linear Approximation to improve similarity search on financial time series. In: Proc. of the Int. Symp. on Information Technology Convergence (ISITC), pp. 58–62 (2007)Google Scholar
  4. 4.
    Jégou, H., Douze, M., Schmid, C.: Product quantization for nearest neighbor search. IEEE Transactions on Pattern Analysis and Machine Intelligence 33(1), 117–128 (2011)CrossRefGoogle Scholar
  5. 5.
    Keogh, E., Zhu, Q., Hu, B., Hao, Y., Xi, X., Wei, L., Ratanamahatana, C.A.: The UCR times series classification/clustering homepage (2011)Google Scholar
  6. 6.
    Li, G., Zhang, L., Yang, L.: TSX: A novel symbolic representation for financial time series. In: Anthony, P., Ishizuka, M., Lukose, D. (eds.) PRICAI 2012. LNCS, vol. 7458, pp. 262–273. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  7. 7.
    Lin, J., Keogh, E.J., Lonardi, S., Chiu, B.Y.: A symbolic representation of time series, with implications for streaming algorithms. In: Proc. of the 8th ACM SIGMOD Workshop on Research Issues in Data Mining and Knowledge Discovery, pp. 2–11 (2003)Google Scholar
  8. 8.
    Lkhagva, B., Suzuki, Y., Kawagoe, K.: New time series data representation esax for financial applications. In: Proc. of the 22nd Int. Conf. on Data Engineering Workshops, pp. 17–22 (2006)Google Scholar
  9. 9.
    Pham, N.D., Le, Q.L., Dang, T.K.: Two novel adaptive symbolic representations for similarity search in time series databases. In: Proc. of the 12th Asia-Pacific Web Conference (APWeb), pp. 181–187 (2010)Google Scholar
  10. 10.
    Shieh, J., Keogh, E.: iSAX: Indexing and mining terabyte sized time series. In: Proc. of the ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining (2008)Google Scholar
  11. 11.
    Zalewski, W., Silva, F., Lee, H.D., Maletzke, A.G., Wu, F.C.: Time series discretization based on the approximation of the local slope information. In: Pavón, J., Duque-Méndez, N.D., Fuentes-Fernández, R. (eds.) IBERAMIA 2012. LNCS, vol. 7637, pp. 91–100. Springer, Heidelberg (2012)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Simon Malinowski
    • 1
  • Thomas Guyet
    • 1
  • René Quiniou
    • 2
  • Romain Tavenard
    • 3
  1. 1.AGROCAMPUS-OUEST/ IRISA-UMR 6074RennesFrance
  2. 2.Centre de Recherche INRIA Rennes Bretagne AtlantiqueFrance
  3. 3.IDIAP Research InstituteMartignySwitzerland

Personalised recommendations