Dynamic Symbolization of Streaming Time Series

  • Xiaoming Jin
  • Jianmin Wang
  • Jiaguang Sun
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3177)

Abstract

Symbolization of time series is an important preprocessing subroutine for many data mining tasks. However, it is usually difficult, if not impossible, to apply the traditional static symbolization approach on streaming time series, because of either the low efficiency of re-computing the typical sub-series, or the low capability of representing the up-to-date series characters. This paper presents a novel symbolization method, in which the typical sub-series are dynamically adjusted to fit the up-to-date characters of streaming time series. It works in an incremental form without scanning the whole date set. Experiments on data set from stock market justify the superiority of the proposed method over the traditional ones.

Keywords

Data mining symbolization stream time series 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Zhu, Y., Shasha, D.: Fast approaches to simple problems in financial time series streams. In: Workshop on management and processing of data streams (2003)Google Scholar
  2. 2.
    Yao, Z., Gao, L., Wang, X.S.: Using triangle inequality to efficiently process continuous queries on high-dimensional streaming time series. In: Proc. of SSDBM 2003 (2003)Google Scholar
  3. 3.
    Jin, X., Lu, Y., Shi, C.: Distribution discovery: local analysis of temporal rules. In: Chen, M.-S., Yu, P.S., Liu, B. (eds.) PAKDD 2002. LNCS (LNAI), vol. 2336, p. 469. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  4. 4.
    Radhakrishnan, N., Wilson, J., Loizou, P.: An alternate partitioning technique to quantify the regularity of complex time series. International Journal of Bifurcation and Chaos 10(7), 1773–1779 (2000)CrossRefGoogle Scholar
  5. 5.
    Das, G., Lin, K., Mannila, H., Renganathan, G., Smyth, P.: Rule discovery from time series. In: Proc. of the 4th International Conference on Knowledge Discovery and Data Mining, KDD 1998 (1998)Google Scholar
  6. 6.
    Agrawal, R., Psaila, G., Wimmers, E., Zaot, M.: Querying shapes of histories. In: Proc. of the 21st international conference on very large database, VLDB 1995 (1995)Google Scholar
  7. 7.
    Keogh, E., Lin, J., Truppel, W.: Clustering of time series subsequences is meaningless. In: Proc. of ICDM 2003 (2003)Google Scholar
  8. 8.
    Rakesh, A., Christos, F.: Efficient similarity search in sequence databases. In: Lomet, D.B. (ed.) FODO 1993. LNCS, vol. 730, Springer, Heidelberg (1993)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Xiaoming Jin
    • 1
  • Jianmin Wang
    • 1
  • Jiaguang Sun
    • 1
  1. 1.School of SoftwareTsinghua UniversityBeijingChina

Personalised recommendations