NEW METHOD FOR STRUCTURAL CHANGE DETECTION OF TIME SERIES AS AN OPTIMAL STOPPING PROBLEM

Hiromichi Kawano, Ken Nishimatsu, Tetsuo Hattori

2004

Abstract

In general, an appropriate prediction expression and/or model is constructed to fit a time series though, the model begins to unfit (or not to fit) the time series from some time point, especially in the field that relates to human activity and social phenomenon. In such case, it will be important not only to quickly detect the unfitting situation but also to rebuild the prediction model after the detection as soon as possible. In this paper, we formulate the structural change detection problem in time series as an optimal stopping problem, using the concept of DP (Dynamic Programming) with a cost function that is the sum of unfitting (or not fitting) loss and action cost to be taken after detection. And we propose a method for optimal solution and show the correctness by proving a theorem. Also we clarify the effectiveness by showing the numerical experimentation.

References

  1. R.Jana and S.Dey, 2000. Change detection in Teletraffic Models. IEEE Trans. Signal Processing, vol.48, No.3, pp.846-853, March 2000.
  2. R.M.Gagliardi and I.S.Reed, 1965. On the Sequential detection of Emerging Targets. IEEE Trans. Information Theory, vol.6, pp.260-263, April 1965.
  3. R.J.Di Francesco, 1990. Real-Time Speech segmentation Using Pitch and Convexity Jump Models. IEEE Trans. Acoustics, Speech, Signal Processing, vol.38, pp.741- 748, May 1990.
  4. A.S.Willsky, 1996. A survey of design methods for failure detection in dynamic systems. Automatica, Vol.12. pp. 601-611, Sept. 1996.
  5. D.Kauame and J.P.remenieras et al., 1996. Effect of The Compensation In Abrupt Model Change Detection Problem. Proc. of IEEE Digital Signal Processing Workshop, pp.311-314, Sept. 1996.
  6. Chow,G.C., 1960. Tests of Equality Between Sets of Coefficients in Two Linear Regressions. Econometrica, Vol.28, No.3, pp.591-605, July 1960.
  7. S.MacDougall, A.K.Nandi and R.Chapman, 1998. Multisolution and hybrid Bayesian algorithms for automatic detection of change points. Proc. of IEEE Visual Image Signal Processing, vol.145, No.4, pp.280-286, August 1998.
  8. V.V.Veeravalli and A.G.Tartakovsky, 2002. Asymptotics of quickest change detection procedures under a Bayesian criterion. ITW2002, pp.100-103, Bangalore, India, Oct. 2002.
  9. E.S.Page, 1954. Continuous inspection schemes. Biometrika, Vol. 41, pp.100-115, 1954.
  10. C.Han,P.k.Willet and D.A.Abraham, 1999. Some methods to evaluate the performance of Page's test as used to detect transient signals. IEEE Trans. Signal processing, vol.47, No.8, pp.2112-2127, August 1999.
  11. S.D.Blostein, 1991. Quickest detection of a time-varying change in distribution. IEEE Trans. Information Theory, vol.37, No.4, pp.1116-1122, July 1991. Y.Liu, S.D.Blostein, 1994. Quickest detection of an abrupt change in a random sequence with finite change-time. IEEE Trans. Information Theory, vol.40, No.6, pp.1985-1993, Nov. 1994.
  12. M.Basseville and I.V.Nikiforov, 1993. Detection and Application, Prentice Hall, Inc., April 1993.
  13. M.Basseville, 1988.Detecting Changes in signals and systems- A survey. Automatica,Vol.24, pp.309- 326, 1988.
  14. N.R.Draper, H.Smith, 1996. Applied Regression Analysis, John Wiley & Sons Inc, 1966.
Download


Paper Citation


in Harvard Style

Kawano H., Nishimatsu K. and Hattori T. (2004). NEW METHOD FOR STRUCTURAL CHANGE DETECTION OF TIME SERIES AS AN OPTIMAL STOPPING PROBLEM . In Proceedings of the First International Conference on Informatics in Control, Automation and Robotics - Volume 3: ICINCO, ISBN 972-8865-12-0, pages 24-31. DOI: 10.5220/0001147500240031


in Bibtex Style

@conference{icinco04,
author={Hiromichi Kawano and Ken Nishimatsu and Tetsuo Hattori},
title={NEW METHOD FOR STRUCTURAL CHANGE DETECTION OF TIME SERIES AS AN OPTIMAL STOPPING PROBLEM},
booktitle={Proceedings of the First International Conference on Informatics in Control, Automation and Robotics - Volume 3: ICINCO,},
year={2004},
pages={24-31},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001147500240031},
isbn={972-8865-12-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Informatics in Control, Automation and Robotics - Volume 3: ICINCO,
TI - NEW METHOD FOR STRUCTURAL CHANGE DETECTION OF TIME SERIES AS AN OPTIMAL STOPPING PROBLEM
SN - 972-8865-12-0
AU - Kawano H.
AU - Nishimatsu K.
AU - Hattori T.
PY - 2004
SP - 24
EP - 31
DO - 10.5220/0001147500240031