Robust Probabilistic Online Change Detection Algorithm Based On the Continuous Wavelet Transform

In this article we present a change point detection algorithm based on the continuous wavelet transform. At the beginning of the article we describe a necessary transformation of a signal which has to be made for the purpose of change detection. Then case study related to iron ore sinter production which can be solved using our proposed technique is discussed. After that we describe a probabilistic algorithm which can be used to find changes using our transformed signal. It is shown that our algorithm works well with the presence of some noise and abnormal random bursts.





References:
[1] Popov A., Zhukov M., Computation of continuous wavelet transform of
discrete signals with adapted mother functions, Proceedings of the SPIE,
vol. 7502, pp. 75021E-75021E-6, 2009.
[2] Bassville M., Nikiforov I.,Detection of abrupt changes. Theory and
application, Pretince-Hall, Englewood Cliffs, New Jersey, 1993.
[3] Burrus C., Ramesh A., Introduction to wavelets and wavelet transforms:
A Primer, Pretince-Hall, New Jersey, 1998.
[4] Charles K., An introduction to wavelets, Academic Press, New York,
1992.
[5] Degroot M., Schervish M., Probability and Statistics, Pearson Education,
Carnegie-Mellon University, 2011.
[6] German R., Sintering theory and practice, John Wiley and Sons, New
York, 1996.
[7] Wald A., Sequential Analysis, John Wiley and Sons, New York, 1947.