Constrained Randomization of Time Series Data

  title={Constrained Randomization of Time Series Data},
  author={Thomas Schreiber},
A new method is introduced to create artificial time sequences that fulfil given constraints but random otherwise. Constraints are usually derived from a measured signal for which surrogate da to be generated. They are fulfilled by minimizing a suitable cost function using simulated annea A wide variety of structures can be imposed on the surrogate series, including multivariate, nonli and nonstationary properties. When the linear correlation structure is to be preserved, the new app avoids… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.


Publications citing this paper.
Showing 1-10 of 56 extracted citations

Signal processing on graphs for improving automatic credit card fraud detection

2017 International Carnahan Conference on Security Technology (ICCST) • 2017
View 1 Excerpt


Publications referenced by this paper.
Showing 1-4 of 4 references

Physica (Amsterdam) 58D

J. Theiler, S. Eubank, A. Longtin, B. Galdrikian, J. D Farmer
77 • 1992
View 5 Excerpts
Highly Influenced


T. Schreiber, A. Schmitz
Rev. E 55, 5443 • 1997

Physica (Amsterdam) 94D

J. Theiler, D. Prichard
221 • 1996
View 1 Excerpt

The Jackknife

B. Efron
the Bootstrap and Other Resam pling Plans • 1982
View 1 Excerpt

Similar Papers

Loading similar papers…