Statistical hypothesis testing with time-frequency surrogates to check signal stationarity

Cédric Richard 1 André Ferrari 1 Hassan Amoud 2 Paul Honeine 2 Patrick Flandrin 3 Pierre Borgnat 3
1 FIZEAU - Laboratoire Hippolyte Fizeau
2 LM2S - Laboratoire Modélisation et Sûreté des Systèmes
ICD - Institut Charles Delaunay
3 Phys-ENS - Laboratoire de Physique de l'ENS Lyon
Abstract : An operational framework is developed for testing stationarity relatively to an observation scale. The proposed method makes use of a family of stationary surrogates for defining the null hypothesis of stationarity. As a further contribution to the field, we demonstrate the strict-sense stationarity of surrogate signals and we exploit this property to derive the asymptotic distributions of their spectrogram and power spectral density. A statistical hypothesis testing framework is then proposed to check signal stationarity. Finally, some results are shown on a typical model of signals that can be thought of as stationary or nonstationary, depending on the observation scale used.
Keywords : Time-frequency analysis Stationarity test Surrogate Spectrogram Probability density function
Document type :
Conference papers
Complete list of metadatas

Cited literature [8 references]  Display  Hide  Download
https://hal-ens-lyon.archives-ouvertes.fr/ensl-00476017
Contributor : Pierre Borgnat <>
Submitted on : Friday, April 23, 2010 - 2:33:39 PM
Last modification on : Monday, September 16, 2019 - 4:35:46 PM
Long-term archiving on : Tuesday, September 28, 2010 - 1:23:08 PM

File

icassp10_article_surrogate.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : ensl-00476017, version 1

Collections

UNICE | INSU | FIZEAU | OCA | ENS-LYON | UNIV-COTEDAZUR | UNIV-LYON1 | ROSAS | UTT

Citation

Cédric Richard, André Ferrari, Hassan Amoud, Paul Honeine, Patrick Flandrin, et al.. Statistical hypothesis testing with time-frequency surrogates to check signal stationarity. IEEE International Conference on Acoustics, Speech, and Signal Processing ICASSP-10, Mar 2010, Dallas, United States. ⟨ensl-00476017⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

465

Files downloads

383

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD