论文信息 - Sur un test temps-frequence de stationnarite

Sur un test temps-frequence de stationnarite

On propose un nouveau test de stationnarite auquel l'utilisation de substituts temps-frequence permet de donner un sens statistique precis. Le test est relatif a une duree d'observation et peut s'appliquer a des bandes de frequence, donnant un cadre a ce qui est souvent fait en pratique. Un degre de non-stationnarite peut etre attache au test, ainsi que, le cas echeant, une echelle caracteristique de la non-stationnarite detectee.

[1] Jun Xiao,et al. Testing Stationarity with Surrogates - A One-Class SVM Approach , 2007, 2007 IEEE/SP 14th Workshop on Statistical Signal Processing.

[2] James Theiler,et al. Testing for nonlinearity in time series: the method of surrogate data , 1992 .

[3] Jun Xiao,et al. Testing stationarity with time-frequency surrogates , 2007, 2007 15th European Signal Processing Conference.

[4] Patrick Flandrin,et al. Time-Frequency/Time-Scale Analysis , 1998 .

[5] Schreiber,et al. Improved Surrogate Data for Nonlinearity Tests. , 1996, Physical review letters.

[6] C. Doncarli,et al. Stationarity index for abrupt changes detection in the time-frequency plane , 1996, IEEE Signal Processing Letters.

[7] P. Flandrin,et al. Detection of changes of signal structure by using the Wigner-Ville spectrum , 1985 .

[8] Anthony Widjaja,et al. Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2003, IEEE Transactions on Neural Networks.

[9] W. Martin. Measuring the degree of non-stationarity by using the Wigner-Ville spectrum , 1984, ICASSP.

[10] Jun Xiao,et al. Multitaper Time-Frequency Reassignment for Nonstationary Spectrum Estimation and Chirp Enhancement , 2007, IEEE Transactions on Signal Processing.

[11] Richard G. Baraniuk,et al. Multiple Window Time Varying Spectrum Estimation , 2000 .