An Improved Stationarity Test Based on Surrogates

Over the last years, several stationarity tests have been proposed. One of these methods uses time-frequency representations and stationarized replicas of the signal (known as surrogates) for testing wide-sense stationarity. In this letter, we propose a procedure to improve the original surrogate test. The proposed methodology can be seen as a guideline on how the surrogate test can be improved. We show mathematically that the modified test should exhibit improved classification performance. Numerical simulations on synthetic and real-world signals are carried out to evaluate the modified test against competing ones.

[1]  Syed Ismail Shah,et al.  Techniques to Obtain Good Resolution and Concentrated Time-Frequency Distributions: A Review , 2009, EURASIP J. Adv. Signal Process..

[2]  Jocelyn Chanussot,et al.  A nonparametric test for slowly-varying nonstationarities , 2018, Signal Process..

[3]  Wei Biao Wu,et al.  Testing parametric assumptions of trends of a nonstationary time series , 2011 .

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

[5]  Jie Ding,et al.  Evolutionary Spectra Based on the Multitaper Method with Application To Stationarity Test , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[6]  Anne-Catherine Favre,et al.  Statistical inference in Lombard's smooth‐change model , 2011 .

[7]  Jocelyn Chanussot,et al.  A modified time-frequency method for testing wide-sense stationarity , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[8]  H. Lins,et al.  Stationarity: Wanted Dead or Alive? 1 , 2011 .

[9]  Zbigniew Leonowicz,et al.  Parametric methods for time-frequency analysis of electric signals , 2006 .

[10]  D. Blumenfeld.  Operations Research Calculations Handbook , 2001 .

[11]  A. Grimm,et al.  Components of multifractality in the central England temperature anomaly series. , 2012, Chaos.

[12]  Dimitris G. Manolakis,et al.  Statistical and Adaptive Signal Processing: Spectral Estimation, Signal Modeling, Adaptive Filtering and Array Processing , 1999 .

[13]  Agathoklis Giaralis,et al.  Determination of non-stationary stochastic processes compatible with seismic response/design spectra , 2011 .

[14]  Steven Kay,et al.  A New Nonstationarity Detector , 2008, IEEE Transactions on Signal Processing.

[15]  Paul Honeine,et al.  Testing Stationarity With Surrogates: A Time-Frequency Approach , 2010, IEEE Transactions on Signal Processing.

[16]  T. Abhayapala,et al.  Wigner-Ville distribution of a type of non-stationary mobile Rayleigh fading channels , 2009, 2009 IEEE 13th International Multitopic Conference.

[17]  F. Lombard.  Rank tests for changepoint problems , 1987 .

[18]  Prabahan Basu,et al.  A nonparametric test for stationarity based on local Fourier analysis , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[19]  M. S. Rahman,et al.  Time-frequency representation of a signal through non-stationary multipath fading channel , 2012, 2012 International Conference on Informatics, Electronics & Vision (ICIEV).

[20]  Yang Li,et al.  High-resolution time-frequency analysis of EEG signals using multiscale radial basis functions , 2016, Neurocomputing.

[21]  Jie Ding,et al.  Estimation of the Evolutionary Spectra With Application to Stationarity Test , 2018, IEEE Transactions on Signal Processing.

[22]  P. Phillips,et al.  Testing the null hypothesis of stationarity against the alternative of a unit root: How sure are we that economic time series have a unit root? , 1992 .

[23]  Boualem Boashash,et al.  Time-Frequency Signal Analysis and Processing: A Comprehensive Reference , 2015 .

[24]  T. Schreiber,et al.  Surrogate time series , 1999, chao-dyn/9909037.

[25]  David J. Thomson,et al.  The Seasons, Global Temperature, and Precession , 1995, Science.

[26]  Md. Arif Khan,et al.  A Test for Non-Stationarity of Synchrophasor Measurements , 2018, 2018 IEEE International Conference on Probabilistic Methods Applied to Power Systems (PMAPS).

[27]  T. Benner.  Central England temperatures: long‐term variability and teleconnections , 1999 .

[28]  Gerald Matz,et al.  Wigner distributions (nearly) everywhere: time-frequency analysis of signals, systems, random processes, signal spaces, and frames , 2003, Signal Process..

[29]  Guang Meng,et al.  Characterize highly oscillating frequency modulation using generalized Warblet transform , 2012 .

[30]  Cheng-Xiang Wang,et al.  A non-stationary MIMO channel model for street corner scenarios considering velocity variations of the mobile station and scatterers , 2017, 2017 IEEE/CIC International Conference on Communications in China (ICCC).

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

[32]  Abdelhak M. Zoubir,et al.  Radar classification of human gait abnormality based on sum-of-harmonics analysis , 2018, 2018 IEEE Radar Conference (RadarConf18).

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

[34]  M. Basseville.  Distance measures for signal processing and pattern recognition , 1989 .

[35]  Rameshwar Rao,et al.  Performance Analysis of Basis Functions in TVAR Model , 2014 .

[36]  Zhipeng Feng,et al.  Iterative generalized time–frequency reassignment for planetary gearbox fault diagnosis under nonstationary conditions , 2016 .

[37]  Tommaso Proietti,et al.  Seasonal changes in central England temperatures , 2015 .

[38]  Patrick Flandrin,et al.  Maximum signal energy concentration in a time-frequency domain , 1988, ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing.

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