Autoregressive frequency detection using Regularized Least Squares

Tracking of an unknown frequency embedded in noise is widely applied in a variety of applications. Unknown frequencies can be obtained by approximating generalized spectral density of a periodic process by an autoregressive (AR) model. The advantage is that an AR model has a simple structure and its parameters can be easily estimated iteratively, which is crucial for online (real-time) applications. Typically, the order of the AR approximation is chosen by information criteria. However, with an increase of a sample size, model order may change, which leads to re-estimation of all model parameters. We propose a new iterative procedure for frequency detection based on a regularization of an empirical information matrix. The suggested method enables to avoid the repeated model selection as well as parameter estimation steps and therefore optimize computational costs. The asymptotic properties of the proposed regularized AR (RAR) frequency estimates are derived and performance of RAR is evaluated by numerical examples.

[1]  L. Breuer.  Introduction to Stochastic Processes , 2022, Statistical Methods for Climate Scientists.

[2]  Christian Léger,et al.  Bootstrap adaptive estimation: The trimmed-mean example , 1990 .

[3]  Ian B. MacNeill,et al.  Applied probability, stochastic processes, and sampling theory , 1986 .

[4]  Dawei Huang,et al.  ON LOW AND HIGH FREQUENCY ESTIMATION , 1996 .

[5]  T. Bengtsson,et al.  Estimation of high-dimensional prior and posterior covariance matrices in Kalman filter variants , 2007 .

[6]  C. Radhakrishna Rao,et al.  Asymptotic behavior of maximum likelihood estimates of superimposed exponential signals , 1993, IEEE Trans. Signal Process..

[7]  Chen Zhao-Guo.  AN ALTERNATIVE CONSISTENT PROCEDURE FOR DETECTING HIDDEN FREQUENCIES , 1988 .

[8]  Richard A. Davis,et al.  Time Series: Theory and Methods , 2013 .

[9]  D. B. Preston.  Spectral Analysis and Time Series , 1983 .

[10]  Rainer Dahlhaus,et al.  Hidden Frequency Estimation with Data Tapers , 2000 .

[11]  Barry G. Quinn,et al.  The Estimation and Tracking of Frequency , 2001 .

[12]  Olivier Ledoit,et al.  A well-conditioned estimator for large-dimensional covariance matrices , 2004 .

[13]  Johannes Ledolter,et al.  Statistical methods for forecasting , 1983 .

[14]  Petre Stoica,et al.  Asymptotic bias of the high-order autoregressive estimates of sinusoidal frequencies , 1987 .

[15]  Robert Andersen.  Modern Methods for Robust Regression , 2007 .

[16]  A. Barabanov,et al.  Strong consistency of the regularized least-squares estimates of infinite autoregressive models , 2007 .

[17]  A. M. Walker.  On the estimation of a harmonic component in a time series with stationary independent residuals , 1971 .

[18]  Michael J. Artis,et al.  Analyzing Strongly Periodic Series in the Frequency Domain: A Comparison of Alternative Approaches with Applications , 2007 .

[19]  Langford B. White,et al.  Asymptotic statistical properties of AR Spectral estimators for processes with mixed spectra , 2002, IEEE Trans. Inf. Theory.

[20]  S.M. Kay,et al.  Spectrum analysis—A modern perspective , 1981, Proceedings of the IEEE.

[21]  V. Pisarenko.  The Retrieval of Harmonics from a Covariance Function , 1973 .

[22]  Petre Stoica,et al.  Asymptotic properties of the high-order Yule-Walker estimates of sinusoidal frequencies , 1989, IEEE Trans. Acoust. Speech Signal Process..

[23]  P. Bickel,et al.  Regularized estimation of large covariance matrices , 2008, 0803.1909.

[24]  Juan Toro,et al.  The detection of hidden periodicities: A comparison of alternative methods , 2004 .

[25]  Ed. McKenzie.  10. Time Series Analysis by Higher Order Crossings , 1996 .

[26]  R. Kumaresan,et al.  Estimation of frequencies of multiple sinusoids: Making linear prediction perform like maximum likelihood , 1982, Proceedings of the IEEE.

[27]  P. Bickel,et al.  Banded regularization of autocovariance matrices in application to parameter estimation and forecasting of time series , 2011 .

[28]  Barry G. Quinn.  On Kay's frequency estimator , 2000 .

[29]  D. Brillinger.  Fitting Cosines: Some Procedures and Some Physical Examples , 1987 .

[30]  P. Bickel,et al.  Covariance regularization by thresholding , 2009, 0901.3079.

[31]  E. J. Hannan,et al.  ON‐LINE FREQUENCY ESTIMATION , 1993 .

[32]  T. Hasan.  NONLINEAR TIME SERIES REGRESSION FOR A CLASS OF AMPLITUDE MODULATED CONSINUSOIDS , 1982 .

[33]  M. S. Mackisack,et al.  Autoregressive frequency estimation , 1989 .

[34]  Steven Kay,et al.  Modern Spectral Estimation: Theory and Application , 1988 .

[35]  M. S. Mackisack,et al.  SOME PROPERTIES OF AUTOREGRESSIVE ESTIMATES FOR PROCESSES WITH MIXED SPECTRA , 1990 .

[36]  Ta-Hsin Li,et al.  Asymptotic normality of sample autocovariances with an application in frequency estimation , 1994 .

[37]  Hideaki Sakai,et al.  Statistical analysis of Pisarenko's method for sinusoidal frequency estimation , 1984 .

[38]  Ta-Hsin Li,et al.  Tracking abrupt frequency changes , 1998 .

[39]  Peter Händel,et al.  Two algorithms for adaptive retrieval of slowly time-varying multiple cisoids in noise , 1995, IEEE Trans. Signal Process..

[40]  Steven Kay,et al.  Accurate frequency estimation at low signal-to-noise ratio , 1984 .

[41]  Yulia R. Gel,et al.  Identification of an unstable ARMA equation , 2001 .

[42]  Ronald K. Pearson,et al.  BMC Bioinformatics BioMed Central Methodology article , 2005 .

[43]  V. N. Fomin.  Filtering of stochastic processes , 1999 .