Improved smoothness priors using bilinear transform

Abstract Smoothness priors is a well-known and most commonly used method in the analysis of stochastic processes making it very useful in the field of stochastic signal processing. It is particularly suited for smoothing the noisy data and detrending the time-series signals. The method is based on an optimization problem where the n-th order derivative of the signal enters as a constraint. When the method is designed in discrete time domain, the backward difference rule is used to perform differential-to-difference conversion. Moreover, the solution depends on a smoothness trade-off parameter. An efficient algorithm for the trade-off parameter selection remains an important and challenging issue. In this paper, first, we propose a closed-form expression for the trade-off parameter. The closed-form expression resulted from a frequency domain interpretation of the smoothness priors procedure. The trade-off parameter determines the amount of frequency components that the procedure allows to pass. We show that the trade-off parameter is related to the arbitrary choice of cutoff frequency. Second, we introduce a new way to the design and implementation of smoothness priors using bilinear transformation method. Frequency analysis and experiments on both synthetic and real world signals with different levels of noise demonstrate that bilinear transform is indeed more effective for smoothness priors implementation when compared with the traditional ones, i.e., the backward difference rule.

[1]  Cewu Lu,et al.  Image smoothing via L0 gradient minimization , 2011, ACM Trans. Graph..

[2]  B. Silverman,et al.  Some Aspects of the Spline Smoothing Approach to Non‐Parametric Regression Curve Fitting , 1985 .

[3]  William A. Sethares,et al.  Smoothing of discontinuous signals: the competitive approach , 1995, IEEE Trans. Signal Process..

[4]  D. M. Titterington,et al.  A Study of Methods of Choosing the Smoothing Parameter in Image Restoration by Regularization , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Fan Zhang,et al.  Bioelectric signal detrending using smoothness prior approach. , 2014, Medical engineering & physics.

[6]  P. Eilers Parametric time warping. , 2004, Analytical chemistry.

[7]  R. Shiller A DISTRIBUTED LAG ESTIMATOR DERIVED FROM SMOOTHNESS PRIORS , 1973 .

[8]  Thomas F. Cooley,et al.  The Inflation Tax in a Real Business Cycle Model , 1988 .

[9]  S. A. Dyer,et al.  The bilinear transformation , 2000 .

[10]  Pascal Frossard,et al.  Learning Laplacian Matrix in Smooth Graph Signal Representations , 2014, IEEE Transactions on Signal Processing.

[11]  A. E. Hoerl,et al.  Ridge regression: biased estimation for nonorthogonal problems , 2000 .

[12]  Hirotugu Akaike,et al.  Likelihood and the Bayes procedure , 1980 .

[13]  Arman Kheirati Roonizi A New Approach to ARMAX Signals Smoothing: Application to Variable-Q ARMA Filter Design , 2019, IEEE Transactions on Signal Processing.

[14]  Genshiro Kitagawa,et al.  Smoothness prior approach to explore mean structure in large-scale time series , 2003, Theor. Comput. Sci..

[15]  H. Akaike Factor analysis and AIC , 1987 .

[16]  Tryphon Kollintzas,et al.  Stylized Facts of Business Cycles in the G7 from a Real Business Cycles Perspective , 1994 .

[17]  Finn E. Kydland,et al.  Time to Build and Aggregate Fluctuations , 1982 .

[18]  R. Shiller,et al.  Smoothness Priors and Nonlinear Regression , 1982 .

[19]  I. Johnstone,et al.  Adapting to Unknown Smoothness via Wavelet Shrinkage , 1995 .

[20]  E. Prescott,et al.  Postwar U.S. Business Cycles: An Empirical Investigation , 1997 .

[21]  G. Moody,et al.  Spontaneous termination of atrial fibrillation: a challenge from physionet and computers in cardiology 2004 , 2004, Computers in Cardiology, 2004.

[22]  Genshiro Kitagawa,et al.  Smoothness Priors ansfer Function Estimation * WILL GERSCHt and GENSHIRO KITAGAWA ¢ , 2002 .

[23]  Andrew W. Fitzgibbon,et al.  Global stereo reconstruction under second order smoothness priors , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[24]  G. Kitagawa,et al.  A Smoothness Priors–State Space Modeling of Time Series with Trend and Seasonality , 1984 .

[25]  Reza Sameni,et al.  Online filtering using piecewise smoothness priors: Application to normal and abnormal electrocardiogram denoising , 2017, Signal Process..

[26]  P. Speckman,et al.  Priors for Bayesian adaptive spline smoothing , 2012 .

[27]  A. Savitzky,et al.  Smoothing and Differentiation of Data by Simplified Least Squares Procedures. , 1964 .

[28]  J. Danthine,et al.  Methodological and Empirical Issues in Real Business Cycle Theory , 1991 .

[29]  Jian Li,et al.  Smoothness Prior Approach to Removing Nonlinear Trends from Signals in Identification of Low Frequency Oscillation Mode , 2014 .

[30]  Mika P. Tarvainen,et al.  An advanced detrending method with application to HRV analysis , 2002, IEEE Transactions on Biomedical Engineering.

[31]  Stephen P. Boyd,et al.  1 Trend Filtering , 2009, SIAM Rev..

[32]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[33]  Paul H. C. Eilers,et al.  Flexible smoothing with B-splines and penalties , 1996 .

[34]  Marianne Baxter,et al.  Measuring Business Cycles: Approximate Band-Pass Filters for Economic Time Series , 1995, Review of Economics and Statistics.

[35]  W. Gersch,et al.  A smoothness priors long AR model method for spectral estimation , 1985, IEEE Transactions on Automatic Control.

[36]  Roberto Sassi,et al.  A Signal Decomposition Model-Based Bayesian Framework for ECG Components Separation , 2016, IEEE Transactions on Signal Processing.

[37]  R. Tibshirani Regression Shrinkage and Selection via the Lasso , 1996 .

[38]  Edmund Taylor Whittaker On a New Method of Graduation , 1922, Proceedings of the Edinburgh Mathematical Society.

[39]  T. N. E. Greville On Smoothing a Finite Table: A Matrix Approach , 1957 .

[40]  Finn E. Kydland,et al.  Business cycles: real facts and a monetary myth , 1990 .

[41]  Valeria Villani,et al.  Baseline wander removal for bioelectrical signals by quadratic variation reduction , 2014, Signal Process..

[42]  B. Silverman,et al.  Nonparametric Regression and Generalized Linear Models: A roughness penalty approach , 1993 .

[43]  A. Tustin A method of analysing the behaviour of linear systems in terms of time series , 1947 .

[44]  E. T. Whittaker VIII.—On the Theory of Graduation , 1925 .

[45]  Patrick J. Kehoe,et al.  International evidence on the historical properties of business cycles , 1992 .

[46]  Gene H. Golub,et al.  Tikhonov Regularization and Total Least Squares , 1999, SIAM J. Matrix Anal. Appl..