Realization of a recursive digital filter based on penalized splines
Kochegurova E.A., Wu D.

 

Tomsk Polytechnic University, Tomsk, Russia

 PDF

Abstract:
In this paper the possibility of development of the recursive digital filter using a P-spline is considered. The frequency and time response of the spline filter for real-time data are analytically obtained and investigated. The influence of the P-spline parameters on effectiveness of interpretation is explored with input metrical data. The patterns obtained during spline filter frequency analysis are confirmed by an example of Doppler function restoration.

Keywords:
penalized spline, smoothing spline, digital filter, impulse infinite response (IIR filter), instrumental function, amplitude and phase-frequency response.

Citation:
Kochegurova EA, D Wu. Realization of a recursive digital filter based on penalized splines. Computer Optics 2018; 42(6): 1083-1092. DOI: 10.18287/2412-6179-2018-42-6-1083-1092.

References:

  1. Lange PK. Correction of the dynamic error of inertial sensors [In Russian]. Vestnik of Samara State Technical University. Technical Sciences Series 2017; 2(54): 58-64.
  2. Sergienko AB. Digital signal processing [In Russian]. Saint-Petersburg: “BHV-Petersburg” Publisher; 2013. ISBN: 978-5-9775-0606-9.
  3. Oppenheim AV, Schafer RW. Discrete-time signal processing. 3rd ed. Pearson; 2009. ISBN: 978-0-13-198842-2.
  4. Bugrov VN. Integer design of iir filters with difficult selective requirements [In Russian]. Digital signal processing 2016; 2: 35-43.
  5. Manolakis D, Ingle V. Applied digital signal processing: Theory and practice. Cambridge: Cambridge University Press; 2011. ISBN: 978-0-521-11002-0.
  6. Karpenkov AS, Grishanovich YuV, Pothekhin DS, Teterin EP. Design procedure of integer digital selection nonrecursive filter with the given Q-factor and suppression level [In Russian]. Vestnik of Lobachevsky University of Nizhni Novgorod 2009; 6-1: 79-85.
  7. Nikitin DA. An algorithm of IIR-filters synthesis on the pulse response applications [In Russian]. Digital signal processing 2009; 4: 8-15.
  8. Davydov AV. Digital signal processing: Thematic lectures [In Russian]. Ekaterinburg: “USMU”, “IgiG”, “GIN”, “Electronic Documents Foundation” Publishers; 2005.
  9. Turulin II, Bulgakova YuI. The technique of synthesis of operated digital filters on the basis of analog prototypes [In Russian]. Izvestiya SFedU. Engineering Sciences 2011; 2(115): 88-92.
  10. Getmanov VG. Evaluation of spline functions for digital filtering problems. Journal of Computer and Systems Sciences International 2016; 55(5): 725-734. DOI: 10.1134/S1064230716040079.
  11. Maystrenko AV, Svetlakov AA. Application of methods of digital signal differentiation to determine a stationary process [In Russian]. Science Bulletin of the Novosibirsk State Technical University 2015; 2(59): 7-19. DOI: 10.17212/1814-1196-2015-2-7-19.
  12.  Zjavka L. Multi-site post-processing of numerical forecasts using a polynomial network substitution for the general differential equation based on operational calculus 2018; 73: 192-202. DOI: 10.1016/j.asoc.2018.08.040.
  13. de Boor C. A practical guide to splines. New York: Springer-Verlag; 2001. ISBN: 978-0-387-95366-3
  14. Redd AA. Comment on the orthogonalization of B-spline basis function and their derivatives. Stat Comput 2012; 22(1): 251-257. DOI: 10.1007/s11222-010-9221-0.
  15. Shumilov BM. Splitting algorithms for the wavelet transform of first-degree splines on nonuniform grids. Comput Math and Math Phys 2016; 56(7): 1209-1219. DOI: 10.1134/S0965542516070174.
  16. Berenguer-Vidal R, Verdú-Monedero R, Morales-Sánchez J. Design of B-spline multidimensional deformable models in the frequency domain. Mathematical and Computer Modelling 2013; 57(7-8): 1942-1949. DOI: 10.1016/j.mcm.2012.01.011.
  17. Gálvez A, Iglesias A. Efficient particle swarm optimization approach for data fitting with free knot B-splines. Computer-Aided Design 2011; 43(12): 1683-1692. DOI: 10.1016/j.cad.2011.07.010.
  18. Krivobokova T, Crainiceanu CM, Kauermann G. Fast adaptive penalized splines. Journal of Computational and Graphical Statistics 2008; 17(1): 1-20. DOI: 10.1198/106186008X287328.
  19. Yang L, Hong Y. Adaptive penalized splines for data smoothing. Computational Statistics and Data Analysis 2017; 108: 70-83. DOI: 10.1016/j.csda.2016.10.022.
  20. Kouibia A, Pasadas M. Approximation by discrete variational splines. Journal of Computational and Applied Mathematics 2000; 116: 145-156. DOI: 10.1016/S0377-0427(99)00316-7.
  21. Tharmaratnam K, Claeskens G, Croux C, Salibián-Barrera M. S-estimation for penalized regression splines. Journal of Computational and Graphical Statistics 2010; 19(3): 609-625. DOI: 10.1198/jcgs.2010.08149.
  22. Cao J, Cai J, Wang L. Estimating curves and derivatives with parametric penalized spline smoothing. Statistics and Computing 2012; 22(5): 1059-1067. DOI: 10.1007/s11222-011-9278-4.
  23. Kochegurova EA, Gorokhova ES. Real-time recovery of functions and their derivatives by variation splines. Key Engineering Materials 2016; 685: 920-924. DOI: 10.4028/www.scientific.net/KEM.685.920.
  24. Eilers PHC, Marx BD. Splines, knots, and penalties. WIREs Computational Statistics 2010; 2(6): 637-653. DOI: 10.1002/wics.125.
  25. Getmanov VG. Algorithms of calculating of approximating spline functions with optimization of the location of spline nodes. Optoelectronics, Instrumentation and Data Processing 2013; 49(1): 21-33. DOI: 10.3103/S8756699013010044.
  26. Denisov VI, Timofeev VS, Faddeenkov AV. Investigation of algorithms for choosing optimal coordinates of nodal points in semiparametric models of penalty splines [In Russian]. Science Bulletin of the Novosibirsk State Technical University 2013; 51 (2): 35-44.
  27. Aydin D, Memmedli M. Optimum smoothing parameter selection for penalized least squares in form of linear mixed effect models. Optimization 2012; 61(4): 459-476. DOI: 10.1080/02331934.2011.574698.
  28. Crainiceanu CM, Ruppert D, Carrol RJ, Joshi A, Goodner B. Spatially adaptive Bayesian penalized splines with heteroscedastic errors. Journal of Computational and Graphical Statistics 2007; 16(2): 265-288.– DOI: 10.1198/106186007X208768.
  29. Walker CG, MacKenzie ML, Donovan CR, O'Sullivan MJ. SALSA – a spatially adaptive local smoothing algorithm. Journal of Statistical Computation and Simulation 2011; 81(2): 179-191. DOI: 10.1080/00949650903229041.
  30. Chicherin IV. Spline-algorithms for processing signals of measuring information in systems of automation of technological processes [In Russian]. The thesis for the Candidate’s degree in Technical Sciences. Novokuznetsk, 2006.
  31. Khutortsev VV, Fedorenko OS. Using of the spline-function method for syntheses of digital filtering algorithms with grouping of the observations [In Russian]. Radioengineering 2010; 2: 4-15.
  32. Kochegurova EA, Gorokhova ES. Current estimation of the derivative of a nonstationary process based on a recurrent smoothing spline. Optoelectronics, Instrumentation and Data Processing 2016; 52(3): 280-285. DOI: 10.3103/S8756699016030109.
  33. Kochegurova EA, Kochegurov AI, Rozhkova NE. Frequency analysis of recurrent variational P-splines. Optoelectronics, Instrumentation and Data Processing 2017; 53(6): 591-598. DOI: 10.3103/S8756699017060085.
  34. Myasnikov VV. Splines as a tool for constructing efficient algorithms of a local linear transform [In Russian]. Computer optics 2007; 31(2): 52-68.
  35. Mihajlovic Z, Goluban A, Zagar M. Frequency domain analysis of B-spline interpolation. Proc IEEE International Symposium on Industrial Electronics 1999; 1: 193-198. DOI: 10.1109/ISIE.1999.801783.
  36. Guo W, Dai M, Ombao HC, Von Sachs R. Smoothing spline ANOVA for time-dependent spectral analysis. Journal of the American Statistical Association 2003; 98(463): 643-652. DOI: 10.1198/016214503000000549.
  37. Raposo-Sánchez MÁ, Sáez-Landete J, Cruz-Roldán F. Analog and digital filters with α-splines. Digital Signal Processing: A Review Journal 2017; 66: 1-9. DOI: 10.1016/j.dsp.2017.03.003.
  38. Kukushkin YA, Maistrov AI, Bogomolov AV. Rhythmocardiogram approximation methods for calculation of spectral parameters of cardiac rhythm variability. Biomedical Engineering 2010; 44(3): 92-103. DOI: 10.1007/s10527-010-9165-x.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20