Recursive solutions to indirect sensing measurement problems by a generalized innovations approach

  • Edoardo Mosca
System Modelling And Identification
Part of the Lecture Notes in Computer Science book series (LNCS, volume 27)


For a wide class of applications referred to as indirect-sensing experiments, a systematic approach yielding solutions in recursive form is established. Indirectsensing experiments include problems of estimation, filtering, system identification, and interpolation and smoothing by splines. Our approach is based on the novel notion of a discrete-time generalized (not necessarily stochastic) innovations process. The discrete-time linear least-squares filtering problem is used to relate the new concept to the familiar one of a stochastic innovations process. An application to the problem of identifying recursively impulse responses and system parameters by using pseudorandom binary sequences as probing inputs is considered. Further, the problem of interpolation and smoothing by splines is approached by the method developed.


Impulse Response Innovation Process Recursive Formula Reproduce Kernel Hilbert Space Recursive Form 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    A.W. Naylor and G.R. Sell, Linear Operator Theory in Engineering and Science, New York Holt, Rinehart and Winston, 1971, pp. 345.Google Scholar
  2. 2.
    D.G. Luenberger, Optimization by vector space methods, New York:Wiley, 1969, ch.6.Google Scholar
  3. 3.
    E. Mosca, "System identification by reproducing kernel Hilbert space methods", in Preprints 2nd Prague IFAC Symp. Identification and Process Parameter Estimation, Prague, Czechoslovakia: Academia, 1970, paper 1.1Google Scholar
  4. 4.
    E. Mosca, "A deterministic approach to a class of nonparametric system identification problems", IEEE Trans.Inform.Theory, vol. IT-17, pp. 686–696, Nov. 1971.Google Scholar
  5. 5.
    E. Mosca, "Determination of Volterra Kernels from input-output data", Int.J.Systems Sci., vol. 3, pp. 357–374, 1972.Google Scholar
  6. 6.
    D. Graupe, Identification of System, New York: Van nonstrand Reinhold, 1972, Ch.4.Google Scholar
  7. 7.
    K.R. Godfrey, "The application of pseudo-random sequences to industrial processes and nuclear power plant", in Preprints 2nd Prague IFAC Symp. Identification and Process Parameter Estimation, Prague, Czechoslovakia: Academia, 1970, paper 7.1.Google Scholar
  8. 8.
    P.N. Nikiforku, M.M. Gupta and R. Hoffman, "Identification of linear discrete systems in the presence of drift using pseudorandom sequences", in Preprints 2nd Prague IFAC Symp. Identification and Process Parameter Estimation, Prague, Czechoslovakia:Academia, 1970, paper 7.Google Scholar
  9. 9.
    N. Aronszajn, "Theory of reproducing kernels", Trans.Amer.Math.Soc., vol. 68, pp. 337–404, 1950.Google Scholar
  10. 10.
    E. Parzen, Times Series Analysis Papers, San Francisco:Holden-Day, 1971.Google Scholar
  11. 11.
    H.L.Weinert, "A reproducing kernel Hilbert space approach to spline problems with applications in estimation and control", Info. System Lab. Stanford Univ., Tech.Rept.7001–6, May 1972.Google Scholar
  12. 12.
    E. Mosca, "Stochastic extension and functional restrictions of ill-posed estimation problems", Lecture Notes in Computer Scien.: 5th IFIP Conf.Optimiz.Techniques, vol. 3, New York:Springer-verlag, 1973, pp. 57–68.Google Scholar
  13. 13.
    T.E.N. Greville, Theory and applications of spline functions, New York:Academic Press, 1969.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1975

Authors and Affiliations

  • Edoardo Mosca
    • 1
  1. 1.Facoltà di IngegneriaUniversità di FirenzeFirenzeItaly

Personalised recommendations