• DocumentCode
    1270946
  • Title

    New method of designing adaptive nonlinear filters

  • Author

    Rao, K. Deergha ; Reddy, D.C.

  • Author_Institution
    Dept. of Electron. & Commun. Eng., MVSR Coll. of Eng., Osmania Univ., Hyderabad, India
  • Volume
    138
  • Issue
    5
  • fYear
    1991
  • fDate
    10/1/1991 12:00:00 AM
  • Firstpage
    513
  • Lastpage
    519
  • Abstract
    A new method of designing nonlinear filters is proposed. It is shown to be general enough to be applicable to the design of higher order Volterra filters. LMS and fast least squares adaptive algorithms for updating the linear quadratic and cubic weights of a third order nonlinear filter are suggested. Simulation studies are carried out in respect of a third order Volterra filter using the proposed method of design and suggested updating algorithms. The fast least squares implementation is shown to converge to the unknown system parameters considerably faster than the LMS
  • Keywords
    adaptive filters; digital filters; least squares approximations; LMS algorithm; Volterra filters; adaptive nonlinear filters; cubic weights; design; fast least squares adaptive algorithms; quadratic weights; simulation; system parameters; third order nonlinear filter; weights updating;
  • fLanguage
    English
  • Journal_Title
    Radar and Signal Processing, IEE Proceedings F
  • Publisher
    iet
  • ISSN
    0956-375X
  • Type

    jour

  • Filename
    99493