• DocumentCode
    508351
  • Title

    A New Intelligent Algorithm for Designing Digital Filter

  • Author

    Li, Kangshun ; Wang, Ting ; Huang, Ping ; Zhang, Wensheng

  • Author_Institution
    Sch. of Inf. Eng., Jiangxi Univ. of Sci. & Technol., Ganzhou, China
  • Volume
    4
  • fYear
    2009
  • fDate
    14-16 Aug. 2009
  • Firstpage
    103
  • Lastpage
    107
  • Abstract
    Noise reduction is one of the core issues in signal processing, because the noise exists throughout the channel as well as other communication system. And the filtering technology is a conventional technology of noise cancellation. Traditional filtering techniques require some priori statistical knowledge of signal and noise. In this paper, optimal adaptive filters are implemented by using evolutionary algorithm, which don´t need any priori statistical knowledge of signal and noise, and the parameters of these adaptive filters can be automatically adjusted to the best in accordance with certain criteria. Theoretical analysis and simulation results show that it can not only quickly design effective optimal adaptive filters by using evolutionary algorithm, but also can achieve minimal error.
  • Keywords
    adaptive filters; digital filters; evolutionary computation; filtering theory; signal denoising; communication system; digital filter; evolutionary algorithm; filtering technology; intelligent algorithm; noise cancellation; noise reduction; optimal adaptive filters; priori statistical knowledge; signal processing; Adaptive filters; Adaptive signal processing; Algorithm design and analysis; Communication systems; Digital filters; Evolutionary computation; Filtering; Noise cancellation; Noise reduction; Signal processing algorithms; FIR Digital Filter; evolutionary algorithm; mean square error; noise cancellation;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Natural Computation, 2009. ICNC '09. Fifth International Conference on
  • Conference_Location
    Tianjin
  • Print_ISBN
    978-0-7695-3736-8
  • Type

    conf

  • DOI
    10.1109/ICNC.2009.111
  • Filename
    5366902