• DocumentCode
    2582579
  • Title

    Time-varying channel characterization based on SVM under the impulsive noise presence

  • Author

    Dias, João ; De Campos, Fabrício P V ; De Campos, Marcello L R ; Pinto, Ernesto L. ; Ribeiro, Moisés V.

  • Author_Institution
    Electr. Eng. Program, Fed. Univ. of Rio de Janeiro, Rio de Janeiro, Brazil
  • fYear
    2010
  • fDate
    28-31 March 2010
  • Firstpage
    261
  • Lastpage
    266
  • Abstract
    The purpose of this work is to present an off-line technique for characterization of time-varying power line communications channels in the presence of additive impulsive noise when they are used for broadband data transmission. We propose and analyze a channel estimation technique based on Support Vector Machine (SVM). Simulation results reveal that the proposed method is more robust to impulsive noise and has better convergence rate for time-varying channels when compared to classic techniques like least squares (LS).
  • Keywords
    broadband networks; channel estimation; data communication; impulse noise; least squares approximations; support vector machines; telecommunication computing; time-varying systems; SVM; additive impulsive noise; broadband data transmission; channel estimation technique; impulsive noise; least squares techniques; support vector machine; time-varying channel characterization; time-varying power line communications channels; Additive noise; Channel estimation; Data engineering; Least squares methods; Military communication; Noise robustness; Power line communications; Programmable control; Support vector machines; Time-varying channels; Power line communication; additive impulsive noise; support vector machine; time-varying channel characterization;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Power Line Communications and Its Applications (ISPLC), 2010 IEEE International Symposium on
  • Conference_Location
    Rio de Janeiro
  • Print_ISBN
    978-1-4244-5009-1
  • Electronic_ISBN
    978-1-4244-5010-7
  • Type

    conf

  • DOI
    10.1109/ISPLC.2010.5479885
  • Filename
    5479885