Nonlinear Channel Equalization with Gaussian Processes for Regression Articles uri icon

authors

  • PEREZ CRUZ, FERNANDO
  • MURILLO FUENTES, JUAN JOSE
  • CARO, SEBASTIAN

publication date

  • October 2008

start page

  • 5283

end page

  • 5286

issue

  • 10

volume

  • 56

international standard serial number (ISSN)

  • 1053-587X

electronic international standard serial number (EISSN)

  • 1941-0476

abstract

  • We propose Gaussian processes for regression as a novel nonlinear equalizer for digital communications receivers. GPR's main advantage, compared to previous nonlinear estimation approaches, lies on their capability to optimize the kernel hyperparameters by maximum likelihood, which improves its performance significantly for short training sequences. Besides, GPR can be understood as a nonlinear minimum mean square error estimator, a standard criterion for training equalizers that trades-off the inversion of the channel and the amplification of the noise. In the experiment section, we show that the GPR-based equalizer clearly outperforms support vector machine and kernel adaline approaches, exhibiting outstanding results for short training sequences.