Title :
A robust support vector algorithm for nonparametric spectral analysis
Author :
Rojo-Álvarez, José Luis ; Martínez-Ramón, Manel ; Figueiras-Vidal, Aníbal R. ; García-Armada, Ana ; Artés-Rodríguez, AndAntonio
Author_Institution :
Dept. of Signal Theor. & Commun., Univ. Carlos III de Madrid, Leganes, Spain
Abstract :
We present a new approach to nonparametric spectral estimation on the basis of the support vector method (SVM). A reweighted least squares error formulation avoids the computational limitations of quadratic programming. The application to a synthetic example and to a digital communication problem shows the robustness of the SVM spectral analysis algorithm.
Keywords :
channel estimation; digital subscriber lines; impulse noise; learning automata; least squares approximations; spectral analysis; ADSL channel estimation; SVM; impulsive noise; nonparametric spectral analysis; nonparametric spectral estimation; quadratic programming; reweighted least squares error formulation; support vector algorithm; support vector method; Communication systems; Cost function; Fourier transforms; Iterative algorithms; Least squares methods; Quadratic programming; Robustness; Spectral analysis; Support vector machine classification; Support vector machines;
Journal_Title :
Signal Processing Letters, IEEE
DOI :
10.1109/LSP.2003.818866
