Abstract
A channel estimator using complex Least Squares
Support Vector Machines (LS-SVM) is proposed for pilot-aided
OFDM system and applied to Long Term Evolution (LTE)
downlink. This channel estimation algorithm use knowledge of
the pilot signals to estimate the total frequency response of the
channel. Thus, the algorithm maps trained data into a high di-
mensional feature space and uses the structural risk minimiza-
tion (SRM) principle, which minimizes an upper bound on the
generalization error, to carry out the regression estimation for
the frequency response function of the highly selective chan-
nel. Simulation results show that the proposed method has bet-
ter performance compared to the conventional LS and Decision
Feedback methods and it is more robust at high speed mobility.
Users
Please
log in to take part in the discussion (add own reviews or comments).