Estimation of highly selective channels for OFDM system by complex least squares support vector machines

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 dimensional feature space and uses the structural risk minimization (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 channel. Simulation results show that the proposed method has better performance compared to the conventional LS and Decision Feedback methods and it is more robust at high speed mobility.