Nonlinear complex LS-SVM for highly selective OFDM channel with impulse noise

In this contribution, channel estimation for OFDM system in high mobility environment with the presence of Gaussian and non-Gaussian impulse noise with different ranges interfering with reference signals is faced. The estimation of the frequency selective time varying multipath fading channel is performed by using a nonlinear channel estimator based on a complex Least Squares Support Vector Machine (LS-SVM) which is developed and applied to Long Term Evolution (LTE) downlink. The estimation algorithm makes use of the pilot signals to estimate the total frequency response of the frequency selective multipath channel. Thus, the algorithm maps trained data into a high dimensional feature space (possibly infinity) and uses the structural risk minimization (SRM) principle to carry out the regression estimation for the frequency response function of the fading channel. The obtained results confirm the effectiveness of the proposed approach which outperforms the conventional LS and Decision Feedback methods to track the fading channel variations.