Neural Network and Sparse Block Processing Based Nonlinear Adaptive Equalizer for MIMO OFDM Communication Systems

In the proposed work presented in the paper, adaptive equalizer for MIMO-OFDM system is designed using neural network with functional expansions and neural weights are adjusted using sparse adaptive filter with block processing of input samples. By introducing l0-norm sparsity in the cost function of the block RLS (BRLS), equalization can be achieved for MIMO wireless channels with a comparatively less computational load. Nakagami-m fading channel model is used to represent the dispersive nature of fading wireless channel. 16-QAM constellation format is used to modulate the incoming data. The most important contribution of the paper lies in the inclusion of norm based sparsity in equalizer design which yields a low bit error rate (BER) and mean square error (MSE) even in low SNR conditins.