Semi-blind Channel Estimation of MIMO-OFDM System Based on Extreme Learning Machine

In this paper, a novel semi-blind channel estimate method is proposed for a multi-input multi-output orthogonal frequency division multiplexing (MIMO-OFDM) system with time-varying frequency selective fading channels. The channel estimation approach presented is based on ELM (extreme learning machine) which does not experience training bottleneck imposed by gradient descent-based approaches. Simulation results show that the ELM outperform other gradient descent-based feed forward neural networks by using the proposed estimation method in terms of Bit error rate(BER), mean square error (MSE) performances and estimating speed.