Deep learning-based channel estimation in MIMO system for pilot decontamination

The next-generation wireless communication system makes use of the upcoming technology known as massive multiple-input multiple-output (MIMO). The imprecise channel estimation leads to enormous error in communication, and this cause pilot contamination (PC), which is a major concern in the massive MIMO system. An efficient invasive shuffled shepherd optimisation (ISSO)-deep maxout-based channel estimate approach is proposed, which chooses the optimal channel in the massive MIMO system to avoid interference among nearby cells, reducing contamination of pilot sequences. Shuffled shepherd optimisation (SSO) and improved invasive weed optimisation (IWO) are combined to develop the proposed ISSO method. The deep maxout network is trained using the proposed ISSO technique, and the weight factors are computed using the loss function. The proposed channel estimation methodology produced bit error rate (BER) and mean square error (MSE) results for the Rayleigh channel of 0.0009 and 0.00070 and for the Rician channel of 0.0009 and 0.0007.