Neural network based Equaliser for non-Gaussian noise

The noise that affects underwater acoustic communication (UWAC) is primarily characterised by its non-stationary nature and is predominantly non-Gaussian in distribution. The Minimum Mean Square Error (MMSE) criterion-based receiver/equaliser is suboptimal for Underwater Acoustic Communication (UWAC). An underwater acoustic communication (UWAC) system that is resilient should have the capability to effectively manage a wide range of underwater noise patterns and complex multipath, non-stationary channels with a high level of reliability. To address these challenges, we suggest the deployment of a robust receiver that autonomously handles the communication channel. This receiver would consist of two stages: the first stage would involve a prefilter based on the time-reversal mirror (TRM), while the second stage would utilise a Recurrent Neural Network (RNN). Analysis of the proposed receiver in different scenarios unequivocally demonstrates its superiority over the conventional Decision Feedback Equalise (DFE) and Deep Neural Network (DNN) based receiver. Performance of DFE Equalizer, Proposed RNN(LSTM and GRU)based equalizer and DNN for 500 data rate of 8PSK modulation with the separationof 5km. image