Chirag Pradhan

Hybrid CNN-LSTM Channel Estimation for 5G Massive MIMO Systems using Sparse Pilot Reconstruction and Time-Varying 3GPP Channels

A two-stage hybrid deep learning estimator is proposed in which least-squares estimates at pilots placed at every twelfth subcarrier are expanded by two-dimensional bilinear interpolation and refined by a time-distributed convolutional neural network coupled with a long short-term memory (LSTM) recurrent stage.