B-Spline Neural Network Assisted Space-Time Equalization for Single-Carrier Multiuser Nonlinear Frequency-Selective MIMO Uplink

This paper designs a nonlinear space-time equalizer based on B-spline neural network (BSNN) for the singlecarrier high-throughput multiuser frequency-selective multipleinput multiple-output (MIMO) uplink. Specifically, BSNN parametrization of high power amplifiers (NHPAs) at mobile terminals’ transmitters, novel identification scheme is developed to estimate dispersive MIMO uplink channel, which includes models NHPAs transmitters as well channel impulse response (CIR) matrix. Furthermore, inverse are also estimated in closed-form. allows base station implement detection effectively using equalization (STE) frequencyselective CIR matrix and followed by compensating distortion transmitters’ models. Simulation results utilized demonstrate superior bit error rate performance our STE approach single-carrier highthroughput