Bayesian Neural Network Detector for an Orthogonal Time Frequency Space Modulation

The orthogonal time frequency space (OTFS) modulation is proposed for beyond 5G wireless systems to deal with high mobility communications. existing low complexity OTFS detectors’ performance suboptimal in rich scattering environments where there are a large number of moving reflectors that reflect the transmitted signal towards receiver. In this letter, we propose an detector, referred as BPICNet detector integrates NN, Bayesian inference, and parallel interference cancellation concepts. Simulation results show outperforms state-of-the-art.