j991222 / MIMO_JCESD

A Comparative Study of Deep Learning and Iterative Algorithms for Joint Channel Estimation and Signal Detection in OFDM Systems

MIMO_JCESD

Code for the paper

"A Comparative Study of Deep Learning and Iterative Algorithms for Joint Channel Estimation and Signal Detection in OFDM Systems", Signal Processing 223 (2024), 109554., [arxiv version]

We evaluate three DL methods: DeepRx, a lightweight DenseNet adapted to JCESD, and a new unrolled dynamics(UD) model called Hyper-WienerNet, which uses hypernetworks to estimate unknown parameters.