Online ML-based Joint Channel Estimation and MIMO Decoding for Dynamic Channels

TL;DR

This paper introduces an online neural network-based approach for joint channel estimation and decoding in massive MIMO-OFDM systems, demonstrating improved accuracy and convergence in realistic 5G scenarios.

Contribution

It evaluates various complex-valued neural network architectures for joint estimation and decoding, highlighting the effectiveness of RBF-based CVNNs in dynamic wireless environments.

Findings

RBF-based CVNNs outperform other architectures in MSE and BER.

C-RBF and PT-RBF architectures show the best performance.

The proposed methods are suitable for next-generation wireless systems.

Abstract

This paper presents an online method for joint channel estimation and decoding in massive MIMO-OFDM systems using complex-valued neural networks (CVNNs). The study evaluates the performance of various CVNNs, such as the complex-valued feedforward neural network (CVFNN), split-complex feedforward neural network (SCFNN), complex radial basis function (C-RBF), fully-complex radial basis function (FC-RBF) and phase-transmittance radial basis function (PT-RBF), in realistic 5G communication scenarios. Results demonstrate improvements in mean squared error (MSE), convergence, and bit error rate (BER) accuracy. The C-RBF and PT-RBF architectures show the most promising outcomes, suggesting that RBF-based CVNNs provide a reliable and efficient solution for complex and noisy communication environments. These findings have potential implications for applying advanced neural network techniques in next-generation wireless systems.