Regularized Neural Detection for One-Bit Massive MIMO Communication Systems

TL;DR

This paper proposes a novel deep learning-enhanced gradient descent detector for one-bit massive MIMO systems, improving detection accuracy especially for higher order constellations by integrating regularization and a new loss function.

Contribution

It introduces a deep learning-aided regularization step and a constellation-based loss function into gradient descent detection for one-bit massive MIMO systems, enhancing performance.

Findings

Improved detection accuracy for higher order M-QAM constellations.

Enhanced robustness of the detector across different channel realizations.

Demonstrated superiority over existing methods through numerical simulations.

Abstract

Detection for one-bit massive MIMO systems presents several challenges especially for higher order constellations. Recent advances in both model-based analysis and deep learning frameworks have resulted in several robust one-bit detector designs. Our work builds on the current state-of-the-art gradient descent (GD)-based detector. We introduce two novel contributions in our detector design: (i) We augment each GD iteration with a deep learning-aided regularization step, and (ii) We introduce a novel constellation-based loss function for our regularized DNN detector. This one-bit detection strategy is applied to two different DNN architectures based on algorithm unrolling, namely, a deep unfolded neural network and a deep recurrent neural network. Being trained on multiple randomly sampled channel matrices, these networks are developed as general one-bit detectors. The numerical results show that the combination of the DNN-augmented regularized GD and constellation-based loss function improve the quality of our one-bit detector, especially for higher order M-QAM constellations.