Signal Detection in MIMO Systems With Hardware Imperfections: Message Passing on Neural Networks

Gao, Dawei; Guo, Qinghua; Liao, Guisheng; Eldar, Yonina C.; Li, Yonghui; Yu, Yanguang; Vucetic, Branka

doi:10.1109/twc.2023.3283275

Cited by 4 publications

(2 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This success has naturally led to the development of DL-based MIMO detectors that leverage training data to learn nonlinear relationships between transmitted and received signals [17]- [19]. DL-based MIMO detection has also been studied for addressing nonlinear and unknown distortion caused by hardware impairments [20]- [22]. Data-driven DL detectors based on black-box DNN architectures were introduced and analyzed in [20], which can be applied to MIMO systems with hardware impairments.…”

Section: Introductionmentioning

confidence: 99%

“…Data-driven DL detectors based on black-box DNN architectures were introduced and analyzed in [20], which can be applied to MIMO systems with hardware impairments. Model-based DL detectors based on iterative algorithms were developed for MIMO systems with low-resolution ADCs [21], or for MIMO systems with non-ideal PA and I/Q imbalance [22]. By incorporating domain knowledge into the design of a DNN architecture, these detectors require relatively low training overhead compared to detectors that use black-box DNN architectures.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

MIMO Detection under Hardware Impairments via Learning from Noisy Labels

Kwon

Jeon

Poor

2022

GLOBECOM 2022 - 2022 IEEE Global Communications Conference

View full text Add to dashboard Cite

This paper considers a data detection problem in multiple-input multiple-output (MIMO) communication systems with hardware impairments. To address challenges posed by nonlinear and unknown distortion in received signals, two learning-based detection methods, referred to as model-driven and data-driven, are presented. The model-driven method employs a generalized Gaussian distortion model to approximate the conditional distribution of the distorted received signal. By using the outputs of coarse data detection as noisy training data, the model-driven method avoids the need for additional training overhead beyond traditional pilot overhead for channel estimation. An expectation-maximization algorithm is devised to accurately learn the parameters of the distortion model from noisy training data.To resolve a model mismatch problem in the model-driven method, the data-driven method employs a deep neural network (DNN) for approximating a-posteriori probabilities for each received signal. This method uses the outputs of the model-driven method as noisy labels and therefore does not require extra training overhead. To avoid the overfitting problem caused by noisy labels, a robust DNN training algorithm is devised, which involves a warm-up period, sample selection, and loss correction. Simulation results demonstrate that the two proposed methods outperform existing solutions with the same overhead under various hardware impairment scenarios.

show abstract