Neural Network-Optimized Channel Estimator and Training Signal Design for MIMO Systems With Few-Bit ADCs

@article{Nguyen2020NeuralNC,
  title={Neural Network-Optimized Channel Estimator and Training Signal Design for MIMO Systems With Few-Bit ADCs},
  author={Duy H. N. Nguyen},
  journal={IEEE Signal Processing Letters},
  year={2020},
  volume={27},
  pages={1370-1374}
}
  • D. Nguyen
  • Published 19 March 2020
  • Computer Science
  • IEEE Signal Processing Letters
This paper is concerned with channel estimation in MIMO systems with few-bit ADCs. In these systems, a linear minimum mean-squared error (MMSE) channel estimator obtained in closed-form is not an optimal solution. We first consider a deep neural network (DNN) and train it as a nonlinear MMSE channel estimator for few-bit MIMO systems. We then present a first attempt to use DNN in optimizing the training signal and the MMSE channel estimator concurrently. Specifically, we propose an autoencoder… 

Figures and Tables from this paper

SVM-Based Channel Estimation and Data Detection for One-Bit Massive MIMO Systems
TLDR
This paper shows how Support Vector Machine (SVM), a well-known supervised-learning technique in machine learning, can be exploited to provide efficient and robust channel estimation and data detection in massive MIMO systems with one-bit ADCs.
Deep Learning-Based Channel Estimation for Massive-MIMO With Mixed-Resolution ADCs and Low-Resolution Information Utilization
TLDR
Simulation results show that the proposed deep-learning based uplink channel estimation approaches outperform state-of-the-art channel estimation method especially when most antennas are equipped with low-resolution ADCs.
Intelligent Radio Signal Processing: A Contemporary Survey
TLDR
This survey covers four intelligent signal processing topics for the wireless physical layer, including modulation classification, signal detection, beamforming, and channel estimation, and presents a brief overview of AI techniques such as machine learning, deep learning, and federated learning.
Intelligent Radio Signal Processing: A Survey
TLDR
This survey covers four intelligent signal processing topics for the wireless physical layer, including modulation classification, signal detection, beamforming, and channel estimation, and presents a brief overview of AI techniques such as machine learning, deep learning, and federated learning.
Application of Reinforcement Learning and Deep Learning in Multiple-Input and Multiple-Output (MIMO) Systems
TLDR
RL and DL techniques for MIMO systems are presented by presenting a comprehensive review on the integration between the two areas and potential RL and DL applications for different MIMo issues, such as detection, classification, and compression; channel estimation; positioning, sensing, and localization.
Deep Learning for Estimation and Pilot Signal Design in Few-Bit Massive MIMO Systems
TLDR
A deep learning framework for channel estimation, data detection, and pilot signal design to address the nonlinearity in few-bit MIMO systems is proposed and simulation results show significant performance gain in estimation accuracy by the proposeddeep learning framework.
Joint Channel Estimation and Mixed-ADCs Allocation for Massive MIMO via Deep Learning
TLDR
This paper proposes a deep learning-based (DL) joint pilot design and channel estimation method for mixed-ADCs mmWave massive MIMO, and develops a Runge-Kutta model-driven densely connected network as the channel estimator.

References

SHOWING 1-10 OF 33 REFERENCES
Training-based MIMO channel estimation: a study of estimator tradeoffs and optimal training signals
TLDR
This paper considers the popular linear least squares and minimum mean-square-error approaches and proposes new scaled LS (SLS) and relaxed MMSE techniques which require less knowledge of the channel second-order statistics and/or have better performance than the conventional LS and MMSE channel estimators.
Training Signal Design for Estimation of Correlated MIMO Channels With Colored Interference
TLDR
An algorithm to estimate the long-term channel statistics needed for the construction of the optimal training sequences, and an efficient scheme to feed back the required information to the transmitter where they can approximately construct the optimal sequences.
Deep Learning Based Channel Estimation for Massive MIMO With Mixed-Resolution ADCs
In this letter, deep learning is applied to estimate the uplink channels for mixed analog-to-digital converters (ADCs) massive multiple-input multiple-output (MIMO) systems, where a portion of
Channel Estimation in Massive MIMO Under Hardware Non-Linearities: Bayesian Methods Versus Deep Learning
TLDR
The proposed deep learning approach improves the estimation quality by exploiting impairment characteristics, while the state-of-the-art distortion-aware and -unaware Bayesian linear minimum mean-squared error estimators treat distortion as noise.
Channel Estimation and Performance Analysis of One-Bit Massive MIMO Systems
TLDR
This paper proposes an approach for channel estimation that is applicable for both flat and frequency-selective fading, based on the Bussgang decomposition that reformulates the nonlinear quantizer as a linear function with identical first- and second-order statistics.
Channel Estimation in Broadband Millimeter Wave MIMO Systems With Few-Bit ADCs
We develop a broadband channel estimation algorithm for millimeter wave (mmWave) multiple input multiple output (MIMO) systems with few-bit analog-to-digital converters (ADCs). Our methodology
MIMO Channel Estimation with Non-Ideal ADCS: Deep Learning Versus GAMP
TLDR
DL applied to channel estimation of MIMO systems with low resolution analog-to-digital converters (ADCs) indicates that a single neural network trained in a range of practical conditions is more robust to ADC impairments than a GAMP variant.
A Framework for Training-Based Estimation in Arbitrarily Correlated Rician MIMO Channels With Rician Disturbance
TLDR
It is shown under which conditions training sequences that minimize the non-convex MSE can be derived explicitly or with low complexity, and it is proved that spatial correlation improves the estimation performance and establish how it determines the optimal training sequence length.
Uplink Performance of Wideband Massive MIMO With One-Bit ADCs
TLDR
An analysis of the spectral efficiency of single-carrier and orthogonal-frequency-division-multiplexing (OFDM) transmission in massive MIMO systems that use one-bit ADCs is presented and it is concluded that wideband massive M IMO systems work well with one- bit ADCs.
Capacity Lower Bound of MIMO Channels with Output Quantization and Correlated Noise
TLDR
A lower bound on the channel capacity of quantized MIMO channels is derived based on the Bussgang decomposition based on possible noise correlation and reveals that noise correlation might reduce the capacity loss due to quantization when compared to the uncorrelated noise case.
...
...