Sparse Representation for Wireless Communications: A Compressive Sensing Approach

Qin, Zhijin; Fan, Jiancun; Liu, Yuanwei; Gao, Yue; Li, Geoffrey Ye

doi:10.1109/msp.2018.2789521

Cited by 212 publications

(91 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The training of the CENN aims to minimize the difference betweenĝ u and g u , while the training of the THPNN aims to maximize the beamforming gain. Therefore the loss function in (16) is different from that in (24). Note that the output of the NN is the analog precoder vectorf u , while we need to calculate the analog precoding matrix F R so that the spectral efficiency can be obtained.…”

Section: A Analog Precoder Designmentioning

confidence: 99%

Sparse Channel Estimation and Hybrid Precoding Using Deep Learning for Millimeter Wave Massive MIMO

Zhang

et al. 2020

IEEE Trans. Commun.

169

View full text Add to dashboard Cite

Channel estimation and hybrid precoding are considered for multi-user millimeter wave massive multi-input multioutput system. A deep learning compressed sensing (DLCS) channel estimation scheme is proposed. The channel estimation neural network for the DLCS scheme is trained offline using simulated environments to predict the beamspace channel amplitude. Then the channel is reconstructed based on the obtained indices of dominant beamspace channel entries. A deep learning quantized phase (DLQP) hybrid precoder design method is developed after channel estimation. The training hybrid precoding neural network for the DLQP method is obtained offline considering the approximate phase quantization. Then the deployment hybrid precoding neural network (DHPNN) is obtained by replacing the approximate phase quantization with ideal phase quantization and the output of the DHPNN is the analog precoding vector. Finally, the analog precoding matrix is obtained by stacking the analog precoding vectors and the digital precoding matrix is calculated by zero-forcing. Simulation results demonstrate that the DLCS channel estimation scheme outperforms the existing schemes in terms of the normalized mean-squared error and the spectral efficiency, while the DLQP hybrid precoder design method has better spectral efficiency performance than other methods with low phase shifter resolution.

show abstract

Section: A Analog Precoder Designmentioning

confidence: 99%

Sparse Channel Estimation and Hybrid Precoding Using Deep Learning for Millimeter Wave Massive MIMO

Zhang

et al. 2020

IEEE Trans. Commun.

169

View full text Add to dashboard Cite

show abstract

“…With the help of its most recent development on compressive sensing techniques, the bottleneck of wideband spectrum sensing can be broken by utilizing the sparsity property of spectrum [30]. Compressive sensing has been firstly introduced in [31], which enables sub-Nyquist sampling over a wide frequency band without loss of any information.…”

Section: Submentioning

confidence: 99%

20 Years of Evolution From Cognitive to Intelligent Communications

Qin

Zhou

Zhang

et al. 2020

IEEE Trans. Cogn. Commun. Netw.

Self Cite

View full text Add to dashboard Cite

It has been 20 years since the concept of cognitive radio (CR) was proposed, which is an efficient approach to provide more access opportunities to connect massive wireless devices. To improve the spectrum efficiency, CR enables unlicensed usage of licensed spectrum resources. It has been regarded as the key enabler for intelligent communications. In this article, we will provide an overview on the intelligent communication in the past two decades to illustrate the revolution of its capability from cognition to artificial intelligence (AI). Particularly, this article starts from a comprehensive review of typical spectrum sensing and sharing, followed by the recent achievements on the AIenabled intelligent radio. Moreover, research challenges in the future intelligent communications will be discussed to show a path to the real deployment of intelligent radio. After witnessing the glorious developments of CR in the past 20 years, we try to provide readers a clear picture on how intelligent radio could be further developed to smartly utilize the limited spectrum resources as well as to optimally configure wireless devices in the future communication systems.

show abstract

“…However, this feedback strategy is infeasible in massive MIMO because the substantial antennas at the BS greatly increase the dimension of CSI matrix, thereby leading to a large overhead [7], [9]. To address this issue, the CSI matrix should be efficiently compressed [9], [10], which can be based on compressive sensing (CS) or deep learning (DL). The CS-based methods exploit the sparsity of massive MIMO CSI in certain domain [11].…”

Section: Introductionmentioning

confidence: 99%

“…In [13], a hidden joint sparsity structure in the user channel matrices has been found and exploited due to the shared local scatterers. CS techniques simplify the encoding (compression) process; but, the decoding (decompression) process turns into solving an optimization problem and demands substantial computing sources and time [10], thereby making it difficult to implement in many practical communication systems.…”

Section: Introductionmentioning

confidence: 99%

Convolutional Neural Network-Based Multiple-Rate Compressive Sensing for Massive MIMO CSI Feedback: Design, Simulation, and Analysis

Guo

Wen

Jin

et al. 2020

IEEE Trans. Wireless Commun.

Self Cite

269

178

View full text Add to dashboard Cite

Massive multiple-input multiple-output (MIMO) is a promising technology to increase link capacity and energy efficiency. However, these benefits are based on available channel state information (CSI) at the base station (BS). Therefore, user equipment (UE) needs to keep on feeding CSI back to the BS, thereby consuming precious bandwidth resource. Large-scale antennas at the BS for massive MIMO seriously increase this overhead. In this paper, we propose a multiple-rate compressive sensing neural network framework to compress and quantize the CSI. This framework not only improves reconstruction accuracy but also decreases storage space at the UE, thus enhancing the system feasibility. Specifically, we establish two network design principles for CSI feedback, propose a new network architecture, CsiNet+, according to these principles, and develop a novel quantization framework and training strategy.Next, we further introduce two different variable-rate approaches, namely, SM-CsiNet+ and PM-CsiNet+, which decrease the parameter number at the UE by 38.0% and 46.7%, respectively. Experimental results show that CsiNet+ outperforms the state-of-the-art network by a margin but only slightly increases the parameter number. We also investigate the compression and reconstruction mechanism behind deep learning-based CSI feedback methods via parameter visualization, which provides a guideline for subsequent research.

show abstract

Sparse Representation for Wireless Communications: A Compressive Sensing Approach

Cited by 212 publications

References 74 publications

Sparse Channel Estimation and Hybrid Precoding Using Deep Learning for Millimeter Wave Massive MIMO

Sparse Channel Estimation and Hybrid Precoding Using Deep Learning for Millimeter Wave Massive MIMO

20 Years of Evolution From Cognitive to Intelligent Communications

Convolutional Neural Network-Based Multiple-Rate Compressive Sensing for Massive MIMO CSI Feedback: Design, Simulation, and Analysis

Contact Info

Product

Resources

About