DNN-Aided message passing based block sparse Bayesian learning for joint user activity detection and channel estimation

Zhaoji Zhang; Ying Li; Chongwen Huang; Qinghua Guo; Chau Yuen; Yong Liang Guan

doi:10.1109/VTS-APWCS.2019.8851613

DNN-Aided message passing based block sparse Bayesian learning for joint user activity detection and channel estimation

Zhaoji Zhang, Ying Li, Chongwen Huang, Qinghua Guo, Chau Yuen, Yong Liang Guan

President's Office

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Citations (Scopus)

Abstract

Faced with the massive connection, sporadic transmission, and small-sized data packets in future cellular communication, a grant-free non-orthogonal random access (NORA) system is considered in this paper, which could reduce the access delay and support more devices. In order to address the joint user activity detection (UAD) and channel estimation (CE) problem in the grant-free NORA system, we propose a deep neural network-aided message passing-based block sparse Bayesian learning (DNN-MP-BSBL) algorithm. In this algorithm, the message passing process is transferred from a factor graph to a deep neural network (DNN). Weights are imposed on the messages in the DNN and trained to minimize the estimation error. It is shown that the weights could alleviate the convergence problem of the MP-BSBL algorithm. Simulation results show that the proposed DNN-MP-BSBL algorithm could improve the UAD and CE accuracy with a smaller number of iterations.

Original language	English
Title of host publication	Proceedings - 2019 IEEE VTS Asia Pacific Wireless Communications Symposium, APWCS 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728112046
DOIs	https://doi.org/10.1109/VTS-APWCS.2019.8851613
Publication status	Published - Aug 2019
Event	2019 IEEE VTS Asia Pacific Wireless Communications Symposium, APWCS 2019 - Singapore, Singapore Duration: Aug 28 2019 → Aug 30 2019

Publication series

Name	Proceedings - 2019 IEEE VTS Asia Pacific Wireless Communications Symposium, APWCS 2019

Conference

Conference	2019 IEEE VTS Asia Pacific Wireless Communications Symposium, APWCS 2019
Country/Territory	Singapore
City	Singapore
Period	8/28/19 → 8/30/19

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

ASJC Scopus Subject Areas

Signal Processing
Computer Networks and Communications

Keywords

Channel estimation
Deep neural network
Grant-free
Sparse Bayesian learning
User activity detection

Access to Document

10.1109/VTS-APWCS.2019.8851613

Cite this

Zhang, Z., Li, Y., Huang, C., Guo, Q., Yuen, C., & Guan, Y. L. (2019). DNN-Aided message passing based block sparse Bayesian learning for joint user activity detection and channel estimation. In Proceedings - 2019 IEEE VTS Asia Pacific Wireless Communications Symposium, APWCS 2019 Article 8851613 (Proceedings - 2019 IEEE VTS Asia Pacific Wireless Communications Symposium, APWCS 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/VTS-APWCS.2019.8851613

Zhang, Zhaoji ; Li, Ying ; Huang, Chongwen et al. / DNN-Aided message passing based block sparse Bayesian learning for joint user activity detection and channel estimation. Proceedings - 2019 IEEE VTS Asia Pacific Wireless Communications Symposium, APWCS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. (Proceedings - 2019 IEEE VTS Asia Pacific Wireless Communications Symposium, APWCS 2019).

@inproceedings{08a36ebed3fa444597ffd1be944a816b,

title = "DNN-Aided message passing based block sparse Bayesian learning for joint user activity detection and channel estimation",

abstract = "Faced with the massive connection, sporadic transmission, and small-sized data packets in future cellular communication, a grant-free non-orthogonal random access (NORA) system is considered in this paper, which could reduce the access delay and support more devices. In order to address the joint user activity detection (UAD) and channel estimation (CE) problem in the grant-free NORA system, we propose a deep neural network-aided message passing-based block sparse Bayesian learning (DNN-MP-BSBL) algorithm. In this algorithm, the message passing process is transferred from a factor graph to a deep neural network (DNN). Weights are imposed on the messages in the DNN and trained to minimize the estimation error. It is shown that the weights could alleviate the convergence problem of the MP-BSBL algorithm. Simulation results show that the proposed DNN-MP-BSBL algorithm could improve the UAD and CE accuracy with a smaller number of iterations.",

keywords = "Channel estimation, Deep neural network, Grant-free, Sparse Bayesian learning, User activity detection",

author = "Zhaoji Zhang and Ying Li and Chongwen Huang and Qinghua Guo and Chau Yuen and Guan, {Yong Liang}",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 IEEE VTS Asia Pacific Wireless Communications Symposium, APWCS 2019 ; Conference date: 28-08-2019 Through 30-08-2019",

year = "2019",

month = aug,

doi = "10.1109/VTS-APWCS.2019.8851613",

language = "English",

series = "Proceedings - 2019 IEEE VTS Asia Pacific Wireless Communications Symposium, APWCS 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "Proceedings - 2019 IEEE VTS Asia Pacific Wireless Communications Symposium, APWCS 2019",

address = "United States",

}

Zhang, Z, Li, Y, Huang, C, Guo, Q, Yuen, C & Guan, YL 2019, DNN-Aided message passing based block sparse Bayesian learning for joint user activity detection and channel estimation. in Proceedings - 2019 IEEE VTS Asia Pacific Wireless Communications Symposium, APWCS 2019., 8851613, Proceedings - 2019 IEEE VTS Asia Pacific Wireless Communications Symposium, APWCS 2019, Institute of Electrical and Electronics Engineers Inc., 2019 IEEE VTS Asia Pacific Wireless Communications Symposium, APWCS 2019, Singapore, Singapore, 8/28/19. https://doi.org/10.1109/VTS-APWCS.2019.8851613

DNN-Aided message passing based block sparse Bayesian learning for joint user activity detection and channel estimation. / Zhang, Zhaoji; Li, Ying; Huang, Chongwen et al.
Proceedings - 2019 IEEE VTS Asia Pacific Wireless Communications Symposium, APWCS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8851613 (Proceedings - 2019 IEEE VTS Asia Pacific Wireless Communications Symposium, APWCS 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - DNN-Aided message passing based block sparse Bayesian learning for joint user activity detection and channel estimation

AU - Zhang, Zhaoji

AU - Li, Ying

AU - Huang, Chongwen

AU - Guo, Qinghua

AU - Yuen, Chau

AU - Guan, Yong Liang

PY - 2019/8

Y1 - 2019/8

N2 - Faced with the massive connection, sporadic transmission, and small-sized data packets in future cellular communication, a grant-free non-orthogonal random access (NORA) system is considered in this paper, which could reduce the access delay and support more devices. In order to address the joint user activity detection (UAD) and channel estimation (CE) problem in the grant-free NORA system, we propose a deep neural network-aided message passing-based block sparse Bayesian learning (DNN-MP-BSBL) algorithm. In this algorithm, the message passing process is transferred from a factor graph to a deep neural network (DNN). Weights are imposed on the messages in the DNN and trained to minimize the estimation error. It is shown that the weights could alleviate the convergence problem of the MP-BSBL algorithm. Simulation results show that the proposed DNN-MP-BSBL algorithm could improve the UAD and CE accuracy with a smaller number of iterations.

AB - Faced with the massive connection, sporadic transmission, and small-sized data packets in future cellular communication, a grant-free non-orthogonal random access (NORA) system is considered in this paper, which could reduce the access delay and support more devices. In order to address the joint user activity detection (UAD) and channel estimation (CE) problem in the grant-free NORA system, we propose a deep neural network-aided message passing-based block sparse Bayesian learning (DNN-MP-BSBL) algorithm. In this algorithm, the message passing process is transferred from a factor graph to a deep neural network (DNN). Weights are imposed on the messages in the DNN and trained to minimize the estimation error. It is shown that the weights could alleviate the convergence problem of the MP-BSBL algorithm. Simulation results show that the proposed DNN-MP-BSBL algorithm could improve the UAD and CE accuracy with a smaller number of iterations.

KW - Channel estimation

KW - Deep neural network

KW - Grant-free

KW - Sparse Bayesian learning

KW - User activity detection

UR - http://www.scopus.com/inward/record.url?scp=85073522437&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073522437&partnerID=8YFLogxK

U2 - 10.1109/VTS-APWCS.2019.8851613

DO - 10.1109/VTS-APWCS.2019.8851613

M3 - Conference contribution

AN - SCOPUS:85073522437

T3 - Proceedings - 2019 IEEE VTS Asia Pacific Wireless Communications Symposium, APWCS 2019

BT - Proceedings - 2019 IEEE VTS Asia Pacific Wireless Communications Symposium, APWCS 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 IEEE VTS Asia Pacific Wireless Communications Symposium, APWCS 2019

Y2 - 28 August 2019 through 30 August 2019

ER -

Zhang Z, Li Y, Huang C, Guo Q, Yuen C, Guan YL. DNN-Aided message passing based block sparse Bayesian learning for joint user activity detection and channel estimation. In Proceedings - 2019 IEEE VTS Asia Pacific Wireless Communications Symposium, APWCS 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 8851613. (Proceedings - 2019 IEEE VTS Asia Pacific Wireless Communications Symposium, APWCS 2019). doi: 10.1109/VTS-APWCS.2019.8851613

DNN-Aided message passing based block sparse Bayesian learning for joint user activity detection and channel estimation

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus Subject Areas

Keywords

Access to Document

Other files and links

Fingerprint

Cite this