Deep Learning Based MIMO Transmission with Precoding and Radio Transformer Networks

Wenqi Cui; Anming Dong; Yi Cao; Chuanting Zhang; Jiguo Yu; Sufang Li

doi:10.1016/j.procs.2021.04.078

Deep Learning Based MIMO Transmission with Precoding and Radio Transformer Networks

Wenqi Cui, Anming Dong, Yi Cao, Chuanting Zhang, Jiguo Yu, Sufang Li

Computer, Electrical and Mathematical Sciences and Engineering

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

5 Scopus citations

Abstract

In this paper, we study MIMO transmission schemes based on deep learning (DL). We propose a novel DL-based MIMO communication structure by combing a beamforming network at the transmitter side and a radio transformer network (RTN) at the receiver side. Compared with the classical DL-based MIMO communication systems, the interference is potentially mitigated by a precoding network and a RTN network, which is thus beneficial to improve the performance of signal detection. Simulation results show that the proposed scheme outperforms the classical MIMO transmission schemes in terms of bit error rate (BER).

Original language	English (US)
Title of host publication	Procedia Computer Science
Publisher	Elsevier BV
Pages	396-401
Number of pages	6
DOIs	https://doi.org/10.1016/j.procs.2021.04.078
State	Published - Jun 12 2021

Access to Document

10.1016/j.procs.2021.04.078

https://repository.kaust.edu.sa/bitstream/10754/670864/1/1-s2.0-S1877050921008747-main.pdf

Cite this

@inproceedings{6082afc5a3064f5cb1ccb8040401b594,

title = "Deep Learning Based MIMO Transmission with Precoding and Radio Transformer Networks",

abstract = "In this paper, we study MIMO transmission schemes based on deep learning (DL). We propose a novel DL-based MIMO communication structure by combing a beamforming network at the transmitter side and a radio transformer network (RTN) at the receiver side. Compared with the classical DL-based MIMO communication systems, the interference is potentially mitigated by a precoding network and a RTN network, which is thus beneficial to improve the performance of signal detection. Simulation results show that the proposed scheme outperforms the classical MIMO transmission schemes in terms of bit error rate (BER).",

author = "Wenqi Cui and Anming Dong and Yi Cao and Chuanting Zhang and Jiguo Yu and Sufang Li",

note = "KAUST Repository Item: Exported on 2021-09-01 Acknowledgements: This work was supported in part by the National Key R&D Program of China under grant 2019YFB2102600, the National Natural Science Foundation of China (NSFC) under Grants 61701269, 61832012, 61771289 and 61672321, the Shandong Provincial Natural Science Foundation under Grant ZR2017BF012, the Key Research and Development Program of Shandong Province under Grants 2019JZZY010313 and 2019JZZY020124, the Joint Research Fund for Young Scholars in Qilu University (Shandong Academy of Sciences) under Grant 2017BSHZ005.",

year = "2021",

month = jun,

day = "12",

doi = "10.1016/j.procs.2021.04.078",

language = "English (US)",

pages = "396--401",

booktitle = "Procedia Computer Science",

publisher = "Elsevier BV",

}

TY - GEN

T1 - Deep Learning Based MIMO Transmission with Precoding and Radio Transformer Networks

AU - Cui, Wenqi

AU - Dong, Anming

AU - Cao, Yi

AU - Zhang, Chuanting

AU - Yu, Jiguo

AU - Li, Sufang

N1 - KAUST Repository Item: Exported on 2021-09-01 Acknowledgements: This work was supported in part by the National Key R&D Program of China under grant 2019YFB2102600, the National Natural Science Foundation of China (NSFC) under Grants 61701269, 61832012, 61771289 and 61672321, the Shandong Provincial Natural Science Foundation under Grant ZR2017BF012, the Key Research and Development Program of Shandong Province under Grants 2019JZZY010313 and 2019JZZY020124, the Joint Research Fund for Young Scholars in Qilu University (Shandong Academy of Sciences) under Grant 2017BSHZ005.

PY - 2021/6/12

Y1 - 2021/6/12

N2 - In this paper, we study MIMO transmission schemes based on deep learning (DL). We propose a novel DL-based MIMO communication structure by combing a beamforming network at the transmitter side and a radio transformer network (RTN) at the receiver side. Compared with the classical DL-based MIMO communication systems, the interference is potentially mitigated by a precoding network and a RTN network, which is thus beneficial to improve the performance of signal detection. Simulation results show that the proposed scheme outperforms the classical MIMO transmission schemes in terms of bit error rate (BER).

AB - In this paper, we study MIMO transmission schemes based on deep learning (DL). We propose a novel DL-based MIMO communication structure by combing a beamforming network at the transmitter side and a radio transformer network (RTN) at the receiver side. Compared with the classical DL-based MIMO communication systems, the interference is potentially mitigated by a precoding network and a RTN network, which is thus beneficial to improve the performance of signal detection. Simulation results show that the proposed scheme outperforms the classical MIMO transmission schemes in terms of bit error rate (BER).

UR - http://hdl.handle.net/10754/670864

UR - https://linkinghub.elsevier.com/retrieve/pii/S1877050921008747

UR - http://www.scopus.com/inward/record.url?scp=85112534289&partnerID=8YFLogxK

U2 - 10.1016/j.procs.2021.04.078

DO - 10.1016/j.procs.2021.04.078

M3 - Conference contribution

SP - 396

EP - 401

BT - Procedia Computer Science

PB - Elsevier BV

ER -

Deep Learning Based MIMO Transmission with Precoding and Radio Transformer Networks

Abstract

Access to Document

Other files and links

Fingerprint

Cite this