Deep Neural Network Assisted Approach for Antenna Selection in Untrusted Relay Networks

Rugui Yao; Yuxin Zhang; Shengyao Wang; Nan Qi; Nikolaos I. Miridakis; Theodoros A. Tsiftsis

doi:10.1109/LWC.2019.2933392

Deep Neural Network Assisted Approach for Antenna Selection in Untrusted Relay Networks

Rugui Yao
, Yuxin Zhang
, Shengyao Wang
, Nan Qi
, Nikolaos I. Miridakis
, Theodoros A. Tsiftsis

Research output: Journal Publication › Article › peer-review

21 Citations (Scopus)

Abstract

This letter mainly studies the transmit antenna selection (TAS) scheme based on deep neural network (DNN) in untrusted relay networks. In our previous work, we revealed that machine learning (ML)-based TAS schemes have performance degradation caused by complicated coupling relationship between the achievable secrecy rate and channel gains. To solve this issue, we here introduce DNN to decouple the above complicated relationship. The simulation results show that the DNN scheme can achieve better decoupling and, thus, accomplish almost the same performance as the exhaustive searching scheme.

Original language	English
Article number	8789659
Pages (from-to)	1644-1647
Number of pages	4
Journal	IEEE Wireless Communications Letters
Volume	8
Issue number	6
DOIs	https://doi.org/10.1109/LWC.2019.2933392
Publication status	Published - Dec 2019
Externally published	Yes

Free Keywords

Deep neural network (DNN)
transmit antenna selection (TAS)
untrusted relay networks

ASJC Scopus subject areas

Control and Systems Engineering
Electrical and Electronic Engineering

Access to Document

10.1109/LWC.2019.2933392

Cite this

@article{87cd2ded5f1748d58f23fabe070ef950,

title = "Deep Neural Network Assisted Approach for Antenna Selection in Untrusted Relay Networks",

abstract = "This letter mainly studies the transmit antenna selection (TAS) scheme based on deep neural network (DNN) in untrusted relay networks. In our previous work, we revealed that machine learning (ML)-based TAS schemes have performance degradation caused by complicated coupling relationship between the achievable secrecy rate and channel gains. To solve this issue, we here introduce DNN to decouple the above complicated relationship. The simulation results show that the DNN scheme can achieve better decoupling and, thus, accomplish almost the same performance as the exhaustive searching scheme.",

keywords = "Deep neural network (DNN), transmit antenna selection (TAS), untrusted relay networks",

author = "Rugui Yao and Yuxin Zhang and Shengyao Wang and Nan Qi and Miridakis, \{Nikolaos I.\} and Tsiftsis, \{Theodoros A.\}",

note = "Publisher Copyright: {\textcopyright} 2012 IEEE.",

year = "2019",

month = dec,

doi = "10.1109/LWC.2019.2933392",

language = "English",

volume = "8",

pages = "1644--1647",

journal = "IEEE Wireless Communications Letters",

issn = "2162-2337",

publisher = "IEEE Communications Society",

number = "6",

}

TY - JOUR

T1 - Deep Neural Network Assisted Approach for Antenna Selection in Untrusted Relay Networks

AU - Yao, Rugui

AU - Zhang, Yuxin

AU - Wang, Shengyao

AU - Qi, Nan

AU - Miridakis, Nikolaos I.

AU - Tsiftsis, Theodoros A.

PY - 2019/12

Y1 - 2019/12

N2 - This letter mainly studies the transmit antenna selection (TAS) scheme based on deep neural network (DNN) in untrusted relay networks. In our previous work, we revealed that machine learning (ML)-based TAS schemes have performance degradation caused by complicated coupling relationship between the achievable secrecy rate and channel gains. To solve this issue, we here introduce DNN to decouple the above complicated relationship. The simulation results show that the DNN scheme can achieve better decoupling and, thus, accomplish almost the same performance as the exhaustive searching scheme.

AB - This letter mainly studies the transmit antenna selection (TAS) scheme based on deep neural network (DNN) in untrusted relay networks. In our previous work, we revealed that machine learning (ML)-based TAS schemes have performance degradation caused by complicated coupling relationship between the achievable secrecy rate and channel gains. To solve this issue, we here introduce DNN to decouple the above complicated relationship. The simulation results show that the DNN scheme can achieve better decoupling and, thus, accomplish almost the same performance as the exhaustive searching scheme.

KW - Deep neural network (DNN)

KW - transmit antenna selection (TAS)

KW - untrusted relay networks

UR - https://www.scopus.com/pages/publications/85076568723

U2 - 10.1109/LWC.2019.2933392

DO - 10.1109/LWC.2019.2933392

M3 - Article

AN - SCOPUS:85076568723

SN - 2162-2337

VL - 8

SP - 1644

EP - 1647

JO - IEEE Wireless Communications Letters

JF - IEEE Wireless Communications Letters

IS - 6

M1 - 8789659

ER -

Deep Neural Network Assisted Approach for Antenna Selection in Untrusted Relay Networks

Abstract

Free Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this