Deep Learning-Based Codebook Designs for Generalized Space Shift Keying Systems

Di Huang; Xue Qin Jiang; Inkyu Lee; Han Hai

doi:10.1109/TVT.2021.3128693

Deep Learning-Based Codebook Designs for Generalized Space Shift Keying Systems

Di Huang
, Xue Qin Jiang
, Inkyu Lee
, Han Hai

Research output: Contribution to journal › Article › peer-review

2 Citations (Scopus)

Abstract

In this paper, we propose a novel deep learning (DL)-based codebook design method for generalized space shift keying (GSSK) systems. In this DL-based method, the transmitter and receiver of GSSK systems are designed based on deep neural network (DNN). By training the DNN in an end-to-end manner, the DL-based method can adaptively generate suitable binary codewords and combine them into a codebook for GSSK systems. Simulation results show that the proposed DL-based method obtains better performance compared to conventional approaches.

Original language	English
Pages (from-to)	1038-1042
Number of pages	5
Journal	IEEE Transactions on Vehicular Technology
Volume	71
Issue number	1
DOIs	https://doi.org/10.1109/TVT.2021.3128693
Publication status	Published - 2022 Jan 1

Bibliographical note

Publisher Copyright:
© 1967-2012 IEEE.

Keywords

Generalized space shift keying
codebook
deep learning
multiple-input multiple-output

ASJC Scopus subject areas

Automotive Engineering
Aerospace Engineering
Electrical and Electronic Engineering
Applied Mathematics

Access to Document

10.1109/TVT.2021.3128693

Cite this

@article{8bbcef956c7747b4858acb337d6535b9,

title = "Deep Learning-Based Codebook Designs for Generalized Space Shift Keying Systems",

abstract = "In this paper, we propose a novel deep learning (DL)-based codebook design method for generalized space shift keying (GSSK) systems. In this DL-based method, the transmitter and receiver of GSSK systems are designed based on deep neural network (DNN). By training the DNN in an end-to-end manner, the DL-based method can adaptively generate suitable binary codewords and combine them into a codebook for GSSK systems. Simulation results show that the proposed DL-based method obtains better performance compared to conventional approaches. ",

keywords = "Generalized space shift keying, codebook, deep learning, multiple-input multiple-output",

author = "Di Huang and Jiang, \{Xue Qin\} and Inkyu Lee and Han Hai",

note = "Publisher Copyright: {\textcopyright} 1967-2012 IEEE.",

year = "2022",

month = jan,

day = "1",

doi = "10.1109/TVT.2021.3128693",

language = "English",

volume = "71",

pages = "1038--1042",

journal = "IEEE Transactions on Vehicular Technology",

issn = "0018-9545",

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

number = "1",

}

TY - JOUR

T1 - Deep Learning-Based Codebook Designs for Generalized Space Shift Keying Systems

AU - Huang, Di

AU - Jiang, Xue Qin

AU - Lee, Inkyu

AU - Hai, Han

PY - 2022/1/1

Y1 - 2022/1/1

N2 - In this paper, we propose a novel deep learning (DL)-based codebook design method for generalized space shift keying (GSSK) systems. In this DL-based method, the transmitter and receiver of GSSK systems are designed based on deep neural network (DNN). By training the DNN in an end-to-end manner, the DL-based method can adaptively generate suitable binary codewords and combine them into a codebook for GSSK systems. Simulation results show that the proposed DL-based method obtains better performance compared to conventional approaches.

AB - In this paper, we propose a novel deep learning (DL)-based codebook design method for generalized space shift keying (GSSK) systems. In this DL-based method, the transmitter and receiver of GSSK systems are designed based on deep neural network (DNN). By training the DNN in an end-to-end manner, the DL-based method can adaptively generate suitable binary codewords and combine them into a codebook for GSSK systems. Simulation results show that the proposed DL-based method obtains better performance compared to conventional approaches.

KW - Generalized space shift keying

KW - codebook

KW - deep learning

KW - multiple-input multiple-output

UR - https://www.scopus.com/pages/publications/85119412494

U2 - 10.1109/TVT.2021.3128693

DO - 10.1109/TVT.2021.3128693

M3 - Article

AN - SCOPUS:85119412494

SN - 0018-9545

VL - 71

SP - 1038

EP - 1042

JO - IEEE Transactions on Vehicular Technology

JF - IEEE Transactions on Vehicular Technology

IS - 1

ER -

Deep Learning-Based Codebook Designs for Generalized Space Shift Keying Systems

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this