Learning the Wireless Channel: A Deep Neural Network Approach

Guan-Xiong Shen; Muhammad R. A. Khandaker; Faisal Tariq

doi:10.1109/UCET51115.2020.9205318

Learning the Wireless Channel: A Deep Neural Network Approach

Guan-Xiong Shen, Muhammad R. A. Khandaker, Faisal Tariq

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

2 Citations (Scopus)

Abstract

In this paper, we propose a new deep neural network (DNN)-based channel estimation method for the Rayleigh fading channel model. While deep learning has been considered for estimating channels in many communication scenarios, direct estimation of the basic wireless single-input single-output (SISO) communication channel coefficients has not been considered. The proposed DNN-based method can efficiently estimate the channel in real time. Extensive simulation results demonstrate that the proposed channel estimator outperforms conventional least square (LS) estimators in terms of bit error rate (BER) and mean square error (MSE). In addition, the proposed channel does not need channel statistics information or complex matrix computation, thereby reducing the amount of calculation significantly.

Original language	English
Title of host publication	2020 International Conference on UK-China Emerging Technologies (UCET)
Publisher	IEEE
ISBN (Electronic)	9781728194882
DOIs	https://doi.org/10.1109/UCET51115.2020.9205318
Publication status	Published - 29 Sept 2020
Event	5th International Conference on the UK-China Emerging Technologies 2020 - Glasgow, United Kingdom Duration: 20 Aug 2020 → 21 Aug 2020

Conference

Conference	5th International Conference on the UK-China Emerging Technologies 2020
Abbreviated title	UCET 2020
Country/Territory	United Kingdom
City	Glasgow
Period	20/08/20 → 21/08/20

Keywords

channel estimation
Deep learning
deep neural network
SISO

ASJC Scopus subject areas

Computer Science (miscellaneous)
Information Systems and Management
Engineering (miscellaneous)

Access to Document

10.1109/UCET51115.2020.9205318

Cite this

@inproceedings{67131bfe24744e9abda77a532ce82deb,

title = "Learning the Wireless Channel: A Deep Neural Network Approach",

abstract = "In this paper, we propose a new deep neural network (DNN)-based channel estimation method for the Rayleigh fading channel model. While deep learning has been considered for estimating channels in many communication scenarios, direct estimation of the basic wireless single-input single-output (SISO) communication channel coefficients has not been considered. The proposed DNN-based method can efficiently estimate the channel in real time. Extensive simulation results demonstrate that the proposed channel estimator outperforms conventional least square (LS) estimators in terms of bit error rate (BER) and mean square error (MSE). In addition, the proposed channel does not need channel statistics information or complex matrix computation, thereby reducing the amount of calculation significantly.",

keywords = "channel estimation, Deep learning, deep neural network, SISO",

author = "Guan-Xiong Shen and Khandaker, {Muhammad R. A.} and Faisal Tariq",

year = "2020",

month = sep,

day = "29",

doi = "10.1109/UCET51115.2020.9205318",

language = "English",

booktitle = "2020 International Conference on UK-China Emerging Technologies (UCET)",

publisher = "IEEE",

address = "United States",

note = "5th International Conference on the UK-China Emerging Technologies 2020, UCET 2020 ; Conference date: 20-08-2020 Through 21-08-2020",

}

TY - GEN

T1 - Learning the Wireless Channel

T2 - 5th International Conference on the UK-China Emerging Technologies 2020

AU - Shen, Guan-Xiong

AU - Khandaker, Muhammad R. A.

AU - Tariq, Faisal

PY - 2020/9/29

Y1 - 2020/9/29

N2 - In this paper, we propose a new deep neural network (DNN)-based channel estimation method for the Rayleigh fading channel model. While deep learning has been considered for estimating channels in many communication scenarios, direct estimation of the basic wireless single-input single-output (SISO) communication channel coefficients has not been considered. The proposed DNN-based method can efficiently estimate the channel in real time. Extensive simulation results demonstrate that the proposed channel estimator outperforms conventional least square (LS) estimators in terms of bit error rate (BER) and mean square error (MSE). In addition, the proposed channel does not need channel statistics information or complex matrix computation, thereby reducing the amount of calculation significantly.

AB - In this paper, we propose a new deep neural network (DNN)-based channel estimation method for the Rayleigh fading channel model. While deep learning has been considered for estimating channels in many communication scenarios, direct estimation of the basic wireless single-input single-output (SISO) communication channel coefficients has not been considered. The proposed DNN-based method can efficiently estimate the channel in real time. Extensive simulation results demonstrate that the proposed channel estimator outperforms conventional least square (LS) estimators in terms of bit error rate (BER) and mean square error (MSE). In addition, the proposed channel does not need channel statistics information or complex matrix computation, thereby reducing the amount of calculation significantly.

KW - channel estimation

KW - Deep learning

KW - deep neural network

KW - SISO

UR - http://www.scopus.com/inward/record.url?scp=85094322606&partnerID=8YFLogxK

U2 - 10.1109/UCET51115.2020.9205318

DO - 10.1109/UCET51115.2020.9205318

M3 - Conference contribution

AN - SCOPUS:85094322606

BT - 2020 International Conference on UK-China Emerging Technologies (UCET)

PB - IEEE

Y2 - 20 August 2020 through 21 August 2020

ER -

Learning the Wireless Channel: A Deep Neural Network Approach

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this