Blind Estimation of CPFSK Parameters for Bursty Transmission using LSTM Network

Xiaobei Liu; Yong Liang Guan; Yan Qin

doi:10.1109/GLOBECOM54140.2023.10437082

Blind Estimation of CPFSK Parameters for Bursty Transmission using LSTM Network

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

Abstract

Continuous phase frequency shift keying (CPFSK) has been widely used in wireless communications, as its continuous phase and constant envelop lead to high bandwidth and power efficiency. In non-cooperative communication systems, the CPFSK parameters such as modulation index, pulse shape and pulse length are unknown to the receiver and need to be estimated. This is a challenging task especially when the transmission is bursty. In this paper, long short term memory (LSTM) neural networks are proposed to tackle this problem. Specifically, three LSTM networks with identical structure but trained separately are used to estimate three important CPFSK parameters (modulation index h, pulse length L and pulse shape q(t)) in parallel. Simulation results show that by suitably preprocessing the input data before the LSTM network, the proposed blind estimation scheme is able achieve high estimation accuracy of more than 95% in most cases.

Original language	English
Title of host publication	GLOBECOM 2023 - 2023 IEEE Global Communications Conference
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	7453-7458
Number of pages	6
ISBN (Electronic)	9798350310900
DOIs	https://doi.org/10.1109/GLOBECOM54140.2023.10437082
Publication status	Published - 2023
Externally published	Yes
Event	2023 IEEE Global Communications Conference, GLOBECOM 2023 - Kuala Lumpur, Malaysia Duration: Dec 4 2023 → Dec 8 2023

Publication series

Name	Proceedings - IEEE Global Communications Conference, GLOBECOM
ISSN (Print)	2334-0983
ISSN (Electronic)	2576-6813

Conference

Conference	2023 IEEE Global Communications Conference, GLOBECOM 2023
Country/Territory	Malaysia
City	Kuala Lumpur
Period	12/4/23 → 12/8/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

ASJC Scopus Subject Areas

Artificial Intelligence
Computer Networks and Communications
Hardware and Architecture
Signal Processing

Keywords

blind estimation
Continuous phase frequency shift keying
deep neural network
long short-term memory

Access to Document

10.1109/GLOBECOM54140.2023.10437082

Cite this

Liu, X., Guan, Y. L., & Qin, Y. (2023). Blind Estimation of CPFSK Parameters for Bursty Transmission using LSTM Network. In GLOBECOM 2023 - 2023 IEEE Global Communications Conference (pp. 7453-7458). (Proceedings - IEEE Global Communications Conference, GLOBECOM). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GLOBECOM54140.2023.10437082

@inproceedings{6a6c107f6aad46a18eec1d21124a365f,

title = "Blind Estimation of CPFSK Parameters for Bursty Transmission using LSTM Network",

abstract = "Continuous phase frequency shift keying (CPFSK) has been widely used in wireless communications, as its continuous phase and constant envelop lead to high bandwidth and power efficiency. In non-cooperative communication systems, the CPFSK parameters such as modulation index, pulse shape and pulse length are unknown to the receiver and need to be estimated. This is a challenging task especially when the transmission is bursty. In this paper, long short term memory (LSTM) neural networks are proposed to tackle this problem. Specifically, three LSTM networks with identical structure but trained separately are used to estimate three important CPFSK parameters (modulation index h, pulse length L and pulse shape q(t)) in parallel. Simulation results show that by suitably preprocessing the input data before the LSTM network, the proposed blind estimation scheme is able achieve high estimation accuracy of more than 95% in most cases.",

keywords = "blind estimation, Continuous phase frequency shift keying, deep neural network, long short-term memory",

author = "Xiaobei Liu and Guan, {Yong Liang} and Yan Qin",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE Global Communications Conference, GLOBECOM 2023 ; Conference date: 04-12-2023 Through 08-12-2023",

year = "2023",

doi = "10.1109/GLOBECOM54140.2023.10437082",

language = "English",

series = "Proceedings - IEEE Global Communications Conference, GLOBECOM",

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

pages = "7453--7458",

booktitle = "GLOBECOM 2023 - 2023 IEEE Global Communications Conference",

address = "United States",

}

Liu, X, Guan, YL & Qin, Y 2023, Blind Estimation of CPFSK Parameters for Bursty Transmission using LSTM Network. in GLOBECOM 2023 - 2023 IEEE Global Communications Conference. Proceedings - IEEE Global Communications Conference, GLOBECOM, Institute of Electrical and Electronics Engineers Inc., pp. 7453-7458, 2023 IEEE Global Communications Conference, GLOBECOM 2023, Kuala Lumpur, Malaysia, 12/4/23. https://doi.org/10.1109/GLOBECOM54140.2023.10437082

Blind Estimation of CPFSK Parameters for Bursty Transmission using LSTM Network. / Liu, Xiaobei; Guan, Yong Liang; Qin, Yan.
GLOBECOM 2023 - 2023 IEEE Global Communications Conference. Institute of Electrical and Electronics Engineers Inc., 2023. p. 7453-7458 (Proceedings - IEEE Global Communications Conference, GLOBECOM).

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

TY - GEN

T1 - Blind Estimation of CPFSK Parameters for Bursty Transmission using LSTM Network

AU - Liu, Xiaobei

AU - Guan, Yong Liang

AU - Qin, Yan

PY - 2023

Y1 - 2023

N2 - Continuous phase frequency shift keying (CPFSK) has been widely used in wireless communications, as its continuous phase and constant envelop lead to high bandwidth and power efficiency. In non-cooperative communication systems, the CPFSK parameters such as modulation index, pulse shape and pulse length are unknown to the receiver and need to be estimated. This is a challenging task especially when the transmission is bursty. In this paper, long short term memory (LSTM) neural networks are proposed to tackle this problem. Specifically, three LSTM networks with identical structure but trained separately are used to estimate three important CPFSK parameters (modulation index h, pulse length L and pulse shape q(t)) in parallel. Simulation results show that by suitably preprocessing the input data before the LSTM network, the proposed blind estimation scheme is able achieve high estimation accuracy of more than 95% in most cases.

AB - Continuous phase frequency shift keying (CPFSK) has been widely used in wireless communications, as its continuous phase and constant envelop lead to high bandwidth and power efficiency. In non-cooperative communication systems, the CPFSK parameters such as modulation index, pulse shape and pulse length are unknown to the receiver and need to be estimated. This is a challenging task especially when the transmission is bursty. In this paper, long short term memory (LSTM) neural networks are proposed to tackle this problem. Specifically, three LSTM networks with identical structure but trained separately are used to estimate three important CPFSK parameters (modulation index h, pulse length L and pulse shape q(t)) in parallel. Simulation results show that by suitably preprocessing the input data before the LSTM network, the proposed blind estimation scheme is able achieve high estimation accuracy of more than 95% in most cases.

KW - blind estimation

KW - Continuous phase frequency shift keying

KW - deep neural network

KW - long short-term memory

UR - http://www.scopus.com/inward/record.url?scp=85187375487&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85187375487&partnerID=8YFLogxK

U2 - 10.1109/GLOBECOM54140.2023.10437082

DO - 10.1109/GLOBECOM54140.2023.10437082

M3 - Conference contribution

AN - SCOPUS:85187375487

T3 - Proceedings - IEEE Global Communications Conference, GLOBECOM

SP - 7453

EP - 7458

BT - GLOBECOM 2023 - 2023 IEEE Global Communications Conference

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE Global Communications Conference, GLOBECOM 2023

Y2 - 4 December 2023 through 8 December 2023

ER -

Blind Estimation of CPFSK Parameters for Bursty Transmission using LSTM Network

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus Subject Areas

Keywords

Access to Document

Other files and links

Fingerprint

Cite this