Using sequence to sequence learning for digital BPSK and QPSK demodulation

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

Abstract

In the last few years Machine Learning (ML) has seen explosive growth in a wide range of research fields and industries. With the advancements in Software Defined Radio (SDR), which allows more intelligent, adaptive radio systems to be built, the wireless communications field has a number of opportunities to apply ML techniques. In this paper, a novel approach to demodulation using a Sequence to Sequence (Seq2Seq) model is proposed. This type of model is shown to work effectively with PSK data and also has a number of useful properties that are not present in other machine learning algorithms. A basic Seq2Seq implementation for BPSK and QPSK demodulation is presented in this paper, and learned properties such as Automatic Modulation Classification (AMC), and ability to adapt to different length input sequences, are demonstrated. This is an exciting new avenue of research that provides considerable potential for application in next generation 5G networks.
LanguageEnglish
Title of host publicationIEEE 5G World Forum
Place of PublicationPiscataway, NJ
PublisherIEEE
Number of pages4
Publication statusAccepted/In press - 30 Apr 2018
Event2018 IEEE 5G World Forum - Santa Clara, United States
Duration: 9 Jul 201811 Jul 2018

Conference

Conference2018 IEEE 5G World Forum
CountryUnited States
CitySanta Clara
Period9/07/1811/07/18

Fingerprint

Quadrature phase shift keying
Demodulation
Learning systems
Phase shift keying
Radio systems
Learning algorithms
Modulation
Communication
Industry

Keywords

  • machine learning
  • software defined radio
  • BPSK
  • QPSK

Cite this

@inproceedings{50289dff597e40328a3878c5a35b4419,
title = "Using sequence to sequence learning for digital BPSK and QPSK demodulation",
abstract = "In the last few years Machine Learning (ML) has seen explosive growth in a wide range of research fields and industries. With the advancements in Software Defined Radio (SDR), which allows more intelligent, adaptive radio systems to be built, the wireless communications field has a number of opportunities to apply ML techniques. In this paper, a novel approach to demodulation using a Sequence to Sequence (Seq2Seq) model is proposed. This type of model is shown to work effectively with PSK data and also has a number of useful properties that are not present in other machine learning algorithms. A basic Seq2Seq implementation for BPSK and QPSK demodulation is presented in this paper, and learned properties such as Automatic Modulation Classification (AMC), and ability to adapt to different length input sequences, are demonstrated. This is an exciting new avenue of research that provides considerable potential for application in next generation 5G networks.",
keywords = "machine learning, software defined radio, BPSK, QPSK",
author = "Sarunas Kalade and Louise Crockett and Robert Stewart",
note = "{\circledC} 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”",
year = "2018",
month = "4",
day = "30",
language = "English",
booktitle = "IEEE 5G World Forum",
publisher = "IEEE",

}

Kalade, S, Crockett, L & Stewart, R 2018, Using sequence to sequence learning for digital BPSK and QPSK demodulation. in IEEE 5G World Forum. IEEE, Piscataway, NJ, 2018 IEEE 5G World Forum, Santa Clara, United States, 9/07/18.

Using sequence to sequence learning for digital BPSK and QPSK demodulation. / Kalade, Sarunas; Crockett, Louise; Stewart, Robert.

IEEE 5G World Forum. Piscataway, NJ : IEEE, 2018.

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - Using sequence to sequence learning for digital BPSK and QPSK demodulation

AU - Kalade, Sarunas

AU - Crockett, Louise

AU - Stewart, Robert

N1 - © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”

PY - 2018/4/30

Y1 - 2018/4/30

N2 - In the last few years Machine Learning (ML) has seen explosive growth in a wide range of research fields and industries. With the advancements in Software Defined Radio (SDR), which allows more intelligent, adaptive radio systems to be built, the wireless communications field has a number of opportunities to apply ML techniques. In this paper, a novel approach to demodulation using a Sequence to Sequence (Seq2Seq) model is proposed. This type of model is shown to work effectively with PSK data and also has a number of useful properties that are not present in other machine learning algorithms. A basic Seq2Seq implementation for BPSK and QPSK demodulation is presented in this paper, and learned properties such as Automatic Modulation Classification (AMC), and ability to adapt to different length input sequences, are demonstrated. This is an exciting new avenue of research that provides considerable potential for application in next generation 5G networks.

AB - In the last few years Machine Learning (ML) has seen explosive growth in a wide range of research fields and industries. With the advancements in Software Defined Radio (SDR), which allows more intelligent, adaptive radio systems to be built, the wireless communications field has a number of opportunities to apply ML techniques. In this paper, a novel approach to demodulation using a Sequence to Sequence (Seq2Seq) model is proposed. This type of model is shown to work effectively with PSK data and also has a number of useful properties that are not present in other machine learning algorithms. A basic Seq2Seq implementation for BPSK and QPSK demodulation is presented in this paper, and learned properties such as Automatic Modulation Classification (AMC), and ability to adapt to different length input sequences, are demonstrated. This is an exciting new avenue of research that provides considerable potential for application in next generation 5G networks.

KW - machine learning

KW - software defined radio

KW - BPSK

KW - QPSK

UR - http://ieee-wf-5g.org/

M3 - Conference contribution book

BT - IEEE 5G World Forum

PB - IEEE

CY - Piscataway, NJ

ER -