The Application of Deep Learning in Communication Signal Modulation Recognition

Yun Lin; Ya Tu; Zheng Dou; Zhiqiang Wu

doi:10.1109/ICCChina.2017.8330488

The Application of Deep Learning in Communication Signal Modulation Recognition

Yun Lin, Ya Tu, Zheng Dou, Zhiqiang Wu

Electrical Engineering

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

Abstract

Automated Modulation Classification (AMC) has been applied in various emerging areas such as cognitive radio (CR). We also notice that Deep Learning (DL) is a powerful classification tool that has gained great popularity in various field. This article focuses on DL and aims at using it to solve communications problems. We propose a new data conversion algorithm in order to gain a better classification accuracy of communication signal modulation. This paper will show that our new method will bring significant improvement in signal modulation classification accuracy. Besides, AlexNet and GoogLeNet, two well-known DL network models, ResNet and VGG, will be utilized in this task to compare with each other.

Original language	English
Title of host publication	2017 IEEE/CIC International Conference on Communications in China (ICCC)
Publisher	IEEE
Pages	1-5
Number of pages	5
ISBN (Electronic)	978-1-5386-4502-4, 978-1-5386-5557-3
ISBN (Print)	978-1-5386-4503-1
DOIs	https://doi.org/10.1109/ICCChina.2017.8330488
State	Published - Apr 2 2018
Event	2017 IEEE/CIC International Conference on Communications in China, ICCC 2017 - Qingdao, China Duration: Oct 22 2017 → Oct 24 2017

Conference

Conference	2017 IEEE/CIC International Conference on Communications in China, ICCC 2017
Country/Territory	China
City	Qingdao
Period	10/22/17 → 10/24/17

ASJC Scopus Subject Areas

Computer Networks and Communications
Computer Science Applications
Signal Processing

Keywords

AlexNet
Convolutional Networks
Deep Learning
GoogLeNet
ResNet
VGG
modulation recognition
Machine learning
Training
Task analysis
Feature extraction
Constellation diagram
Communication systems

Disciplines

Electrical and Computer Engineering

Access to Document

10.1109/ICCChina.2017.8330488License: Unspecified

Cite this

@inproceedings{734a06e9c3bf4ba4ae322981785a89df,

title = "The Application of Deep Learning in Communication Signal Modulation Recognition",

abstract = "Automated Modulation Classification (AMC) has been applied in various emerging areas such as cognitive radio (CR). We also notice that Deep Learning (DL) is a powerful classification tool that has gained great popularity in various field. This article focuses on DL and aims at using it to solve communications problems. We propose a new data conversion algorithm in order to gain a better classification accuracy of communication signal modulation. This paper will show that our new method will bring significant improvement in signal modulation classification accuracy. Besides, AlexNet and GoogLeNet, two well-known DL network models, ResNet and VGG, will be utilized in this task to compare with each other.",

keywords = "AlexNet, Convolutional Networks, Deep Learning, GoogLeNet, ResNet, VGG, modulation recognition, Machine learning, Training, Task analysis, Feature extraction, Constellation diagram, Communication systems",

author = "Yun Lin and Ya Tu and Zheng Dou and Zhiqiang Wu",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 2017 IEEE/CIC International Conference on Communications in China, ICCC 2017 ; Conference date: 22-10-2017 Through 24-10-2017",

year = "2018",

month = apr,

day = "2",

doi = "10.1109/ICCChina.2017.8330488",

language = "English",

isbn = "978-1-5386-4503-1",

pages = "1--5",

booktitle = "2017 IEEE/CIC International Conference on Communications in China (ICCC)",

publisher = "IEEE",

}

TY - GEN

T1 - The Application of Deep Learning in Communication Signal Modulation Recognition

AU - Lin, Yun

AU - Tu, Ya

AU - Dou, Zheng

AU - Wu, Zhiqiang

PY - 2018/4/2

Y1 - 2018/4/2

N2 - Automated Modulation Classification (AMC) has been applied in various emerging areas such as cognitive radio (CR). We also notice that Deep Learning (DL) is a powerful classification tool that has gained great popularity in various field. This article focuses on DL and aims at using it to solve communications problems. We propose a new data conversion algorithm in order to gain a better classification accuracy of communication signal modulation. This paper will show that our new method will bring significant improvement in signal modulation classification accuracy. Besides, AlexNet and GoogLeNet, two well-known DL network models, ResNet and VGG, will be utilized in this task to compare with each other.

AB - Automated Modulation Classification (AMC) has been applied in various emerging areas such as cognitive radio (CR). We also notice that Deep Learning (DL) is a powerful classification tool that has gained great popularity in various field. This article focuses on DL and aims at using it to solve communications problems. We propose a new data conversion algorithm in order to gain a better classification accuracy of communication signal modulation. This paper will show that our new method will bring significant improvement in signal modulation classification accuracy. Besides, AlexNet and GoogLeNet, two well-known DL network models, ResNet and VGG, will be utilized in this task to compare with each other.

KW - AlexNet

KW - Convolutional Networks

KW - Deep Learning

KW - GoogLeNet

KW - ResNet

KW - VGG

KW - modulation recognition

KW - Machine learning

KW - Training

KW - Task analysis

KW - Feature extraction

KW - Constellation diagram

KW - Communication systems

UR - http://www.scopus.com/inward/record.url?scp=85049665836&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049665836&partnerID=8YFLogxK

UR - https://corescholar.libraries.wright.edu/ee/61

U2 - 10.1109/ICCChina.2017.8330488

DO - 10.1109/ICCChina.2017.8330488

M3 - Conference contribution

AN - SCOPUS:85049665836

SN - 978-1-5386-4503-1

SP - 1

EP - 5

BT - 2017 IEEE/CIC International Conference on Communications in China (ICCC)

PB - IEEE

T2 - 2017 IEEE/CIC International Conference on Communications in China, ICCC 2017

Y2 - 22 October 2017 through 24 October 2017

ER -

The Application of Deep Learning in Communication Signal Modulation Recognition

Abstract

Conference

ASJC Scopus Subject Areas

Keywords

Disciplines

Access to Document

Other files and links

Cite this