Hierarchical Modulation Classification Using Deep Learning

Garrett Vanhoy, Noah Thurston, Andrew Burger, Jacob Breckenridge, Tamal Bose

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

Abstract

Recent work in modulation classification using deep learning has produced promising results in classifying a diverse set of signals with only 128 IQ samples having undergone common radio impairments and frequency selective fading. Using deep learning as an approach differs significantly from established methods in classification where a set of expert features are derived and justified for specific channel conditions and computational resources. Instead, deep learning provides a way to efficiently identify features that are best suited for any set modulations, channel conditions, or available resources that may be of interest. However, deep learning approaches have only recently been used in this area and many questions about its limitations still exist. In this work, an expanded set of signals that include radar signals, multi -carrier signals, and higher order modulations are used with architectures presented in previous work to gain further insight into the flexibility of this approach. With a total of 29 signals to classify, it's shown how previous approaches can be augmented by training the network to classify signals on several hierarchical levels simultaneously with improved classification accuracy and a more flexible network architecture. Branch convolutional neural networks (B-CNN), which have been used to identify the subject of a body of text within a large hierarchy of subjects, are adapted to the problem of modulation classification to improve classification accuracy and facilitate the development of networks that can classify an even more diverse set of signals.

Original languageEnglish (US)
Title of host publication2018 IEEE Military Communications Conference, MILCOM 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages20-25
Number of pages6
ISBN (Electronic)9781538671856
DOIs
StatePublished - Jan 2 2019
Event2018 IEEE Military Communications Conference, MILCOM 2018 - Los Angeles, United States
Duration: Oct 29 2018Oct 31 2018

Publication series

NameProceedings - IEEE Military Communications Conference MILCOM
Volume2019-October

Conference

Conference2018 IEEE Military Communications Conference, MILCOM 2018
CountryUnited States
CityLos Angeles
Period10/29/1810/31/18

Fingerprint

Modulation
Frequency selective fading
Network architecture
Radar
Deep learning
Neural networks

Keywords

  • Convolutional Neural Networks
  • Deep Learning
  • Hierarchical Modulation Classification

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Vanhoy, G., Thurston, N., Burger, A., Breckenridge, J., & Bose, T. (2019). Hierarchical Modulation Classification Using Deep Learning. In 2018 IEEE Military Communications Conference, MILCOM 2018 (pp. 20-25). [8599861] (Proceedings - IEEE Military Communications Conference MILCOM; Vol. 2019-October). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MILCOM.2018.8599861

Hierarchical Modulation Classification Using Deep Learning. / Vanhoy, Garrett; Thurston, Noah; Burger, Andrew; Breckenridge, Jacob; Bose, Tamal.

2018 IEEE Military Communications Conference, MILCOM 2018. Institute of Electrical and Electronics Engineers Inc., 2019. p. 20-25 8599861 (Proceedings - IEEE Military Communications Conference MILCOM; Vol. 2019-October).

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

Vanhoy, G, Thurston, N, Burger, A, Breckenridge, J & Bose, T 2019, Hierarchical Modulation Classification Using Deep Learning. in 2018 IEEE Military Communications Conference, MILCOM 2018., 8599861, Proceedings - IEEE Military Communications Conference MILCOM, vol. 2019-October, Institute of Electrical and Electronics Engineers Inc., pp. 20-25, 2018 IEEE Military Communications Conference, MILCOM 2018, Los Angeles, United States, 10/29/18. https://doi.org/10.1109/MILCOM.2018.8599861
Vanhoy G, Thurston N, Burger A, Breckenridge J, Bose T. Hierarchical Modulation Classification Using Deep Learning. In 2018 IEEE Military Communications Conference, MILCOM 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 20-25. 8599861. (Proceedings - IEEE Military Communications Conference MILCOM). https://doi.org/10.1109/MILCOM.2018.8599861
Vanhoy, Garrett ; Thurston, Noah ; Burger, Andrew ; Breckenridge, Jacob ; Bose, Tamal. / Hierarchical Modulation Classification Using Deep Learning. 2018 IEEE Military Communications Conference, MILCOM 2018. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 20-25 (Proceedings - IEEE Military Communications Conference MILCOM).
@inproceedings{cfa4ceec5a8342ae951852d854c4c829,
title = "Hierarchical Modulation Classification Using Deep Learning",
abstract = "Recent work in modulation classification using deep learning has produced promising results in classifying a diverse set of signals with only 128 IQ samples having undergone common radio impairments and frequency selective fading. Using deep learning as an approach differs significantly from established methods in classification where a set of expert features are derived and justified for specific channel conditions and computational resources. Instead, deep learning provides a way to efficiently identify features that are best suited for any set modulations, channel conditions, or available resources that may be of interest. However, deep learning approaches have only recently been used in this area and many questions about its limitations still exist. In this work, an expanded set of signals that include radar signals, multi -carrier signals, and higher order modulations are used with architectures presented in previous work to gain further insight into the flexibility of this approach. With a total of 29 signals to classify, it's shown how previous approaches can be augmented by training the network to classify signals on several hierarchical levels simultaneously with improved classification accuracy and a more flexible network architecture. Branch convolutional neural networks (B-CNN), which have been used to identify the subject of a body of text within a large hierarchy of subjects, are adapted to the problem of modulation classification to improve classification accuracy and facilitate the development of networks that can classify an even more diverse set of signals.",
keywords = "Convolutional Neural Networks, Deep Learning, Hierarchical Modulation Classification",
author = "Garrett Vanhoy and Noah Thurston and Andrew Burger and Jacob Breckenridge and Tamal Bose",
year = "2019",
month = "1",
day = "2",
doi = "10.1109/MILCOM.2018.8599861",
language = "English (US)",
series = "Proceedings - IEEE Military Communications Conference MILCOM",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "20--25",
booktitle = "2018 IEEE Military Communications Conference, MILCOM 2018",

}

TY - GEN

T1 - Hierarchical Modulation Classification Using Deep Learning

AU - Vanhoy, Garrett

AU - Thurston, Noah

AU - Burger, Andrew

AU - Breckenridge, Jacob

AU - Bose, Tamal

PY - 2019/1/2

Y1 - 2019/1/2

N2 - Recent work in modulation classification using deep learning has produced promising results in classifying a diverse set of signals with only 128 IQ samples having undergone common radio impairments and frequency selective fading. Using deep learning as an approach differs significantly from established methods in classification where a set of expert features are derived and justified for specific channel conditions and computational resources. Instead, deep learning provides a way to efficiently identify features that are best suited for any set modulations, channel conditions, or available resources that may be of interest. However, deep learning approaches have only recently been used in this area and many questions about its limitations still exist. In this work, an expanded set of signals that include radar signals, multi -carrier signals, and higher order modulations are used with architectures presented in previous work to gain further insight into the flexibility of this approach. With a total of 29 signals to classify, it's shown how previous approaches can be augmented by training the network to classify signals on several hierarchical levels simultaneously with improved classification accuracy and a more flexible network architecture. Branch convolutional neural networks (B-CNN), which have been used to identify the subject of a body of text within a large hierarchy of subjects, are adapted to the problem of modulation classification to improve classification accuracy and facilitate the development of networks that can classify an even more diverse set of signals.

AB - Recent work in modulation classification using deep learning has produced promising results in classifying a diverse set of signals with only 128 IQ samples having undergone common radio impairments and frequency selective fading. Using deep learning as an approach differs significantly from established methods in classification where a set of expert features are derived and justified for specific channel conditions and computational resources. Instead, deep learning provides a way to efficiently identify features that are best suited for any set modulations, channel conditions, or available resources that may be of interest. However, deep learning approaches have only recently been used in this area and many questions about its limitations still exist. In this work, an expanded set of signals that include radar signals, multi -carrier signals, and higher order modulations are used with architectures presented in previous work to gain further insight into the flexibility of this approach. With a total of 29 signals to classify, it's shown how previous approaches can be augmented by training the network to classify signals on several hierarchical levels simultaneously with improved classification accuracy and a more flexible network architecture. Branch convolutional neural networks (B-CNN), which have been used to identify the subject of a body of text within a large hierarchy of subjects, are adapted to the problem of modulation classification to improve classification accuracy and facilitate the development of networks that can classify an even more diverse set of signals.

KW - Convolutional Neural Networks

KW - Deep Learning

KW - Hierarchical Modulation Classification

UR - http://www.scopus.com/inward/record.url?scp=85061454195&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061454195&partnerID=8YFLogxK

U2 - 10.1109/MILCOM.2018.8599861

DO - 10.1109/MILCOM.2018.8599861

M3 - Conference contribution

AN - SCOPUS:85061454195

T3 - Proceedings - IEEE Military Communications Conference MILCOM

SP - 20

EP - 25

BT - 2018 IEEE Military Communications Conference, MILCOM 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -