Low-SNR Modulation Recognition based on Deep Learning on Software Defined Radio

Husam Alzaq-Osmanoglu; Jilan Alrehaili; B. Berk Ustundag

doi:10.1109/CommNet56067.2022.9993934

Low-SNR Modulation Recognition based on Deep Learning on Software Defined Radio

Husam Alzaq-Osmanoglu, Jilan Alrehaili, B. Berk Ustundag

Department of Computer Engineering

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

2 Citations (Scopus)

Abstract

Automatic modulation classification (AMC) and recognition (AMR) of received wireless signals have a significant role for various commercial and military areas. These methods are able to identify the modulation type and recognize the received signal by extracting discriminating features from the signals. Deep neural network (DNN) offer a great tool that assist the identification of signal modulation because of its capability to extract complex features from the received signals. In this work, we propose a convolutional network model to classify the modulation type of a wireless signal at low-SNR values. The experimental results demonstrate that the proposed model correctly classify 72% digital signals at -4 dB. The accuracy can be increased if the similarities between QAM4 and QAM64, 8PSK and QPSK is reduced.

Original language	English
Title of host publication	Proceedings - 2022 5th International Conference on Advanced Communication Technologies and Networking, CommNet 2022
Editors	Faissal El Bouanani, Fouad Ayoub
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665450546
DOIs	https://doi.org/10.1109/CommNet56067.2022.9993934
Publication status	Published - 2022
Event	5th International Conference on Advanced Communication Technologies and Networking, CommNet 2022 - Virtual, Online, Morocco Duration: 12 Dec 2022 → 14 Dec 2022

Publication series

Name	Proceedings - 2022 5th International Conference on Advanced Communication Technologies and Networking, CommNet 2022

Conference

Conference	5th International Conference on Advanced Communication Technologies and Networking, CommNet 2022
Country/Territory	Morocco
City	Virtual, Online
Period	12/12/22 → 14/12/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

Cognitive Radio
Deep Neural Network
Digital Signal Processing

Access to Document

10.1109/CommNet56067.2022.9993934

Cite this

Alzaq-Osmanoglu, H., Alrehaili, J., & Ustundag, B. B. (2022). Low-SNR Modulation Recognition based on Deep Learning on Software Defined Radio. In F. El Bouanani, & F. Ayoub (Eds.), Proceedings - 2022 5th International Conference on Advanced Communication Technologies and Networking, CommNet 2022 (Proceedings - 2022 5th International Conference on Advanced Communication Technologies and Networking, CommNet 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CommNet56067.2022.9993934

Alzaq-Osmanoglu, Husam ; Alrehaili, Jilan ; Ustundag, B. Berk. / Low-SNR Modulation Recognition based on Deep Learning on Software Defined Radio. Proceedings - 2022 5th International Conference on Advanced Communication Technologies and Networking, CommNet 2022. editor / Faissal El Bouanani ; Fouad Ayoub. Institute of Electrical and Electronics Engineers Inc., 2022. (Proceedings - 2022 5th International Conference on Advanced Communication Technologies and Networking, CommNet 2022).

@inproceedings{65e7c1508bdf446f9918108adb17793a,

title = "Low-SNR Modulation Recognition based on Deep Learning on Software Defined Radio",

abstract = "Automatic modulation classification (AMC) and recognition (AMR) of received wireless signals have a significant role for various commercial and military areas. These methods are able to identify the modulation type and recognize the received signal by extracting discriminating features from the signals. Deep neural network (DNN) offer a great tool that assist the identification of signal modulation because of its capability to extract complex features from the received signals. In this work, we propose a convolutional network model to classify the modulation type of a wireless signal at low-SNR values. The experimental results demonstrate that the proposed model correctly classify 72% digital signals at -4 dB. The accuracy can be increased if the similarities between QAM4 and QAM64, 8PSK and QPSK is reduced.",

keywords = "Cognitive Radio, Deep Neural Network, Digital Signal Processing",

author = "Husam Alzaq-Osmanoglu and Jilan Alrehaili and Ustundag, {B. Berk}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 5th International Conference on Advanced Communication Technologies and Networking, CommNet 2022 ; Conference date: 12-12-2022 Through 14-12-2022",

year = "2022",

doi = "10.1109/CommNet56067.2022.9993934",

language = "English",

series = "Proceedings - 2022 5th International Conference on Advanced Communication Technologies and Networking, CommNet 2022",

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

editor = "{El Bouanani}, Faissal and Fouad Ayoub",

booktitle = "Proceedings - 2022 5th International Conference on Advanced Communication Technologies and Networking, CommNet 2022",

address = "United States",

}

Alzaq-Osmanoglu, H, Alrehaili, J & Ustundag, BB 2022, Low-SNR Modulation Recognition based on Deep Learning on Software Defined Radio. in F El Bouanani & F Ayoub (eds), Proceedings - 2022 5th International Conference on Advanced Communication Technologies and Networking, CommNet 2022. Proceedings - 2022 5th International Conference on Advanced Communication Technologies and Networking, CommNet 2022, Institute of Electrical and Electronics Engineers Inc., 5th International Conference on Advanced Communication Technologies and Networking, CommNet 2022, Virtual, Online, Morocco, 12/12/22. https://doi.org/10.1109/CommNet56067.2022.9993934

Low-SNR Modulation Recognition based on Deep Learning on Software Defined Radio. / Alzaq-Osmanoglu, Husam; Alrehaili, Jilan; Ustundag, B. Berk.
Proceedings - 2022 5th International Conference on Advanced Communication Technologies and Networking, CommNet 2022. ed. / Faissal El Bouanani; Fouad Ayoub. Institute of Electrical and Electronics Engineers Inc., 2022. (Proceedings - 2022 5th International Conference on Advanced Communication Technologies and Networking, CommNet 2022).

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

TY - GEN

T1 - Low-SNR Modulation Recognition based on Deep Learning on Software Defined Radio

AU - Alzaq-Osmanoglu, Husam

AU - Alrehaili, Jilan

AU - Ustundag, B. Berk

PY - 2022

Y1 - 2022

N2 - Automatic modulation classification (AMC) and recognition (AMR) of received wireless signals have a significant role for various commercial and military areas. These methods are able to identify the modulation type and recognize the received signal by extracting discriminating features from the signals. Deep neural network (DNN) offer a great tool that assist the identification of signal modulation because of its capability to extract complex features from the received signals. In this work, we propose a convolutional network model to classify the modulation type of a wireless signal at low-SNR values. The experimental results demonstrate that the proposed model correctly classify 72% digital signals at -4 dB. The accuracy can be increased if the similarities between QAM4 and QAM64, 8PSK and QPSK is reduced.

AB - Automatic modulation classification (AMC) and recognition (AMR) of received wireless signals have a significant role for various commercial and military areas. These methods are able to identify the modulation type and recognize the received signal by extracting discriminating features from the signals. Deep neural network (DNN) offer a great tool that assist the identification of signal modulation because of its capability to extract complex features from the received signals. In this work, we propose a convolutional network model to classify the modulation type of a wireless signal at low-SNR values. The experimental results demonstrate that the proposed model correctly classify 72% digital signals at -4 dB. The accuracy can be increased if the similarities between QAM4 and QAM64, 8PSK and QPSK is reduced.

KW - Cognitive Radio

KW - Deep Neural Network

KW - Digital Signal Processing

UR - http://www.scopus.com/inward/record.url?scp=85146490460&partnerID=8YFLogxK

U2 - 10.1109/CommNet56067.2022.9993934

DO - 10.1109/CommNet56067.2022.9993934

M3 - Conference contribution

AN - SCOPUS:85146490460

T3 - Proceedings - 2022 5th International Conference on Advanced Communication Technologies and Networking, CommNet 2022

BT - Proceedings - 2022 5th International Conference on Advanced Communication Technologies and Networking, CommNet 2022

A2 - El Bouanani, Faissal

A2 - Ayoub, Fouad

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 5th International Conference on Advanced Communication Technologies and Networking, CommNet 2022

Y2 - 12 December 2022 through 14 December 2022

ER -

Alzaq-Osmanoglu H, Alrehaili J, Ustundag BB. Low-SNR Modulation Recognition based on Deep Learning on Software Defined Radio. In El Bouanani F, Ayoub F, editors, Proceedings - 2022 5th International Conference on Advanced Communication Technologies and Networking, CommNet 2022. Institute of Electrical and Electronics Engineers Inc. 2022. (Proceedings - 2022 5th International Conference on Advanced Communication Technologies and Networking, CommNet 2022). doi: 10.1109/CommNet56067.2022.9993934

Low-SNR Modulation Recognition based on Deep Learning on Software Defined Radio

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this