Multi-Channel Learning with Preprocessing for Automatic Modulation Order Separation

Gizem Sumen; Burak Ahmet Celebi; Gunes Karabulut Kurt; Ali Gorcin; Semiha Tedik Basaran

doi:10.1109/ISCC55528.2022.9912830

Multi-Channel Learning with Preprocessing for Automatic Modulation Order Separation

Gizem Sumen, Burak Ahmet Celebi, Gunes Karabulut Kurt, Ali Gorcin, Semiha Tedik Basaran

Department of Electronics and Communication Engineering

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

1 Citation (Scopus)

Abstract

Automatic modulation classification (AMC) with deep learning (DL) based methods has been studied in recent years and improvements have been shown in many studies; however, it has been difficult to design a classifier that can distinguish modulation orders such as 16-QAM and 64-QAM, with high accuracy. In this study, the distinction performance of 16-QAM and 64-QAM modulation orders increased by feeding the features obtained during the preprocessing stage to the multi-channel convolutional long short-term deep neural network (MCLDNN). Simulation results indicate performance improvements, particularly at the low SNR region. Furthermore, the proposed method can be extended for the separation of other orders of QAM and other digital modulations.

Original language	English
Title of host publication	2022 IEEE Symposium on Computers and Communications, ISCC 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665497923
DOIs	https://doi.org/10.1109/ISCC55528.2022.9912830
Publication status	Published - 2022
Event	27th IEEE Symposium on Computers and Communications, ISCC 2022 - Rhodes, Greece Duration: 30 Jun 2022 → 3 Jul 2022

Publication series

Name	Proceedings - IEEE Symposium on Computers and Communications
Volume	2022-June
ISSN (Print)	1530-1346

Conference

Conference	27th IEEE Symposium on Computers and Communications, ISCC 2022
Country/Territory	Greece
City	Rhodes
Period	30/06/22 → 3/07/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

Automatic modulation classification
convolutional neural network
cumulant
deep learning
feature extraction

Access to Document

10.1109/ISCC55528.2022.9912830

Cite this

Sumen, G., Celebi, B. A., Kurt, G. K., Gorcin, A., & Basaran, S. T. (2022). Multi-Channel Learning with Preprocessing for Automatic Modulation Order Separation. In 2022 IEEE Symposium on Computers and Communications, ISCC 2022 (Proceedings - IEEE Symposium on Computers and Communications; Vol. 2022-June). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISCC55528.2022.9912830

@inproceedings{e13cda258d7546de8d7fd3350d059144,

title = "Multi-Channel Learning with Preprocessing for Automatic Modulation Order Separation",

abstract = "Automatic modulation classification (AMC) with deep learning (DL) based methods has been studied in recent years and improvements have been shown in many studies; however, it has been difficult to design a classifier that can distinguish modulation orders such as 16-QAM and 64-QAM, with high accuracy. In this study, the distinction performance of 16-QAM and 64-QAM modulation orders increased by feeding the features obtained during the preprocessing stage to the multi-channel convolutional long short-term deep neural network (MCLDNN). Simulation results indicate performance improvements, particularly at the low SNR region. Furthermore, the proposed method can be extended for the separation of other orders of QAM and other digital modulations.",

keywords = "Automatic modulation classification, convolutional neural network, cumulant, deep learning, feature extraction",

author = "Gizem Sumen and Celebi, {Burak Ahmet} and Kurt, {Gunes Karabulut} and Ali Gorcin and Basaran, {Semiha Tedik}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 27th IEEE Symposium on Computers and Communications, ISCC 2022 ; Conference date: 30-06-2022 Through 03-07-2022",

year = "2022",

doi = "10.1109/ISCC55528.2022.9912830",

language = "English",

series = "Proceedings - IEEE Symposium on Computers and Communications",

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

booktitle = "2022 IEEE Symposium on Computers and Communications, ISCC 2022",

address = "United States",

}

Sumen, G, Celebi, BA, Kurt, GK, Gorcin, A & Basaran, ST 2022, Multi-Channel Learning with Preprocessing for Automatic Modulation Order Separation. in 2022 IEEE Symposium on Computers and Communications, ISCC 2022. Proceedings - IEEE Symposium on Computers and Communications, vol. 2022-June, Institute of Electrical and Electronics Engineers Inc., 27th IEEE Symposium on Computers and Communications, ISCC 2022, Rhodes, Greece, 30/06/22. https://doi.org/10.1109/ISCC55528.2022.9912830

Multi-Channel Learning with Preprocessing for Automatic Modulation Order Separation. / Sumen, Gizem; Celebi, Burak Ahmet; Kurt, Gunes Karabulut et al.
2022 IEEE Symposium on Computers and Communications, ISCC 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (Proceedings - IEEE Symposium on Computers and Communications; Vol. 2022-June).

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

TY - GEN

T1 - Multi-Channel Learning with Preprocessing for Automatic Modulation Order Separation

AU - Sumen, Gizem

AU - Celebi, Burak Ahmet

AU - Kurt, Gunes Karabulut

AU - Gorcin, Ali

AU - Basaran, Semiha Tedik

PY - 2022

Y1 - 2022

N2 - Automatic modulation classification (AMC) with deep learning (DL) based methods has been studied in recent years and improvements have been shown in many studies; however, it has been difficult to design a classifier that can distinguish modulation orders such as 16-QAM and 64-QAM, with high accuracy. In this study, the distinction performance of 16-QAM and 64-QAM modulation orders increased by feeding the features obtained during the preprocessing stage to the multi-channel convolutional long short-term deep neural network (MCLDNN). Simulation results indicate performance improvements, particularly at the low SNR region. Furthermore, the proposed method can be extended for the separation of other orders of QAM and other digital modulations.

AB - Automatic modulation classification (AMC) with deep learning (DL) based methods has been studied in recent years and improvements have been shown in many studies; however, it has been difficult to design a classifier that can distinguish modulation orders such as 16-QAM and 64-QAM, with high accuracy. In this study, the distinction performance of 16-QAM and 64-QAM modulation orders increased by feeding the features obtained during the preprocessing stage to the multi-channel convolutional long short-term deep neural network (MCLDNN). Simulation results indicate performance improvements, particularly at the low SNR region. Furthermore, the proposed method can be extended for the separation of other orders of QAM and other digital modulations.

KW - Automatic modulation classification

KW - convolutional neural network

KW - cumulant

KW - deep learning

KW - feature extraction

UR - http://www.scopus.com/inward/record.url?scp=85141154525&partnerID=8YFLogxK

U2 - 10.1109/ISCC55528.2022.9912830

DO - 10.1109/ISCC55528.2022.9912830

M3 - Conference contribution

AN - SCOPUS:85141154525

T3 - Proceedings - IEEE Symposium on Computers and Communications

BT - 2022 IEEE Symposium on Computers and Communications, ISCC 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 27th IEEE Symposium on Computers and Communications, ISCC 2022

Y2 - 30 June 2022 through 3 July 2022

ER -

Multi-Channel Learning with Preprocessing for Automatic Modulation Order Separation

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this