Deep Receiver Design for Multi-carrier Waveforms Using CNNs

Yasin Yildirim; Sedat Ozer; Hakan Ali Cirpan

doi:10.1109/TSP49548.2020.9163562

Deep Receiver Design for Multi-carrier Waveforms Using CNNs

Yasin Yildirim, Sedat Ozer, Hakan Ali Cirpan

Department of Electronics and Communication Engineering

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

5 Citations (Scopus)

Abstract

In this paper, a deep learning based receiver is proposed for a collection of multi-carrier wave-forms including both current and next-generation wireless communication systems. In particular, we propose to use a convolutional neural network (CNN) for jointly detection and demodulation of the received signal at the receiver in wireless environments. We compare our proposed architecture to the classical methods and demonstrate that our proposed CNN-based architecture can perform better on different multi-carrier forms including OFDM and GFDM in various simulations. Furthermore, we compare the total number of required parameters for each network for memory requirements.

Original language	English
Title of host publication	2020 43rd International Conference on Telecommunications and Signal Processing, TSP 2020
Editors	Norbert Herencsar
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	31-36
Number of pages	6
ISBN (Electronic)	9781728163765
DOIs	https://doi.org/10.1109/TSP49548.2020.9163562
Publication status	Published - Jul 2020
Event	43rd International Conference on Telecommunications and Signal Processing, TSP 2020 - Milan, Italy Duration: 7 Jul 2020 → 9 Jul 2020

Publication series

Name	2020 43rd International Conference on Telecommunications and Signal Processing, TSP 2020

Conference

Conference	43rd International Conference on Telecommunications and Signal Processing, TSP 2020
Country/Territory	Italy
City	Milan
Period	7/07/20 → 9/07/20

Bibliographical note

Publisher Copyright:
© 2020 IEEE.

Keywords

CNN
Deep Learning
Deep Receiver Design
GFDM
Multi-carrier Wave-forms
OFDM

Access to Document

10.1109/TSP49548.2020.9163562

Cite this

Yildirim, Y., Ozer, S., & Cirpan, H. A. (2020). Deep Receiver Design for Multi-carrier Waveforms Using CNNs. In N. Herencsar (Ed.), 2020 43rd International Conference on Telecommunications and Signal Processing, TSP 2020 (pp. 31-36). Article 9163562 (2020 43rd International Conference on Telecommunications and Signal Processing, TSP 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/TSP49548.2020.9163562

Yildirim, Yasin ; Ozer, Sedat ; Cirpan, Hakan Ali. / Deep Receiver Design for Multi-carrier Waveforms Using CNNs. 2020 43rd International Conference on Telecommunications and Signal Processing, TSP 2020. editor / Norbert Herencsar. Institute of Electrical and Electronics Engineers Inc., 2020. pp. 31-36 (2020 43rd International Conference on Telecommunications and Signal Processing, TSP 2020).

@inproceedings{3dea85111dda4a9a8676f6d2b7c7ee9a,

title = "Deep Receiver Design for Multi-carrier Waveforms Using CNNs",

abstract = "In this paper, a deep learning based receiver is proposed for a collection of multi-carrier wave-forms including both current and next-generation wireless communication systems. In particular, we propose to use a convolutional neural network (CNN) for jointly detection and demodulation of the received signal at the receiver in wireless environments. We compare our proposed architecture to the classical methods and demonstrate that our proposed CNN-based architecture can perform better on different multi-carrier forms including OFDM and GFDM in various simulations. Furthermore, we compare the total number of required parameters for each network for memory requirements.",

keywords = "CNN, Deep Learning, Deep Receiver Design, GFDM, Multi-carrier Wave-forms, OFDM",

author = "Yasin Yildirim and Sedat Ozer and Cirpan, {Hakan Ali}",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 43rd International Conference on Telecommunications and Signal Processing, TSP 2020 ; Conference date: 07-07-2020 Through 09-07-2020",

year = "2020",

month = jul,

doi = "10.1109/TSP49548.2020.9163562",

language = "English",

series = "2020 43rd International Conference on Telecommunications and Signal Processing, TSP 2020",

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

pages = "31--36",

editor = "Norbert Herencsar",

booktitle = "2020 43rd International Conference on Telecommunications and Signal Processing, TSP 2020",

address = "United States",

}

Yildirim, Y, Ozer, S & Cirpan, HA 2020, Deep Receiver Design for Multi-carrier Waveforms Using CNNs. in N Herencsar (ed.), 2020 43rd International Conference on Telecommunications and Signal Processing, TSP 2020., 9163562, 2020 43rd International Conference on Telecommunications and Signal Processing, TSP 2020, Institute of Electrical and Electronics Engineers Inc., pp. 31-36, 43rd International Conference on Telecommunications and Signal Processing, TSP 2020, Milan, Italy, 7/07/20. https://doi.org/10.1109/TSP49548.2020.9163562

Deep Receiver Design for Multi-carrier Waveforms Using CNNs. / Yildirim, Yasin; Ozer, Sedat; Cirpan, Hakan Ali.
2020 43rd International Conference on Telecommunications and Signal Processing, TSP 2020. ed. / Norbert Herencsar. Institute of Electrical and Electronics Engineers Inc., 2020. p. 31-36 9163562 (2020 43rd International Conference on Telecommunications and Signal Processing, TSP 2020).

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

TY - GEN

T1 - Deep Receiver Design for Multi-carrier Waveforms Using CNNs

AU - Yildirim, Yasin

AU - Ozer, Sedat

AU - Cirpan, Hakan Ali

PY - 2020/7

Y1 - 2020/7

N2 - In this paper, a deep learning based receiver is proposed for a collection of multi-carrier wave-forms including both current and next-generation wireless communication systems. In particular, we propose to use a convolutional neural network (CNN) for jointly detection and demodulation of the received signal at the receiver in wireless environments. We compare our proposed architecture to the classical methods and demonstrate that our proposed CNN-based architecture can perform better on different multi-carrier forms including OFDM and GFDM in various simulations. Furthermore, we compare the total number of required parameters for each network for memory requirements.

AB - In this paper, a deep learning based receiver is proposed for a collection of multi-carrier wave-forms including both current and next-generation wireless communication systems. In particular, we propose to use a convolutional neural network (CNN) for jointly detection and demodulation of the received signal at the receiver in wireless environments. We compare our proposed architecture to the classical methods and demonstrate that our proposed CNN-based architecture can perform better on different multi-carrier forms including OFDM and GFDM in various simulations. Furthermore, we compare the total number of required parameters for each network for memory requirements.

KW - CNN

KW - Deep Learning

KW - Deep Receiver Design

KW - GFDM

KW - Multi-carrier Wave-forms

KW - OFDM

UR - http://www.scopus.com/inward/record.url?scp=85090567216&partnerID=8YFLogxK

U2 - 10.1109/TSP49548.2020.9163562

DO - 10.1109/TSP49548.2020.9163562

M3 - Conference contribution

AN - SCOPUS:85090567216

T3 - 2020 43rd International Conference on Telecommunications and Signal Processing, TSP 2020

SP - 31

EP - 36

BT - 2020 43rd International Conference on Telecommunications and Signal Processing, TSP 2020

A2 - Herencsar, Norbert

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 43rd International Conference on Telecommunications and Signal Processing, TSP 2020

Y2 - 7 July 2020 through 9 July 2020

ER -

Yildirim Y, Ozer S, Cirpan HA. Deep Receiver Design for Multi-carrier Waveforms Using CNNs. In Herencsar N, editor, 2020 43rd International Conference on Telecommunications and Signal Processing, TSP 2020. Institute of Electrical and Electronics Engineers Inc. 2020. p. 31-36. 9163562. (2020 43rd International Conference on Telecommunications and Signal Processing, TSP 2020). doi: 10.1109/TSP49548.2020.9163562

Deep Receiver Design for Multi-carrier Waveforms Using CNNs

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this