Deep Learning Based Hybrid Multiple Access Consisting of SCMA and OFDMA Using User Position Information

Yuta Kumagai; Naoya Gonda; Yukiko Shimbo; Hirofumi Suganuma; Fumiaki Maehara

doi:10.1109/ICAIIC51459.2021.9415180

Deep Learning Based Hybrid Multiple Access Consisting of SCMA and OFDMA Using User Position Information

Yuta Kumagai, Naoya Gonda, Yukiko Shimbo, Hirofumi Suganuma, Fumiaki Maehara^*

^*Corresponding author for this work

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

1 Citation (Scopus)

Abstract

This paper proposes a deep-learning-based uplink hybrid multiple access scheme consisting of both sparse code multiple access (SCMA) and orthogonal frequency-division multiple access (OFDMA). SCMA improves the system throughput when the carrier-To-noise ratio (CNR) is high. However, SCMA performance is significantly degraded, compared to OFDMA, when the CNR is low. To overcome this problem, the proposed scheme introduces a combination of SCMA and OFDMA as a novel multiple access pattern. The scheme determines the appropriate pattern among SCMA-only, OFDMA-only, or their combination, by utilizing user position information through deep learning. The effectiveness of the proposed scheme is demonstrated in terms of system throughput under different user distributions via computer simulations.

Original language	English
Title of host publication	3rd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	10-13
Number of pages	4
ISBN (Electronic)	9781728176383
DOIs	https://doi.org/10.1109/ICAIIC51459.2021.9415180
Publication status	Published - 2021 Apr 13
Event	3rd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2021 - Jeju Island, Korea, Republic of Duration: 2021 Apr 13 → 2021 Apr 16

Publication series

Name	3rd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2021

Conference

Conference	3rd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2021
Country/Territory	Korea, Republic of
City	Jeju Island
Period	21/4/13 → 21/4/16

Keywords

Sparse code multiple access (SCMA)
deep learning
orthogonal frequency-division multiple access (OFDMA)
system throughput
user position information

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Computer Science Applications
Information Systems
Information Systems and Management

Access to Document

10.1109/ICAIIC51459.2021.9415180

Cite this

Kumagai, Y., Gonda, N., Shimbo, Y., Suganuma, H., & Maehara, F. (2021). Deep Learning Based Hybrid Multiple Access Consisting of SCMA and OFDMA Using User Position Information. In 3rd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2021 (pp. 10-13). Article 9415180 (3rd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICAIIC51459.2021.9415180

Deep Learning Based Hybrid Multiple Access Consisting of SCMA and OFDMA Using User Position Information. / Kumagai, Yuta; Gonda, Naoya; Shimbo, Yukiko et al.
3rd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2021. Institute of Electrical and Electronics Engineers Inc., 2021. p. 10-13 9415180 (3rd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2021).

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

Kumagai, Y, Gonda, N, Shimbo, Y, Suganuma, H & Maehara, F 2021, Deep Learning Based Hybrid Multiple Access Consisting of SCMA and OFDMA Using User Position Information. in 3rd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2021., 9415180, 3rd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2021, Institute of Electrical and Electronics Engineers Inc., pp. 10-13, 3rd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2021, Jeju Island, Korea, Republic of, 21/4/13. https://doi.org/10.1109/ICAIIC51459.2021.9415180

Kumagai Y, Gonda N, Shimbo Y, Suganuma H, Maehara F. Deep Learning Based Hybrid Multiple Access Consisting of SCMA and OFDMA Using User Position Information. In 3rd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2021. Institute of Electrical and Electronics Engineers Inc. 2021. p. 10-13. 9415180. (3rd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2021). doi: 10.1109/ICAIIC51459.2021.9415180

Kumagai, Yuta ; Gonda, Naoya ; Shimbo, Yukiko et al. / Deep Learning Based Hybrid Multiple Access Consisting of SCMA and OFDMA Using User Position Information. 3rd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2021. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 10-13 (3rd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2021).

@inproceedings{11660b2053374f549f7245f1e91a13aa,

title = "Deep Learning Based Hybrid Multiple Access Consisting of SCMA and OFDMA Using User Position Information",

abstract = "This paper proposes a deep-learning-based uplink hybrid multiple access scheme consisting of both sparse code multiple access (SCMA) and orthogonal frequency-division multiple access (OFDMA). SCMA improves the system throughput when the carrier-To-noise ratio (CNR) is high. However, SCMA performance is significantly degraded, compared to OFDMA, when the CNR is low. To overcome this problem, the proposed scheme introduces a combination of SCMA and OFDMA as a novel multiple access pattern. The scheme determines the appropriate pattern among SCMA-only, OFDMA-only, or their combination, by utilizing user position information through deep learning. The effectiveness of the proposed scheme is demonstrated in terms of system throughput under different user distributions via computer simulations.",

keywords = "Sparse code multiple access (SCMA), deep learning, orthogonal frequency-division multiple access (OFDMA), system throughput, user position information",

author = "Yuta Kumagai and Naoya Gonda and Yukiko Shimbo and Hirofumi Suganuma and Fumiaki Maehara",

note = "Funding Information: This work was supported by JSPS Grant-in-Aid for tific Research (C) Grant Number 19K04381. Publisher Copyright: {\textcopyright} 2021 IEEE.; 3rd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2021 ; Conference date: 13-04-2021 Through 16-04-2021",

year = "2021",

month = apr,

day = "13",

doi = "10.1109/ICAIIC51459.2021.9415180",

language = "English",

series = "3rd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2021",

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

pages = "10--13",

booktitle = "3rd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2021",

}

TY - GEN

T1 - Deep Learning Based Hybrid Multiple Access Consisting of SCMA and OFDMA Using User Position Information

AU - Kumagai, Yuta

AU - Gonda, Naoya

AU - Shimbo, Yukiko

AU - Suganuma, Hirofumi

AU - Maehara, Fumiaki

PY - 2021/4/13

Y1 - 2021/4/13

N2 - This paper proposes a deep-learning-based uplink hybrid multiple access scheme consisting of both sparse code multiple access (SCMA) and orthogonal frequency-division multiple access (OFDMA). SCMA improves the system throughput when the carrier-To-noise ratio (CNR) is high. However, SCMA performance is significantly degraded, compared to OFDMA, when the CNR is low. To overcome this problem, the proposed scheme introduces a combination of SCMA and OFDMA as a novel multiple access pattern. The scheme determines the appropriate pattern among SCMA-only, OFDMA-only, or their combination, by utilizing user position information through deep learning. The effectiveness of the proposed scheme is demonstrated in terms of system throughput under different user distributions via computer simulations.

AB - This paper proposes a deep-learning-based uplink hybrid multiple access scheme consisting of both sparse code multiple access (SCMA) and orthogonal frequency-division multiple access (OFDMA). SCMA improves the system throughput when the carrier-To-noise ratio (CNR) is high. However, SCMA performance is significantly degraded, compared to OFDMA, when the CNR is low. To overcome this problem, the proposed scheme introduces a combination of SCMA and OFDMA as a novel multiple access pattern. The scheme determines the appropriate pattern among SCMA-only, OFDMA-only, or their combination, by utilizing user position information through deep learning. The effectiveness of the proposed scheme is demonstrated in terms of system throughput under different user distributions via computer simulations.

KW - Sparse code multiple access (SCMA)

KW - deep learning

KW - orthogonal frequency-division multiple access (OFDMA)

KW - system throughput

KW - user position information

UR - http://www.scopus.com/inward/record.url?scp=85105509566&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85105509566&partnerID=8YFLogxK

U2 - 10.1109/ICAIIC51459.2021.9415180

DO - 10.1109/ICAIIC51459.2021.9415180

M3 - Conference contribution

AN - SCOPUS:85105509566

T3 - 3rd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2021

SP - 10

EP - 13

BT - 3rd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 3rd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2021

Y2 - 13 April 2021 through 16 April 2021

ER -

Deep Learning Based Hybrid Multiple Access Consisting of SCMA and OFDMA Using User Position Information

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this