Deep Learning-Based Data-Aided Activity Detection with Extraction Network for Grant-Free Sparse Code Multiple Access

Minsig Han; Metasebia D. Gemeda; Ameha T. Abebe; Chung G. Kang

doi:10.1109/WCNC61545.2025.10978572

Deep Learning-Based Data-Aided Activity Detection with Extraction Network for Grant-Free Sparse Code Multiple Access

Minsig Han^*
, Metasebia D. Gemeda^*
, Ameha T. Abebe
, Chung G. Kang^*

^*Corresponding author for this work

School of Electrical Engineering

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

Abstract

This work proposes a deep learning-based data-aided active user detection network (D-AUDN) for grant-free sparse code multiple access (SCMA) systems that leverages both SCMA codebook and Zadoff-Chu preamble for activity detection. Due to disparate data and preamble distribution as well as codebook collision, existing D-AUDNs experience performance degradation when multiple preambles are associated with each codebook. To address this, a user activity extraction network (UAEN) is integrated within the D-AUDN to extract a-priori activity information from the codebook, improving activity detection of the associated preambles. Additionally, efficient SCMA codebook design and preamble sequence association are considered to further enhance performance.

Original language	English
Title of host publication	2025 IEEE Wireless Communications and Networking Conference, WCNC 2025
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350368369
DOIs	https://doi.org/10.1109/WCNC61545.2025.10978572
Publication status	Published - 2025
Event	2025 IEEE Wireless Communications and Networking Conference, WCNC 2025 - Milan, Italy Duration: 2025 Mar 24 → 2025 Mar 27

Publication series

Name	IEEE Wireless Communications and Networking Conference, WCNC
ISSN (Print)	1525-3511

Conference

Conference	2025 IEEE Wireless Communications and Networking Conference, WCNC 2025
Country/Territory	Italy
City	Milan
Period	25/3/24 → 25/3/27

Bibliographical note

Publisher Copyright:
© 2025 IEEE.

Keywords

active user detection
deep learning
extraction network
Grant-free random access
sparse code multiple access

ASJC Scopus subject areas

General Engineering

Access to Document

10.1109/WCNC61545.2025.10978572

Cite this

Han, M., Gemeda, M. D., Abebe, A. T., & Kang, C. G. (2025). Deep Learning-Based Data-Aided Activity Detection with Extraction Network for Grant-Free Sparse Code Multiple Access. In 2025 IEEE Wireless Communications and Networking Conference, WCNC 2025 (IEEE Wireless Communications and Networking Conference, WCNC). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WCNC61545.2025.10978572

Deep Learning-Based Data-Aided Activity Detection with Extraction Network for Grant-Free Sparse Code Multiple Access. / Han, Minsig; Gemeda, Metasebia D.; Abebe, Ameha T. et al.
2025 IEEE Wireless Communications and Networking Conference, WCNC 2025. Institute of Electrical and Electronics Engineers Inc., 2025. (IEEE Wireless Communications and Networking Conference, WCNC).

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

Han, M, Gemeda, MD, Abebe, AT & Kang, CG 2025, Deep Learning-Based Data-Aided Activity Detection with Extraction Network for Grant-Free Sparse Code Multiple Access. in 2025 IEEE Wireless Communications and Networking Conference, WCNC 2025. IEEE Wireless Communications and Networking Conference, WCNC, Institute of Electrical and Electronics Engineers Inc., 2025 IEEE Wireless Communications and Networking Conference, WCNC 2025, Milan, Italy, 25/3/24. https://doi.org/10.1109/WCNC61545.2025.10978572

Han M, Gemeda MD, Abebe AT, Kang CG. Deep Learning-Based Data-Aided Activity Detection with Extraction Network for Grant-Free Sparse Code Multiple Access. In 2025 IEEE Wireless Communications and Networking Conference, WCNC 2025. Institute of Electrical and Electronics Engineers Inc. 2025. (IEEE Wireless Communications and Networking Conference, WCNC). doi: 10.1109/WCNC61545.2025.10978572

Han, Minsig ; Gemeda, Metasebia D. ; Abebe, Ameha T. et al. / Deep Learning-Based Data-Aided Activity Detection with Extraction Network for Grant-Free Sparse Code Multiple Access. 2025 IEEE Wireless Communications and Networking Conference, WCNC 2025. Institute of Electrical and Electronics Engineers Inc., 2025. (IEEE Wireless Communications and Networking Conference, WCNC).

@inproceedings{bd62b65d90c548d2b1bb757e77558d7f,

title = "Deep Learning-Based Data-Aided Activity Detection with Extraction Network for Grant-Free Sparse Code Multiple Access",

abstract = "This work proposes a deep learning-based data-aided active user detection network (D-AUDN) for grant-free sparse code multiple access (SCMA) systems that leverages both SCMA codebook and Zadoff-Chu preamble for activity detection. Due to disparate data and preamble distribution as well as codebook collision, existing D-AUDNs experience performance degradation when multiple preambles are associated with each codebook. To address this, a user activity extraction network (UAEN) is integrated within the D-AUDN to extract a-priori activity information from the codebook, improving activity detection of the associated preambles. Additionally, efficient SCMA codebook design and preamble sequence association are considered to further enhance performance.",

keywords = "active user detection, deep learning, extraction network, Grant-free random access, sparse code multiple access",

author = "Minsig Han and Gemeda, \{Metasebia D.\} and Abebe, \{Ameha T.\} and Kang, \{Chung G.\}",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 2025 IEEE Wireless Communications and Networking Conference, WCNC 2025 ; Conference date: 24-03-2025 Through 27-03-2025",

year = "2025",

doi = "10.1109/WCNC61545.2025.10978572",

language = "English",

series = "IEEE Wireless Communications and Networking Conference, WCNC",

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

booktitle = "2025 IEEE Wireless Communications and Networking Conference, WCNC 2025",

}

TY - GEN

T1 - Deep Learning-Based Data-Aided Activity Detection with Extraction Network for Grant-Free Sparse Code Multiple Access

AU - Han, Minsig

AU - Gemeda, Metasebia D.

AU - Abebe, Ameha T.

AU - Kang, Chung G.

PY - 2025

Y1 - 2025

N2 - This work proposes a deep learning-based data-aided active user detection network (D-AUDN) for grant-free sparse code multiple access (SCMA) systems that leverages both SCMA codebook and Zadoff-Chu preamble for activity detection. Due to disparate data and preamble distribution as well as codebook collision, existing D-AUDNs experience performance degradation when multiple preambles are associated with each codebook. To address this, a user activity extraction network (UAEN) is integrated within the D-AUDN to extract a-priori activity information from the codebook, improving activity detection of the associated preambles. Additionally, efficient SCMA codebook design and preamble sequence association are considered to further enhance performance.

AB - This work proposes a deep learning-based data-aided active user detection network (D-AUDN) for grant-free sparse code multiple access (SCMA) systems that leverages both SCMA codebook and Zadoff-Chu preamble for activity detection. Due to disparate data and preamble distribution as well as codebook collision, existing D-AUDNs experience performance degradation when multiple preambles are associated with each codebook. To address this, a user activity extraction network (UAEN) is integrated within the D-AUDN to extract a-priori activity information from the codebook, improving activity detection of the associated preambles. Additionally, efficient SCMA codebook design and preamble sequence association are considered to further enhance performance.

KW - active user detection

KW - deep learning

KW - extraction network

KW - Grant-free random access

KW - sparse code multiple access

UR - https://www.scopus.com/pages/publications/105006435380

U2 - 10.1109/WCNC61545.2025.10978572

DO - 10.1109/WCNC61545.2025.10978572

M3 - Conference contribution

AN - SCOPUS:105006435380

T3 - IEEE Wireless Communications and Networking Conference, WCNC

BT - 2025 IEEE Wireless Communications and Networking Conference, WCNC 2025

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2025 IEEE Wireless Communications and Networking Conference, WCNC 2025

Y2 - 24 March 2025 through 27 March 2025

ER -

Deep Learning-Based Data-Aided Activity Detection with Extraction Network for Grant-Free Sparse Code Multiple Access

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this