Deep Learning-Based Codebook Design for Code-Domain Non-Orthogonal Multiple Access: Approaching Single-User Bit-Error Rate Performance

Han, Minsig; Seo, Hanchang; Abebe, Ameha T.; Kang, Chung G.

doi:10.1109/tccn.2021.3130308

Cited by 8 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that the number of available CBs is limited due to the complexity of designing CB for SCMA, which grows exponentially with J [10]. Therefore, the number of CBs is much smaller than the number of users, i.e., J K. If two or more users employ the same CB, they will be collided.…”

Section: System Model a Grant-free Scma Systemmentioning

confidence: 99%

“…, δ N −1 ĥN−1 ] T . Finally, active users' transmitted bit sequences is detected by a BS performs MUD, e.g., the message passing algorithm (MPA)-based MUD [9] or NN-based MUD [10], using δ, ĥδ , and the received data stream {y…”

Section: Decoded Data Bits For Active Usersmentioning

confidence: 99%

“…2, i.e., without considering a collision performance as in [5]- [8]. Meanwhile, the SCMA CBs herein are optimized independently, e.g., using the conventional or DL-based design approaches in [9]- [10].…”

Section: A Overall End-to-end Ae Architecturementioning

confidence: 99%

See 2 more Smart Citations

Data-aided Active User Detection with a User Activity Extraction Network for Grant-free SCMA Systems

Han¹,

Abebe²,

Kang³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

In grant-free sparse code multiple access system, joint optimization of contention resources for users and active user detection (AUD) at the receiver is a complex combinatorial problem. To this end, we propose a deep learning-based dataaided AUD scheme which extracts a priori user activity information via a novel user activity extraction network (UAEN). This is enabled by an end-to-end training of an autoencoder (AE), which simultaneously optimizes the contention resources, i.e., preamble sequences, each associated with one of the codebooks, and extraction of user activity information from both preamble and data transmission. Furthermore, we propose self-supervised pretraining scheme for the UAEN, which ensures the convergence of offline end-to-end training. Simulation results demonstrated that the proposed AUD scheme achieved 3 to 5dB gain at a target activity detection error rate of 10 −3 compared to the state-ofthe-art DL-based AUD schemes.

show abstract

Section: System Model a Grant-free Scma Systemmentioning

confidence: 99%

Section: Decoded Data Bits For Active Usersmentioning

confidence: 99%