A novel deep neural network based approach for sparse code multiple access

Lin, Jinzhi; Feng, Shijie; Zhang, Yun; Yang, Zhile; Zhang, Yong

doi:10.1016/j.neucom.2019.11.066

Cited by 30 publications

(20 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, some works using HDA coding for UHD and 3D videos transmission are emerging [33,36]. Deep learning based approaches have been investigated to improve the JSCC and JSCD [7,31,34], which brought interesting inspirations and performance improvements.…”

Section: Related Work 21 General Jscd Jscc and Cross-layer Schemesmentioning

confidence: 99%

Joint Source-Channel Decoding of Polar Codes for HEVC-Based Video Streaming

Lin

Zhang

et al. 2022

ACM Trans. Multimedia Comput. Commun. Appl.

Self Cite

View full text Add to dashboard Cite

Ultra High-Definition (UHD) and Virtual Reality (VR) video streaming over 5G networks are emerging, in which High-Efficiency Video Coding (HEVC) is used as source coding to compress videos more efficiently and polar code is used as channel coding to transmit bitstream reliably over an error-prone channel. In this article, a novel Joint Source-Channel Decoding (JSCD) of polar codes for HEVC-based video streaming is presented to improve the streaming reliability and visual quality. Firstly, a Kernel Density Estimation (KDE) fitting approach is proposed to estimate the positions of error channel decoded bits. Secondly, a modified polar decoder called R-SCFlip is designed to improve the channel decoding accuracy. Finally, to combine the KDE estimator and the R-SCFlip decoder together, the JSCD scheme is implemented in an iterative process. Extensive experimental results reveal that, compared to the conventional methods without JSCD, the error data-frame correction ratios are increased. Averagely, 1.07% and 1.11% Frame Error Ratio (FER) improvements have been achieved for Additive White Gaussian Noise (AWGN) and Rayleigh fading channels, respectively. Meanwhile, the qualities of the recovered videos are significantly improved. For the 2D videos, the average Peak Signal-to-Noise Ratio (PSNR) and Structural SIMilarity (SSIM) gains reach 14% and 34%, respectively. For the 360֯ videos, the average improvements in terms of Weighted-to-Spherically-uniform PSNR (WS-PSNR) and Voronoi-based Video Multimethod Assessment Fusion (VI-VMAF) reach 21% and 7%, respectively.

show abstract

Section: Related Work 21 General Jscd Jscc and Cross-layer Schemesmentioning

confidence: 99%

Joint Source-Channel Decoding of Polar Codes for HEVC-Based Video Streaming

Lin

Zhang

et al. 2022

ACM Trans. Multimedia Comput. Commun. Appl.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The SCMA technique has seen further improvement through the use of deep learning. In research conducted by Lin et al, 13 deep learning was used to improve the accuracy of codebooks and reduce the complexity of decoding at the receiver. The deep learning assisted SCMA system was found to outperform conventional SCMA systems significantly.…”

Section: Related Workmentioning

confidence: 99%

Particle swarm optimization of the spectral and energy efficiency of an SCMA‐based heterogeneous cellular network

Noma‐Osaghae

Misra

Ahuja

et al. 2022

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Background: The effect of stochastic small base station (SBS) deployment on the energy efficiency (EE) and spectral efficiency (SE) of sparse code multiple access (SCMA)-based heterogeneous cellular networks (HCNs) is still mostly unknown.Aim: This research study seeks to provide insight into the interaction between SE and EE in SBS sleep-mode enabled SCMA-based HCNs.Methodology: A model that characterizes the energy-spectral-efficiency (ESE) of a two-tier SBS sleep-mode enabled SCMA-based HCN was derived. A multiobjective optimization problem was formulated to maximize the SE and EE of the SCMA-based HCN simultaneously. The multiobjective optimization problem was solved using a proposed weighted sum modified particle swarm optimization algorithm (PSO). A comparison was made between the performance of the proposed weighted sum modified PSO algorithm and the genetic algorithm (GA) and the case where the SCMA-based HCN is unoptimized. Results: The Pareto-optimal front generated showed a simultaneous maximization of the SE and EE of the SCMA-based HCN at high traffic levels and a convex front that allows network operators to select the SE-EE tradeoff at low traffic levels flexibly. The proposed PSO algorithm offers a higher SBS density, and a higher SBS transmit power at high traffic levels than at low traffic levels. The unoptimized SCMA-based HCN achieves an 80% lower SE and a 51% lower EE than the proposed PSO optimized SCMA-based HCN. The optimum SE and EE achieved by the SCMA-based HCN using the proposed PSO algorithm or the GA are comparable, but the proposed PSO uses a 51.85% lower SBS density and a 35.96% lower SBS transmit power to achieve the optimal SE and EE at moderate traffic levels. Conclusion:In sleep-mode enabled SCMA-based HCNs, network engineers have to decide the balance of SBS density and SBS transmit power that helps achieve the desired SE and EE.

show abstract

“…In this survey, we are more interested in how deep learning was applied to design SCMA detectors. Very recently, this problem attracted some attention [169]- [174]. The aim is to design a detector by offline training a DNN such that one shot online non-iterative decoding is performed with a relative lowcomplexity.…”

Section: F Deep Learning Based Detectorsmentioning

confidence: 99%

“…The training data is randomly generated with a given corruption level. A similar approach is also studied in [174]. However, the aforementioned detector can not be used with any given codebook.…”

Section: F Deep Learning Based Detectorsmentioning

confidence: 99%

Sparse Code Multiple Access: Potentials and Challenges

Rebhi

Hassan

Raoof

et al. 2021

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

The massive connectivity is among other unprecedented requirements which are expected to be satisfied in order to follow the perpetual increase of connected devices in the era of internet of things. In contrast to the family of conventional orthogonal multiple access schemes, the key distinguishing feature of non-orthogonal multiple access (NOMA) is its capacity to support the massive connectivity. Sparse code multiple access (SCMA) is one of the powerful schemes of code-domain NOMA (CD-NOMA) and is among the promising candidates of multiple access techniques to be employed in future generations of wireless communication systems thanks to the sparsity pattern of its codebooks. This technique has been actively investigated in recent years. In this paper, we provide a comprehensive survey of the state-of-the-art of SCMA. First, we will pinpoint SCMA place in the NOMA landscape including power-domain NOMA and CD-NOMA with the aim of justifying why SCMA is prominent. Then, its system architecture is highlighted and its basic principles are presented, afterwards a review of exiting codebook designs and available SCMA detectors is provided, before showing how resources are expected to be assigned, and how SCMA can be combined with other existing and emerging technologies. Finally, we present a range of future research trends and challenging open issues that should be addressed to optimize SCMA performance.

show abstract

A novel deep neural network based approach for sparse code multiple access

Cited by 30 publications

References 50 publications

Joint Source-Channel Decoding of Polar Codes for HEVC-Based Video Streaming

Joint Source-Channel Decoding of Polar Codes for HEVC-Based Video Streaming

Particle swarm optimization of the spectral and energy efficiency of an SCMA‐based heterogeneous cellular network

Sparse Code Multiple Access: Potentials and Challenges

Contact Info

Product

Resources

About