Cited by Non-orthogonal Multiple Access for Semantic Communications

AI Empowered Wireless Communications: From Bits to Semantics DOI

Zhijin Qin, Le Liang, Zijing Wang

et al.

Proceedings of the IEEE, Journal Year: 2024, Volume and Issue: 112(7), P. 621 - 652

Published: July 1, 2024

Language: Английский

Citations

NOMA-based intelligent resource allocation and trajectory optimization for multi-UAVs assisted semantic communication networks DOI

Ping Xie, Qian Chen,

Jingyan Wu

et al.

Ad Hoc Networks, Journal Year: 2025, Volume and Issue: unknown, P. 103762 - 103762

Published: Feb. 1, 2025

Language: Английский

Citations

Sum Rate Maximization for NOMA-Aided Cell-Free System DOI

Qiling Gao,

Zhongming Feng, Yun Lin

et al.

Published: Jan. 1, 2025

Language: Английский

Citations

Task Scheduling and Power Allocation in Multiuser Multiserver Vehicular Networks by NOMA and Deep Reinforcement Learning DOI

Yuliang Cong,

Maiou Liu,

Cong Wang

et al.

IEEE Internet of Things Journal, Journal Year: 2024, Volume and Issue: 11(13), P. 23532 - 23543

Published: April 10, 2024

In the pursuit of achieving optimal functionality for internet vehicles (IoV), integration multi-access edge computing (MEC) emerges as a solution, offering high bandwidth, low latency, robust security, and reliability services. this article, we consider multi-user multi-server vehicular network scenario, where non-orthogonal multiple access (NOMA) technology in 5G is used to optimize spectrum resource utilization. We firstly formulate problem using mixed integer non-linear programming (MINLP) propose task scheduling scheme based on deep reinforcement learning (DRL) handle high-dimensional state action spaces approximate solution. then proposed solutions NOMA clustering power allocation problems order further reducing system latency uplink transmission stage. Simulation results underscore efficacy our algorithm systems with unevenly distributed resources, showcasing superior performance compared alternative algorithms.

Language: Английский

Citations

Joint Optimization on Mode Switching and Power Adaptation in Semantic-Assisted Hybrid NOMA DOI

Wenqian Tang,

Ronghua Liu,

Qiang Li

et al.

IEEE Open Journal of the Communications Society, Journal Year: 2024, Volume and Issue: 5, P. 4797 - 4807

Published: Jan. 1, 2024

In this paper, a semantic-assisted hybrid non-orthogonal multiple access (NOMA) is investigated, in which secondary far user (F-user) wishes to transmit common point simultaneously with primary near (N-user) the same frequency band. order take advantages of both semantic communication (SemCom) and traditional bit (BitCom), SemCom/BitCom mode switching proposed at F-user, by adapting varying fading states channel. On basis, optimize performance F-user while providing adequate protection N-user, an optimization problem maximizing ergodic rate formulated, subject instantaneous constraint N-user. This non-convex requires joint design on power adaptation over different states. To provide insights, it first proved that formulated satisfies time-sharing condition, indicating there exists dual zero duality gap original problem. A Lagrangian Sub-Gradient Algorithm then solve Simulation results demonstrate NOMA, significant improvement can be achieved for meeting requirement Furthermore, states, scheme outperforms BitCom SemCom.

Language: Английский

Citations

Semantic Communication Meets Edge Intelligence: Semantic-Relay-Aided Text Transmissions DOI

Zeyang Hu,

Changsheng You, Tianyu Liu

et al.

IEEE Internet of Things Journal, Journal Year: 2024, Volume and Issue: 11(24), P. 39409 - 39423

Published: Aug. 16, 2024

Language: Английский

Citations

A Relay System for Semantic Image Transmission Based on Shared Feature Extraction and Hyperprior Entropy Compression DOI

Wannian An, Zhicheng Bao, Haotai Liang

et al.

IEEE Internet of Things Journal, Journal Year: 2024, Volume and Issue: 11(9), P. 16158 - 16170

Published: Jan. 11, 2024

Nowadays, the need for high-quality image reconstruction and restoration is more urgent. However, most transmission systems may suffer from quality degradation or interruption in face of interference such as channel noise link fading. To solve this problem, a relay communication network semantic based on shared feature extraction hyperprior entropy compression (HEC) proposed, where technology Pearson correlation proposed to eliminate partial extracted latent feature. In addition, HEC used resist effect fading carried out respectively at source node node. Experimental results demonstrate that compared with other recent research methods, system has lower overhead higher performance. Particularly, under same conditions, multi-scale structural similarity (MS-SSIM) superior comparison method by approximately 0.2.

Language: Английский

Citations

Flag Vector Assisted Multi-user Semantic Communications for Downlink Text Transmission DOI

Huang Wei, Jun Wang, Xiaonan Chen

et al.

IEEE Communications Letters, Journal Year: 2024, Volume and Issue: 28(6), P. 1283 - 1287

Published: April 16, 2024

Semantic communication has become a promising paradigm tailored for multi-user intelligent communications. Existing semantic methods schemes assume that the receiver sends channel state information (CSI) feedback to transmitter, which is not always realistic. In this work, we design feedback-free scheme called Multi-user Efficient Transmission DeepSC (MET_DeepSC) communication. The idea utilize dedicated flag vectors identification of different users. We embed these on both transmitter and sides, thus CSI no longer needed. also propose fusion mechanism compresses messages all users into single signal. way, users' can be simultaneously sent, transmission workload greatly relieved. Simulation results show MET_DeepSC transmits without additional resources at cost only slight performance degradation outperforms baselines.

Language: Английский

Citations

Multi-User Detection Based on Improved Cheetah Optimization Algorithm DOI

Shuang Chen,

Yuanfa Ji,

Xiyan Sun

et al.

Electronics, Journal Year: 2024, Volume and Issue: 13(10), P. 1842 - 1842

Published: May 9, 2024

Targeting the issues of slow speed and inadequate precision optimal solution calculation for multi-user detection in complex noise environments, this paper proposes a algorithm based on Hybrid Cheetah Optimizer (HCO). The first optimizes control parameters individual update mechanism (CO) using nonlinear strategy to improve uniformity discretization search range, then dynamically introduces differential evolutionary into improved selection CO algorithm, which is utilized fine-tune space maintain local diversity during fast process. Simulation results demonstrate that not only realizes convergence with very low bit error rate (BER) at eight iterations but also has obvious advantages terms immunity, resistance far near effects, communication capacity, etc., greatly improves accuracy position solving can achieve purpose accurate environments.

Language: Английский

Citations

Two‐View Image Semantic Cooperative Nonorthogonal Transmission in Distributed Edge Networks DOI

W. Wang, Donghong Cai, Zhicheng Dong

et al.

International Journal of Intelligent Systems, Journal Year: 2024, Volume and Issue: 2024(1)

Published: Jan. 1, 2024

With the wide application of deep learning (DL) across various fields, joint source–channel coding (DeepJSCC) schemes have emerged as a new approach for image transmission. Compared with traditional separated source and CC (SSCC) schemes, DeepJSCC is more robust to channel environment. To address limited sensing capability individual devices, distributed cooperative transmission implemented among edge devices. However, this significantly increases communication overhead. In addition, existing primarily focus on specific tasks, such classification or data recovery. paper, we explore wireless semantic collaborative nonorthogonal networks, where devices network extract features same target from different viewpoints transmit these an server. A two‐view (two‐view‐DC‐DeepJSCC) without information disentanglement scheme proposed. particular, two‐view‐DC‐DeepJSCC (two‐view‐DC‐DeepJSCC‐D) proposed achieving balancing performance between multitasking communication; while only pursues outstanding recovery performance. Through curriculum (CL), two‐view‐DC‐DeepJSCC‐D effectively captures both common private data. The server uses received accomplish tasks recovery, classification, clustering. experimental results demonstrate that our capable simultaneously performing clustering tasks. has better compared not maintains competitive advantage in but also significant improvement accuracy. will sacrifice some balance multiple Furthermore, exhibits stronger robustness signal‐to‐noise ratios.

Language: Английский

Citations