Article
Engineering, Electrical & Electronic
Helin Yang, Zehui Xiong, Jun Zhao, Dusit Niyato, Liang Xiao, Qingqing Wu
Summary: This paper investigates an intelligent reflecting surface (IRS)-aided wireless secure communication system, utilizing deep reinforcement learning to optimize beamforming strategies for enhancing system secrecy rate and QoS satisfaction probability. Post-decision state (PDS) and prioritized experience replay (PER) schemes are applied to improve learning efficiency and secrecy performance against multiple eavesdroppers in dynamic environments.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2021)
Article
Engineering, Electrical & Electronic
Danya A. Saifaldeen, Bekir S. Ciftler, Mohamed M. Abdallah, Khalid A. Qaraqe
Summary: This paper develops a novel Physical Layer Security (PLS) technique for a Visible Light Communication (VLC) system using Intelligent Reflecting Surfaces (IRS). The proposed solution utilizes Deep Reinforcement Learning (DRL) based on the Deep Deterministic Policy Gradient (DDPG) algorithm to optimize the Secrecy Capacity (SC). Results demonstrate the importance of considering both mirror array sheet and beamforming vectors for maximizing SC.
IEEE PHOTONICS JOURNAL
(2022)
Article
Telecommunications
Baogang Li, Kangjia Cui
Summary: In this paper, an intelligent reflecting surface (IRS)-assisted proactive eavesdropping system is studied, where the reflecting ability of IRS is fully exploited to improve the long-term eavesdropping performance. A double deep Q-Learning network (DDQN)-based algorithm is proposed to achieve the optimal reflecting beamforming policy. Simulation results demonstrate that the proposed approach significantly improves the eavesdropping performance compared to traditional algorithms with the assistance of IRS.
IEEE COMMUNICATIONS LETTERS
(2022)
Article
Computer Science, Theory & Methods
Cenk Albayrak, Sinasi Cetinkaya, Kadir Turk, Huseyin Arslan
Summary: Visible light communication (VLC) is a promising technology for indoor wireless broadband communication systems. This study investigates the effects of inter-symbol interference (ISI) on the secrecy rate in VLC systems and proposes solutions to compensate for the ISI effects. The results show that ISI significantly degrades the secrecy rate, but well-designed beamformers can overcome this issue.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2023)
Article
Telecommunications
Zhao Li, Pintian Lyu, Jun Li, Zhixian Chang, Jia Liu, Zheng Yan
Summary: Due to the broadcast nature of wireless communications, the security and privacy of users' wireless data transmission are at risk. Additionally, interference caused by limited spectrum resources can greatly decrease the efficiency of data transmission. Therefore, it is important to improve both the efficiency and secrecy of data transmission. This paper introduces a wireless transmission scheme called SCIM, which takes into account both Secure Communication (SC) and Interference Management (IM). By generating an SCIM signal and transmitting it alongside the desired signal, SCIM can suppress environmental interference and deteriorate eavesdropping performance, ultimately enhancing both transmission efficiency and privacy. Various implementations of SCIM are developed based on different transmission preferences, and simulation results show that the proposed methods effectively improve the efficiency and secrecy of legitimate transmission.
DIGITAL COMMUNICATIONS AND NETWORKS
(2023)
Article
Engineering, Electrical & Electronic
Shuai Ma, Jing Wang, Chun Du, Hang Li, Xiaodong Liu, Youlong Wu, Naofal Al-Dhahir, Shiyin Li
Summary: This paper proposes joint beamforming and photo-detector (PD) orientation (BO) optimization schemes for mobile visible light communication (VLC) with the orientation adjustable receiver (OAR). Two cases of UE orientation, fixed and random, are considered for BO optimization with minimal UE power consumption to ensure the quality of service (QoS) of mobile VLC. An alternating optimization algorithm is proposed for the fixed UE orientation case, while a robust alternating BO optimization algorithm is proposed for the random UE orientation case. Numerical experiments are conducted to evaluate the performance of the proposed BO optimization design schemes for mobile VLC.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2023)
Article
Engineering, Electrical & Electronic
Shuai Han, Jinming Wang, Liang Xiao, Cheng Li
Summary: This paper proposes a UAV-empowered IRS-BackCom network that addresses the issues of double-fading effect and eavesdropping, while ensuring secure transmission and maximizing the broadcast secrecy rate.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2023)
Article
Computer Science, Information Systems
Jiawei Wang, Peng Zhang, Lan Tang, Yechao Bai, Lvxi Yang
Summary: This letter investigates passive eavesdropping scheme in massive MIMO-OFDM systems by utilizing mobility of the monitor, aiming to maximize the eavesdropping rate by optimizing receiving beamformers and moving trajectory. The proposed solution based on concatenated deep Q-network (DQN) is validated to be effective through simulation results.
IEEE WIRELESS COMMUNICATIONS LETTERS
(2022)
Article
Engineering, Electrical & Electronic
Zitian Zhang, Jinbo Hou, Xiaoli Chu, Haibo Zhou, Guiyi Wei, Jie Zhang
Summary: In this paper, a beamforming framework is proposed that utilizes multi-agent deep reinforcement learning (DRL) to maximize the system downlink sum-rate in a heterogeneous network (HetNet). Each access point (AP) acts as an agent and generates a beamforming vector based on local observations, which is then evaluated for its appropriateness. The proposed framework converges fast and outperforms benchmark beamforming methods in terms of the system downlink sum-rate performance.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2023)
Article
Engineering, Electrical & Electronic
Man Chu, An Liu, Vincent K. N. Lau, Chen Jiang, Tingting Yang
Summary: This paper proposes reinforcement learning based end-to-end channel prediction and beamforming algorithms for multi-user downlink systems, achieving autonomous learning and performance optimization without perfect channel state information. Empirical simulations and complexity analysis verify the effectiveness and superiority of the algorithms.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2022)
Article
Computer Science, Information Systems
Runze Dong, Buhong Wang, Kunrui Cao
Summary: This study introduces a 3D beamforming method based on deep learning for physical layer security design in UAV communication systems. Simulation experiments demonstrate that this method can achieve better secrecy rate and flexible beam steering compared to benchmarks.
IEEE WIRELESS COMMUNICATIONS LETTERS
(2021)
Article
Engineering, Electrical & Electronic
Ambrish Kumar, Dushantha Nalin K. Jayakody
Summary: In this paper, two LED selection schemes are proposed to improve the security performance in underwater visible light communication. The closed-form expressions for secrecy outage probability are derived using successive interference cancellation. The validity of the numerical results is verified through experiments.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2022)
Article
Optics
Yi Huang, Dahai Han, Min Zhang, Yanwen Zhu, Liqiang Wang
Summary: This study proposes a novel direct time-domain waveform equalization approach using a bidirectional gated recurrent unit (BiGRU) neural network for indoor visible light communication with direct current-biased orthogonal frequency division multiplexing (DCO-OFDM). Experimental results demonstrate that the BiGRU-based approach exhibits low complexity and exceptional nonlinear channel learning capabilities, outperforming other strategies in terms of bit error rate without the need for pilot signals.
Article
Engineering, Chemical
Bin Wang, Zhengkun He, Jinfang Sheng, Yu Chen
Summary: This paper proposes a traffic light timing optimization method called EP-D3QN based on double dueling deep Q-network, MaxPressure, and Self-organizing traffic lights (SOTL). The method controls traffic flows by dynamically adjusting the duration of traffic lights in a cycle, leading to significant reductions in waiting and travel times for vehicles, and improving the efficiency of intersections.
Article
Engineering, Electrical & Electronic
Jiale Chen, Lan Tang, Delin Guo, Yechao Bai, Lvxi Yang, Ying-Chang Liang
Summary: In this paper, a scheme for monitoring suspicious links in massive MIMO-OFDM systems is proposed. The scheme uses proactive eavesdropping and implements beam misleading and data eavesdropping algorithms. The optimal precoders and power split factors are found using the MADDPG algorithm. Simulation results demonstrate the effectiveness and superiority of the proposed eavesdropping scheme.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2022)
Article
Computer Science, Information Systems
Yang Liu, Leiqing Ni, Mugen Peng
Summary: This study proposes an access authentication protocol with user anonymity and traceability in order to reduce communication delay and signaling cost in satellite-terrestrial networks, improving the user's network experience. Additionally, a hierarchical group key distribution scheme is proposed to enable cross-domain handover authentication between different user groups, effectively avoiding the need for reauthentication.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Kun Cheng, Fengxian Guo, Mugen Peng
Summary: Distributed machine learning (DML) is a promising computing paradigm for enabling edge intelligence in wireless networks. This paper studies the convergence and system implementation of DML over a wireless device-to-device (D2D) network. By introducing the DML training process and system model, and analyzing the convergence rate and delay, the paper proposes a system implementation approach to reduce the convergence rate and delay. Experimental results show that the proposed D2D framework effectively reduces training delay and improves computation efficiency.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2023)
Article
Telecommunications
Nan Li, Qi Sun, Xiang Li, Fengxian Guo, Yuhong Huang, Ziqi Chen, Yiwei Yan, Mugen Peng
Summary: In order to accommodate the diversified use cases in 5G, the radio access networks (RAN) need to be more flexible, open, and versatile. By embedding computing capabilities within RAN, it transforms into a cost-effective radio edge computing platform, enhancing RAN agility for various services and improving users' quality of experience (QoE).
CHINA COMMUNICATIONS
(2023)
Article
Engineering, Electrical & Electronic
Tian Dang, Chenxi Liu, Mugen Peng
Summary: In this paper, we propose an approach utilizing UAV-enabled wireless networks to achieve low-latency mobile virtual reality content delivery. We formulate an average latency minimization problem considering the limited energy storage at UAVs, and solve it by transforming it into a weighted-latency-plus-energy minimization problem. We propose an iterative algorithm to solve the transformed problem by decomposing it into three subproblems.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2023)
Article
Engineering, Electrical & Electronic
Binghong Liu, Chenxi Liu, Mugen Peng
Summary: This paper proposes a novel cloud-edge framework to facilitate mobile edge computing (MEC) in UAV networks. The edge UAVs, together with the cloud, provide caching and computing services for terrestrial users. The proposed algorithm of sequential convex programming (SCP) and sequential quadratic programming (SQP) based deep Q-learning (SS-DQN) improves system performance significantly compared to two benchmark schemes.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2023)
Article
Engineering, Electrical & Electronic
Xiaolei Qi, Mugen Peng, Hongming Zhang
Summary: This paper proposes a method that combines computation offloading and mmWave massive MIMO-NOMA communication to achieve energy-efficient performance for IoT devices in MEC network. It introduces an IoT device clustering algorithm to schedule devices into limited beams, and then optimizes the energy consumption by joint optimization of hybrid beamforming, offloading task assignment ratio, and power allocation. Simulation results validate the convergence of the proposed algorithms and the superiority of the proposed schemes leveraging the massive MIMO-NOMA technique during computational offloading.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2023)
Article
Engineering, Electrical & Electronic
Xiaoling Hu, Chenxi Liu, Mugen Peng, Caijun Zhong
Summary: In this paper, an integrated sensing and communication (ISAC) system based on distributed semi-passive intelligent reflecting surface (IRS) is proposed, which enables simultaneous location sensing and data transmission on the same time-frequency resources. The working process, including transmission protocol, location sensing, and beamforming optimization, is designed. Simulation results demonstrate that the proposed system can achieve millimeter-level positioning accuracy and the beamforming schemes based on sensed location information perform similarly to the benchmark schemes assuming perfect channel state information.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2023)
Article
Engineering, Electrical & Electronic
Xian Zhang, Mugen Peng, Chenxi Liu
Summary: The performance of UAV-enabled networks is limited by inter-cell interference and backhaul connectivity. In this study, we analyze the performance of UAV-enabled heterogeneous networks using antenna downtilt and tethered UAV-mounted BS to mitigate interference and provide backhaul connectivity. The user association probability and distance distributions are derived, along with the coverage probability and ergodic rate of the networks. The results validate the effectiveness of antenna downtilt and TUAV-enabled backhaul connectivity, and demonstrate the impact of deployment altitude and network area size on performance.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2023)
Article
Geography, Physical
Wenjia Xu, Jiuniu Wang, Zhiwei Wei, Mugen Peng, Yirong Wu
Summary: Deep neural networks have achieved promising progress in remote sensing image classification, but the annotation process for each remote sensing category is time-consuming and unrealistic. We propose to collect visually detectable attributes automatically and use the self-attention mechanism to integrate background context information for prediction, improving the performance of zero-shot learning classification.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2023)
Article
Engineering, Electrical & Electronic
Hongxia Miao, Feng Zhang, Ran Tao, Mugen Peng
Summary: This study combines Ramanujan and Fourier transform with affine Fourier transform to provide affine multiresolution analysis tools for nonstationary signals. The proposed techniques, including affine Ramanujan sums and affine Ramanujan Fourier transform (ARFT), are capable of estimating chirp periods accurately and improve performance in radar moving target detection and velocity estimation compared to affine Fourier transform based algorithms.
Article
Telecommunications
Xueyan Cao, Xiaoling Hu, Mugen Peng
Summary: In this paper, an intelligent reflecting surface (IRS) aided maritime cooperative communication system is studied, where multiple relay ships with both active relay and passive IRS assist the downlink transmission from the base station (BS) to the destination ship. The joint optimization problem of mode selection, power control, and beamforming is formulated and solved to minimize the total transmit power, subject to the quality of service constraint. Two algorithms based on exhaustive searching and many-to-one matching are proposed for the mode selection and power control sub-problem, while a semidefinite programming-based algorithm is proposed for the beamforming sub-problem. The numerical results confirm the good performance of the proposed algorithms and the power saving advantage of the proposed IRS-aided system.
IEEE TRANSACTIONS ON GREEN COMMUNICATIONS AND NETWORKING
(2023)
Article
Engineering, Electrical & Electronic
Zhifeng Wang, Xiqing Liu, Yiran Yang, Mugen Peng
Summary: A complementary coded identical code cyclic shift multiple access (CC-ICCSMA) system is proposed in this article, which allows multiple data streams to transmit in parallel by sharing one spreading code. It can achieve higher bandwidth efficiency compared to traditional CC-CDMA and outperform traditional DS-CDMA schemes in terms of bit-error rates and transmission rates.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2023)
Article
Engineering, Electrical & Electronic
Hongxia Miao, Mugen Peng
Summary: This study proposes a novel orthogonal time chirp space (OTCS) modulation method based on fractional Fourier transform (FrFT) by replacing the two-dimensional sinusoidal carriers with two-dimensional linear chirps in orthogonal time frequency space (OTFS) modulation. The OTCS-FrFT method adapts to different time-varying Doppler scenarios by placing information symbols on the delay-fractional Doppler plane with a rotation parameter. The robustness of OTCS-FrFT is proven for time-varying channels with linear delay/Doppler spreading functions, and simulations demonstrate its superior performance over other FrFT-based OTFS modulation methods, reducing the bit error rate by approximately 1 dB for high-speed and high-acceleration terminals.
Article
Computer Science, Information Systems
Fengxian Guo, Mugen Peng
Summary: Mobile edge computing is an essential technology for latency-critical applications by providing computing services in close proximity to mobile users. However, supporting user mobility remains challenging. This article proposes an efficient mobility management framework that is centered around users' performance and cost, and uses game theory and user-oriented deep reinforcement learning to handle the interactions in space and time.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Bin Cao, Zixin Wang, Long Zhang, Daquan Feng, Mugen Peng, Lei Zhang, Zhu Han
Summary: Blockchain has shown a promising vision in the past decade to build trust in a secure, decentralized, and scalable manner. However, its wide application and complex nature require a methodological perspective to fully understand the blockchain process. This article introduces the working principle of blockchain, research activities, and challenges, as well as the adoption of stochastic process, game theory, optimization theory, and machine learning in blockchain systems. The advantages and limitations of these methods are discussed, and the remaining technical, commercial, and political problems are also addressed. The findings provide valuable insights for studying blockchain fundamentals, designing blockchain-based mechanisms and algorithms, and applying blockchain to the Internet of Things.
IEEE COMMUNICATIONS SURVEYS AND TUTORIALS
(2023)