Article
Engineering, Electrical & Electronic
Farah Mahdi Alsalami, Nurudeen Aigoro, Abdulrahman A. Mahmoud, Zahir Ahmad, Paul Anthony Haigh, Olivier C. L. Haas, Sujan Rajbhandari
Summary: This article develops a statistical large-scale fading (path loss) model for a dynamic vehicular visible light communication system. Different radiation patterns of vehicles' headlights were examined to analyze the statistical path loss of the VVLC system, with the results showing the need for modeling the radiation intensity distribution for accurate VVLC channel model for each manufacturer's headlights. The proposed Gaussian model offers a close approximation and adaptability for modeling headlights from different manufacturers.
JOURNAL OF LIGHTWAVE TECHNOLOGY
(2021)
Article
Engineering, Electrical & Electronic
Guangyao Ding, Jiantao Yuan, Guanding Yu, Yuan Jiang
Summary: This paper proposes a novel resource allocation framework to support ultra-reliable low-latency vehicle-to-vehicle (V2V) communications. The framework includes both large-scale and small-scale resource optimizations, which significantly improve traffic safety and driving experience.
IEEE TRANSACTIONS ON COMMUNICATIONS
(2022)
Article
Chemistry, Analytical
Seoyeon Oh, Yejin Lee, Minseok Yu, Seonghyeon Cho, Sana Javed, Hyunchae Chun
Summary: This study proposes a smart license plate receiver with a fluorescent concentrator, enabling fast vehicle-to-vehicle communication with a large field of view and high optical gain. Experimental results demonstrate high data rates and real-time video streaming using LED-based headlamps and a beam-steering system with image processing.
Article
Computer Science, Information Systems
Laszlo Toka, Mark Konrad, Istvan Pelle, Balazs Sonkoly, Marcell Szabo, Bhavishya Sharma, Shashwat Kumar, Madhuri Annavazzala, Sree Teja Deekshitula, A. Antony Franklin
Summary: With the rise of autonomous driving, coordination among vehicular actors becomes crucial, and communication latency poses a critical factor in information gathering, processing, and redistribution. This work proposes a privacy-preserving system for collecting and sharing data in high-mobility automotive environments, focusing on keeping high definition maps up-to-date in a crowd-sourced manner. By employing federated analytics and optimizations, the system aims to minimize the latency of data distribution using the low latency, high throughput, and broadcast capabilities of 5G edge infrastructure.
Article
Computer Science, Information Systems
Agon Memedi, Falko Dressler
Summary: In this paper, interference in vehicular scenarios is extensively studied, and a novel location-aware cross-layer approach is proposed to handle medium access. The approach exploits the space-division features of modern matrix lighting modules to avoid interference and collisions, and schedules V-VLC transmissions based on shared vehicle positions through the RF channel.
COMPUTER COMMUNICATIONS
(2023)
Article
Computer Science, Information Systems
Tahir H. Ahmed, Jun Jiat Tiang, Azwan Mahmud, Chung Gwo Chin, Dinh-Thuan Do
Summary: In this paper, a novel switched beam antenna system model integrated with deep reinforcement learning (DRL) for 6G vehicle-to-vehicle (V2V) communications is proposed. The proposed approach addresses the challenges of highly dynamic V2V environments and enhances the performance of 6G V2V communications through beam-switching capabilities and intelligent decision making. Extensive simulations and performance analysis demonstrate that the proposed system model outperforms conventional V2V communication systems and other state-of-the-art techniques.
Article
Computer Science, Information Systems
Jianhang Liu, Haonan Weng, Yuming Ge, Shibao Li, Xuerong Cui
Summary: This article proposes a self-healing routing strategy with ant colony optimization algorithm for real-time and robust multihop forwarding paths in vehicular ad hoc networks (VANETs). The strategy aims to adapt to the new development trend of VANETs by introducing the ACO algorithm and defining a metric to measure the forwarding capability of vehicles. In addition, in-road-repairing and intersection-repairing methods are proposed to reduce overhead of path reconstruction.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Environmental Sciences
Eduard Zadobrischi, Mihai Dimian
Summary: This paper proposes the analysis and management of dangerous situations by developing systems and modules, including identifying problems and addressing them to reduce accidents and loss of life. It also discusses the classification of situations that can cause accidents, including detecting psychosomatic elements, and emphasizes the system's versatility and adaptability to context. Communication with other traffic safety systems such as V2V, V2I, V2X, and VLC is highlighted as a key feature of the proposed system.
Article
Chemistry, Analytical
Emmanuel Plascencia, Hongyu Guan, Luc Chassagne, Olivier Barrois, Oyunchimeg Shagdar, Alin-Mihai Cailean
Summary: This article investigates the disruptive effects of mutual interference caused by neighboring vehicle-to-vehicle (V2V) VLC links, emphasizing the importance of considering these effects in vehicular VLC applications.
Article
Computer Science, Information Systems
Yasir Saleem, Nathalie Mitton, Valeria Loscri
Summary: DIVINE is a vehicular network data offloading scheme that emphasizes QoS provisioning and factors such as connection time, capacity, and speed between vehicles and RSUs.
Article
Chemistry, Analytical
Ahmad Alkhodair, Saraju P. Mohanty, Elias Kougianos
Summary: Due to the immense amount of data generated by users, Intelligent Transportation Systems (ITS) require a reliable and secure infrastructure. The Internet of Vehicles (IoV) refers to the interconnection of all Internet-enabled nodes, devices, sensors, and actuators, whether attached to vehicles or not. This paper explores Distributed Ledger Technology (DLT) and consensus algorithms, aiming to determine their suitability for use in the IoV. The proposed FlexiChain 3.0 serves as a Layer0 network for stakeholders in the IoV, providing a transaction capacity of 2.3 transactions per second and ensuring high security and independence of node numbers.
Article
Engineering, Electrical & Electronic
Mi Yang, Bo Ai, Ruisi He, Zhangfeng Ma, Hang Mi, Dan Fei, Zhangdui Zhong, Yujian Li, Jing Li
Summary: In this article, channel measurements at 5.9 GHz in street intersection scenarios are conducted to provide data for the characterization and modeling of time-varying vehicular channels. A double-slope path loss model is proposed to accurately reflect the signal propagation loss at intersections. Furthermore, the time-varying spatial characteristics of multipath are extracted and analyzed, and the azimuth and elevation spread of arrival are statistically characterized. The research in this article can enrich the investigation of vehicular channels and enable the analysis and design of vehicular communication systems.
IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION
(2023)
Article
Computer Science, Information Systems
Selma Yahia, Yassine Meraihi, Amar Ramdane-Cherif, Asma Benmessaoud Gabis, Hossein B. Eldeeb
Summary: This paper fills the research gap regarding the impact of lateral shift between vehicles and transceiver parameters on the performance of V2V-VLC systems. It also introduces the use of angle-oriented receiver to enhance system performance.
COMPUTER COMMUNICATIONS
(2022)
Article
Computer Science, Information Systems
Ikjot Saini, Sherif Saad, Arunita Jaekel
Summary: In an Intelligent Transportation System, real-time information from vehicles is required for many applications. This paper proposes a comprehensive pseudonym changing scheme that leverages vehicle context and current traffic patterns to determine the optimal situation for changing pseudonyms, improving both user-centric and adversary-centric performance metrics.
INTERNET OF THINGS
(2022)
Article
Engineering, Electrical & Electronic
Mohamed K. Abdel-Aziz, Cristina Perfecto, Sumudu Samarakoon, Mehdi Bennis, Walid Saad
Summary: This paper proposes a novel framework for cooperative perception among vehicles using reinforcement learning and point cloud compression mechanism. Simulation results demonstrate the effectiveness of reinforcement learning in learning vehicle association, resource allocation, and information selection, while federated learning improves the training process.
IEEE TRANSACTIONS ON COMMUNICATIONS
(2022)
Article
Engineering, Electrical & Electronic
Long Zhao, Ping Zhang, Kan Zheng, Hanzo Lajos
Summary: This paper focuses on optimizing power allocation at a base station transmitting information to vehicles in a vehicular network in order to minimize the Power to Velocity Ratio (PVR). Different algorithms are designed for optimizing individual vehicle PVR and system PVR, leading to successful achievement of optimal PVR for both individual vehicles and the system as a whole.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2022)
Article
Engineering, Civil
Jie Mei, Xianbin Wang, Kan Zheng
Summary: The paper proposes a semi-decentralized network slicing framework based on LTE infrastructure, utilizing a model-free deep reinforcement learning algorithm at the eNB for slicing control to meet the requirements of different V2V services.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Electrical & Electronic
Lei Lei, Tong Liu, Kan Zheng, Lajos Hanzo
Summary: This study investigates the impact of Vehicle-to-Everything (V2X) communications on platoon control performance. Deep Reinforcement Learning (DRL) is used to solve the sequential stochastic decision problem (SSDP) of platoon control, considering both control constraints and uncertainty. The value of including exogenous information in the system state for reducing uncertainty is studied, while also considering the curse-of-dimensionality. Different information topologies are conceived and compared to find the most appropriate state space for platoon control. The conditional KL divergence of transition models is used to quantify the value of each piece of information, determining its priority in transmission.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2022)
Article
Engineering, Electrical & Electronic
Pengzun Gao, Long Zhao, Kan Zheng, Pingzhi Fan
Summary: This paper proposes two iterative power allocation algorithms to minimize the maximum communication delay among vehicles by considering the estimation accuracy of vehicles' PSI and the transmit power constraint of RSU. Simulation results demonstrate that the proposed algorithms reduce the transmit delay significantly compared to other schemes.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2022)
Article
Computer Science, Information Systems
Chong Yu, Shuaiqi Shen, Haojun Yang, Kuan Zhang, Hai Zhao
Summary: The proposed routing path selection method in IoBT based on nonuniform node distributions and location-related data generation probabilities aims to minimize energy consumption and latency, while maximizing network robustness simultaneously.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Information Systems
Zhiming Liu, Lu Hou, Kan Zheng, Qihao Zhou, Shiwen Mao
Summary: This article introduces RAFT+, a new leader selection scheme based on the distributed consensus algorithm RAFT, which uses a deep Q-Network to optimize leader selection and improve system performance by reducing disparities between different types of IoT end devices while maintaining system security.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Information Systems
Kan Zheng, Haojun Yang, Shiwen Liu, Kuan Zhang, Lei Lei
Summary: Autonomous driving vehicles can improve traffic conditions by reducing congestion, enhancing safety, and increasing traffic efficiency. This article focuses on a reinforcement-learning based method for intelligent behavior decision-making in autonomous vehicles. The proposed method optimizes driving quality by using a comprehensive reward function and leveraging knowledge of surrounding vehicles to predict behavior. Simulation results demonstrate a significant reduction in collision rate using this approach.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Computer Science, Information Systems
Qihao Zhou, Kan Zheng, Kuan Zhang, Lu Hou, Xianbin Wang
Summary: This article investigates the taxonomy of security issues associated with smart contracts in the context of Blockchain-based Internet of Things (BIoT) applications. It proposes a tree-based machine learning vulnerability detection method to overcome the limitations of existing methods. The experimental evaluation demonstrates the effectiveness and efficiency of the proposed method.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Computer Science, Information Systems
Tong Liu, Lei Lei, Kan Zheng, Kuan Zhang
Summary: Autonomous vehicles in a platoon learn efficient car-following policies by utilizing deep reinforcement learning and dynamic programming techniques. The proposed algorithm, FH-DDPG-SS, overcomes the limitations of lower sampling and training efficiency through three key ideas. Simulation using real driving data demonstrates the effectiveness of FH-DDPG-SS, with comparisons against benchmark algorithms and demonstrations of platoon safety and string stability.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Kan Zheng, Haojun Yang, Ziqiang Ying, Pengshuo Wang, Lajos Hanzo
Summary: This article presents a vision-assisted mm-wave beam management system that employs machine learning algorithms applied to visual data to select the optimal beam for target user equipment. Simulation results demonstrate the attractiveness of this system for next-generation wireless systems.
IEEE VEHICULAR TECHNOLOGY MAGAZINE
(2023)
Article
Computer Science, Information Systems
Zhiming Liu, Kan Zheng, Lu Hou, Haojun Yang, Kan Yang
Summary: This article proposes a blockchain-assisted aggregation scheme for federated learning in IoT networks to address the challenges of efficiency and reliability. By using an improved hierarchical aggregation framework and the deep deterministic policy gradient algorithm, the optimal subset of devices is selected, and blockchain is utilized for performance verification.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Jiaju Qi, Lei Lei, Kan Zheng, Simon X. Yang, Xuemin Shen
Summary: In this article, the scheduling issue of diesel generators (DGs) in an Internet of Things (IoT)-Driven isolated microgrid (MG) is investigated using deep reinforcement learning (DRL). A novel finite-horizon partial observable Markov decision process (POMDP) model is conceived to handle the challenge of discrete-continuous hybrid action space. The proposed DRL algorithm, HAFH-RDPG, seamlessly integrates two classical DRL algorithms and is evaluated using real-world data in an IoT-driven MG.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Geochemistry & Geophysics
Lingyi Han, Lu Hou, Xiangxiang Zheng, Ziyue Ding, Haojun Yang, Kan Zheng
Summary: This article proposes a segmentation-with-reconstruction framework that consists of a SegModel for generating binary road labels and a reconstruction model for refining the labels. By introducing the AV-DAE model and three noise-adding strategies, it improves road connectivity and boundary smoothness. Experimental results demonstrate that the framework achieves competitive road extraction performance and high generalization ability.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
