Article
Computer Science, Information Systems
Maedeh Nasr-Azadani, Jamshid Abouei, Konstantinos N. Plataniotis
Summary: This article examines a wireless network composed of unmanned aerial vehicles (UAVs) as aerial base stations and numerous terrestrial users in a dense urban area. The primary objective is to maximize user downlink rate by clustering users and strategically deploying UAVs. The study employs deep echo-state network (ESN) to accurately estimate user movement patterns, and proposes single- and multiagent actor-critic (AC) algorithms for UAV deployment and trajectory design. Simulation results demonstrate superior accuracy and performance compared to value-based algorithms.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Engineering, Civil
Yanming Fu, Xiaoqiong Qin, Xian Zhang, Youquan Jia
Summary: This paper presents a hybrid recruitment scheme called HR-DLVCS based on deep learning for recruiting suitable vehicles to maximize the completion rate of sensing tasks in vehicular crowdsensing.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Information Systems
Yang Wu, Xinrong Guan, Weiwei Yang, Qingqing Wu
Summary: In the problem of maximizing the sum rate of the cluster head UAV, algorithms based on block coordinate descent and successive convex approximation outperform the benchmark algorithm, and fixed-wing UAVs are more favorable in anti-jamming UAV swarm communications.
IEEE WIRELESS COMMUNICATIONS LETTERS
(2021)
Article
Automation & Control Systems
Vasileios Tzoumas, Luca Carlone, George J. Pappas, Ali Jadbabaie
Summary: The study focuses on the joint design of sensing and control policies, tackling two dual problem instances: sensing-constrained LQG control and minimum-sensing LQG control. While no polynomial time algorithm guarantees a constant approximation factor from the optimal across all problem instances, the authors present the first polynomial time algorithms with per-instance suboptimality guarantees. The research frames LQG codesign as the optimization of approximately supermodular set functions, developing novel algorithms and establishing connections between suboptimality and control-theoretic quantities.
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
(2021)
Article
Engineering, Electrical & Electronic
Xiao Liu, Yuanwei Liu, Yue Chen, H. Vincent Poor
Summary: A novel framework is proposed for the deployment and passive beamforming design of a reconfigurable intelligent surface (RIS) with the aid of non-orthogonal multiple access (NOMA) technology. Machine learning approaches are utilized to tackle the joint problem of deployment and design of RIS, with promising simulation results.
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2021)
Article
Engineering, Electrical & Electronic
Ryo Hayakawa
Summary: This paper proposes a method to predict the asymptotic performance of the ADMM algorithm in compressed sensing by analyzing the convex subproblem in the ADMM iteration and predicting the evolution of the error in large-scale compressed sensing problems based on asymptotic results.
IEEE TRANSACTIONS ON SIGNAL PROCESSING
(2022)
Article
Automation & Control Systems
Arunava Banerjee, Abdelaziz Salah Saidi, Abdullah A. Algethami, Mashuq Un Nabi
Summary: This paper proposes an automatic time-energy efficient robust control deployment approach that selects either a near-optimal closed-loop control law or a robust control law based on the system requirement. The approach utilizes a population-based sine-cosine algorithm for the near-optimal control law and an artificial time delayed control approach for the robust control law. The ATERC methodology deploys the robust guidance law in the presence of external disturbances and the near-optimal guidance law in the absence of uncertainties, while also considering input saturation.
JOURNAL OF DYNAMIC SYSTEMS MEASUREMENT AND CONTROL-TRANSACTIONS OF THE ASME
(2022)
Article
Computer Science, Information Systems
Hosung Baek, Haneul Ko, Joonwoo Kim, Youbin Jeon, Sangheon Pack
Summary: This article focuses on improving the overall sensing quality in multidimensional vehicular urban sensing by formulating an optimization problem and presenting a low-complexity heuristic algorithm.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Aishwarya Gupta, Aditya Trivedi, Binod Prasad
Summary: This paper presents a deployment and trajectory scheme for fixed-wing unmanned aerial vehicles (UAVs) used as flying base stations in multi-UAV enabled non-orthogonal multiple access (NOMA) downlink communication. The deployment of UAVs and power allocation of users are jointly optimized to maximize the overall data rate. The trajectory of UAVs is then optimized by considering the quality of service (QoS) requirements, flight constraints, on-board energy limitations, and users' mobility. Simulation results demonstrate the superior performance of the proposed algorithm compared to benchmark methods.
PHYSICAL COMMUNICATION
(2022)
Article
Engineering, Electrical & Electronic
Pulak Sarangi, Piya Pal
Summary: This letter investigates the problem of recovering a binary-valued signal from compressed measurements of its convolution with a known finite impulse response filter. By adopting an algorithm-measurement co-design strategy and using sequential decoding algorithm, binary signals with arbitrary sparsity can be recovered in extreme compression regimes.
IEEE SIGNAL PROCESSING LETTERS
(2022)
Article
Engineering, Aerospace
Pathawee Kunakorn-ong, Zahra Soltani, Matthew Santer
Summary: A design methodology is proposed for deployable tube flexures made of ultra-thin carbon fiber composite, and the cut-out shape is determined using Bayesian optimization technique. The efficiency of the approach is validated through experimentation.
Article
Engineering, Civil
Yiming Li, Xiaopeng Yuan, Yulin Hu, Junan Yang, Anke Schmeink
Summary: In this paper, a global optimal trajectory design scheme is proposed for a UAV-aided ISAC network with moving ground users. The performance is reduced to a location-determined function by projecting the trajectory onto a user-relative coordinate frame, and the optimization problem is reformulated as the shape determination problem of a density-varying catenary in the APF. The proposed analytic scheme offers a low complexity and a flexible design practice.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Information Systems
Yang Wu, Weiwei Yang, Xinrong Guan, Qingqing Wu
Summary: This research focuses on a UAV-enabled communication system to maximize energy efficiency by optimizing UAV trajectory in the presence of multiple jammers. An iterative algorithm based on SCA technique and Dinkelbach's algorithm is proposed to address the non-convex and fractional form of the objective function. Numerical results demonstrate the algorithm's effectiveness in improving EE by striking a better balance between throughput and energy consumption compared to benchmark algorithms.
IEEE WIRELESS COMMUNICATIONS LETTERS
(2021)
Article
Automation & Control Systems
Kang Wang, Jinghua Xu, Shuyou Zhang, Jianrong Tan
Summary: An antivibration and energy efficiency design method for large stroke additive manufacturing based on dynamic trajectory adaption (DTA) is proposed, which optimizes crucial metrics such as mean trajectory deviation and total energy consumption. The DTA method demonstrates a significant improvement in antivibration and energy efficiency, highlighting its potential for optimizing complex product design in large stroke AM.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2022)
Article
Engineering, Civil
Ying Zhang, Yanhao Wang, Fanyu Li, Bin Wu, Yao-Yi Chiang, Xin Zhang
Summary: This paper proposes a multicriteria-oriented approach for deploying charging infrastructure efficiently and designs acceleration algorithms based on submodularity. Experimental evaluation shows that the proposed approach is more effective and efficient compared to state-of-the-art methods.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2021)
Article
Computer Science, Information Systems
Jingyu Cong, Xianpeng Wang, Chenggang Yan, Laurence T. Yang, Mianxiong Dong, Kaoru Ota
Summary: With the development of the Internet of Things (IoT), the use of multi-unmanned aerial vehicle (UAV) networks for source detection and localization has gained attention. However, the real-time signal processing of UAVs is limited by computing speed and embedded hardware accuracy, reducing the effectiveness of source localization. This study proposes a Cramer-Rao bound (CRB) weighted multi-UAV network source localization method, using deep neural networks (DNNs) and spatial-spectrum fitting (SSF) to improve accuracy and computational efficiency. The proposed method utilizes UAVs equipped with radar arrays and a deep SSF (DeepSSF) algorithm to achieve accurate DOA estimation.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Theory & Methods
Rong Han, Zheng Yan, Xueqin Liang, Laurence T. Yang
Summary: In a blockchain-based system, designing a feasible incentive mechanism becomes essential to improve system performance by regulating entity behaviors. This study proposes evaluation requirements and taxonomies for incentive mechanisms in blockchain systems. Through a thorough review, the study discusses the advantages and disadvantages of existing incentive mechanisms and identifies unresolved issues and potential directions for future research on the relationship between incentive mechanisms and blockchain.
ACM COMPUTING SURVEYS
(2023)
Article
Automation & Control Systems
Yuan Gao, Laurence T. Yang, Jing Yang, Dehua Zheng, Yaliang Zhao
Summary: In this article, a jointly low-rank tensor completion method is proposed for logistics data completion, which constructs multiple periodic subtensors by setting an appropriate time window and performs jointly low-rank completion and imputation. Experimental results demonstrate the promising performance of the proposed method compared with other state-of-the-art competitors in logistics systems.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Automation & Control Systems
Jing Yang, Laurence Tianruo Yang, Hao Wang, Yuan Gao
Summary: Augmented Intelligence of Things, empowered by knowledge graph, drives cognitive intelligence in smart enterprise management systems. The proposed MR-GAT approach effectively improves the accuracy of knowledge fusion by utilizing tensor-based graph attention networks for multirelational graph representation learning.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Automation & Control Systems
Yaguang Lin, Xiaoming Wang, Hongguang Ma, Liang Wang, Fei Hao, Zhipeng Cai
Summary: This article proposes a decentralized knowledge sharing platform for the industrial Internet of Things (IIoT), including public knowledge sharing and private knowledge sharing. For public knowledge, a dynamics model is established to quantitatively describe the sharing process, and an optimal control method is presented. For private knowledge, a trusted transaction control method based on blockchain technology is proposed to protect knowledge integrity and privacy.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Automation & Control Systems
Zhangwei Yu, Yan Liu, Guoqi Xie, Renfa Li, Siming Liu, Laurence T. Yang
Summary: Intelligent connected vehicles are experiencing rapid growth, but this also increases the vulnerability of automotive CAN networks to cyberattacks. Existing intrusion detection technologies for automotive CAN networks are often ineffective against sophisticated attacks. In this study, a novel time interval conditional entropy method is proposed, which shows higher accuracy and ease of deployment compared to existing methods.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Computer Science, Hardware & Architecture
Yanqi Gong, Fei Hao, Liang Wang, Liang Zhao, Geyong Min
Summary: This paper presents a Mobile Edge Computing (MEC) model based on a dependent task offloading strategy, which achieves efficient offloading and execution solutions by considering social relationships between users and factors such as network latency and energy consumption. Experimental results demonstrate that the proposed strategy significantly reduces overhead compared to other baseline strategies.
IEEE TRANSACTIONS ON SUSTAINABLE COMPUTING
(2023)
Article
Computer Science, Information Systems
Wenqing Huang, Fei Hao, Jiaxing Shang, Wangyang Yu, Shengke Zeng, Carmen Bisogni, Vincenzo Loia
Summary: In recent years, graph neural networks have been important in graph data analysis, and the use of graph convolutional networks (GCN) in recommender systems has been extensively studied. This paper proposes a novel dual light graph convolutional network model called Dual-LightGCN, which filters disliked items to achieve more discriminative recommendations. The model divides the user-item interaction graph into two bipartite subgraphs, one for modeling user-item preferences and the other for modeling dislike relationships. Results show that Dual-LightGCN significantly improves F1-score compared to other recommendation algorithms, making it suitable for deployment in various IoT scenarios.
COMPUTER COMMUNICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Xiaohan Wang, Linchao Zhu, Yu Wu, Yi Yang
Summary: In this paper, a framework called SAOA is proposed to tackle egocentric action recognition by suppressing background distractors and enhancing action-relevant interactions. The framework introduces two extra sources of information, spatial location and discriminative features of candidate objects, to enable concentration on the occurring interactions. It includes an object-centric feature alignment method and a symbiotic attention mechanism to provide meticulous reasoning between the actor and the environment, achieving state-of-the-art performance on the largest egocentric video dataset.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Hardware & Architecture
Xiaokang Zhou, Wei Liang, Kevin I-Kai Wang, Zheng Yan, Laurence T. Yang, Wei Wei, Jianhua Ma, Qun Jin
Summary: In this article, a Peer-to-Peer (P2P) based Privacy-Perceiving Asynchronous Federated Learning (PPAFL) framework is introduced for secure and resilient decentralized model training in modern mobile robotic systems. This framework uses reputation-aware coordination and secret sharing based communication mechanisms to achieve encrypted P2P federated learning and anonymous local model updates.
IEEE WIRELESS COMMUNICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Mengya Guan, Xinjun Cai, Jiaxing Shang, Fei Hao, Dajiang Liu, Xianlong Jiao, Wancheng Ni
Summary: This paper proposes a new HGNN model named HMSG, which can comprehensively capture structural, semantic, and attribute information from both homogeneous and heterogeneous neighbors more purposefully. The performance of HMSG is evaluated through multiple graph-mining tasks and outperforms state-of-the-art baselines.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Xiao Shen, Mengqiu Shao, Shirui Pan, Laurence T. Yang, Xi Zhou
Summary: This paper proposes a novel domain-adaptive graph attention-supervised network (DGASN) to effectively tackle the problem of cross-network homophilous and heterophilous edge classification (CNHHEC), and achieves state-of-the-art performance in CNHHEC according to extensive experiments on real-world benchmark datasets.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Information Systems
Laurence T. Yang, Ruonan Zhao, Debin Liu, Wanli Lu, Xianjun Deng
Summary: The deep fusion of human-centered Cyber-Physical-Social Systems (CPSSs) and the importance of big data for providing proactive and accurate wisdom services are discussed. The traditional data centralized learning paradigm is no longer suitable due to concerns about data privacy and security. Federated Learning (FL) is introduced as a distributed privacy-preserving machine learning paradigm with great research significance and application values. The overview and extensive researches on FL from the perspective of human-centered CPSSs and tensor theory are presented. The theory about tensor representation, operation and decomposition, as well as tensor-empowered solutions for heterogeneous resource management, communication overhead, security and privacy are described.
IEEE COMMUNICATIONS SURVEYS AND TUTORIALS
(2023)
Article
Computer Science, Cybernetics
Shunli Zhang, Laurence T. Yang, Yue Zhang, Zhixing Lu, Jing Yu, Zongmin Cui
Summary: The development and applications of artificial intelligence (AI) bring both unprecedented opportunities and challenges for humans. Responsible AI offers a solution by incorporating social/physical rules into AI systems. However, these rules are challenging to formalize. In this article, we propose a data-driven responsible CPSS framework that mines valuable rules from CPSS data to optimize CPSS adaptively.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2023)
Article
Computer Science, Cybernetics
Fei Hao, Yixuan Yang, Jiaxing Shang, Doo-Soon Park
Summary: This article emphasizes the importance of cohesive subgraph mining on attributed social networks and introduces a new problem that incorporates fairness into cliques model. The article proposes an efficient algorithm called AFCMiner to detect absolute fair cliques in different types of attributive social networks. Extensive experiments show that AFCMiner significantly reduces the time for finding absolute fair cliques while ensuring correctness. A case study demonstrates the usefulness of the proposed model.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2023)
