A5103144889- Traffic control and management
- Autonomous Vehicle Technology and Safety
- Vehicular Ad Hoc Networks (VANETs)
- Cryptography and Data Security
- Access Control and Trust
- Neural Networks and Applications
- Caching and Content Delivery
- Stochastic Gradient Optimization Techniques
- Data Stream Mining Techniques
- Brain Tumor Detection and Classification
- Cloud Data Security Solutions
- Software-Defined Networks and 5G
- IoT and Edge/Fog Computing
- Privacy-Preserving Technologies in Data
- Cloud Computing and Resource Management
- Optical Wireless Communication Technologies
- Human Mobility and Location-Based Analysis
- Advanced Malware Detection Techniques
- Big Data Technologies and Applications
- Energy Harvesting in Wireless Networks
- Energy Efficient Wireless Sensor Networks
- Advanced Bandit Algorithms Research
- Adversarial Robustness in Machine Learning
- Image and Video Quality Assessment
- Image Enhancement Techniques
Shanghai Electric (China)
2024-2025
Beijing University of Posts and Telecommunications
2011-2023
University of Electronic Science and Technology of China
2022-2023
Shenzhen University
2023
Hangzhou Dianzi University
2020-2021
University of Oklahoma
2018-2019
Hebei University of Science and Technology
2019
University of Tulsa
2019
Query optimization has long been a fundamental yet challenging topic in the database field. With prosperity of machine learning (ML), some recent works have shown advantages reinforcement (RL) based learned query optimizer. However, they suffer from limitations due to data-driven nature ML. Motivated by ML characteristics and maturity, we propose LEON -a framework for ML-aidEd OptimizatioN. improves expert optimizer self-adjust particular deployment leveraging knowledge To train model,...
Service-oriented architecture and cloud computing have become the prevalent paradigm. In this paradigm, resources can be accessed like other utility services available in today's society. meantime, robotics applications are joining trend. More more robot shifting from manufacture to non-manufacture service industries. However, for on-demand supply of large-scale heterogeneous robots, It is still a problem not yet been studied, including fundamental management efficiency issues using these...
Some recent works have shown the advantages of reinforcement learning (RL) based learned query optimizers. These often use cost (i.e., estimation model) or latency execution time) as guidance signals for training their models. However, cost-based underperforms in and latency-based is time-intensive. In order to bypass such a dilemma, researchers attempt transfer value network from domain domain. We recognize critical insights cost/latency-based training, prompting us reward function rather...
The coordination of microgrid (MG) and distribution is an emerging trend for future development. This paper proposes uncertainty feasible region (UFR) analysis method based on outer approximation cutting (OAC) under the MG distribution. Firstly, optimal economic dispatch scheduling obtained. It serves as basis intraday UFR. Drawing concepts robust optimization, a determining intra-day UFR proposed. Subsequently, problem transformed using duality theory by identifying umbrella constraints,...
Many communities have researched the application of novel network architectures, such as content-centric networking (CCN) and software-defined (SDN), to build future Internet. Another emerging technology which is big data analysis has also won lots attentions from academia industry. splendid researches been done on CCN, SDN, data, all addressed separately in traditional literature. In this paper, we propose a paradigm jointly consider provide architecture internal flow, processing, use cases...
The explosive growth of the Internet Things and modern networking technologies lay foundation for development intelligent transportation systems smart cities. To analyzing massive data under required time issues, edge computing paradigm is applied, which pre-processing large amounts at network to save bandwidth improve response time. However, reliability security are still facing many challenges in environment. In this article, we propose a multi-authority hybrid attribute-based signature...
Traffic context plays an important role in supporting automated driving and intelligent transportation systems. Smart vehicles explore surrounding environments by analyzing sensor data periodically communicating with neighbors road infrastructures. The can be well learned this way to support driving, but the vehicle trajectory also easily exposed under eavesdropping attacks. pseudonym is proposed hide real identity of vehicles. However, effectiveness anonymity, safety convenience...
Velocity control in autonomous driving is an emerging technology that has achieved rapid progress over the last decade. However, existing velocity models are developed single-lane scenarios and ignore negative impacts caused by harsh changes. In this work, we propose a framework based on reinforcement learning, called RISE (contRol velocIty for autonomouS vEhicle). multi-lane circumstances, improves decisions regarding vehicle itself, while minimizing rear vehicles. To achieve multiple...
Metaverse is recently envisioned as the main driver for immersive multimedia in future networks. Light field video (LFV), considered an intermediate transition scheme towards metaverse, conducive to sensing and reconstructing realistic scenes digital twins. However, research on LFV systems still lacks comprehensive investigation, impeding their practical application. This paper addresses major technical challenges involved delivery through mobile networks, showing a trade-off between...
We investigate quantum teleportation between users located in noninertial frames and analyze how the acceleration can improve fidelity of two relatively accelerating partners. see that increases with respect to as a consequence Unruh effect. In our scheme, Alice Rob initially share special $\mathsf{X}$-type state, stays stationary, while is uniformly accelerated Alice. additionally study system-environment dynamics frames, i.e., state shared interacts environment via amplitude damping...
Autonomous driving is an emerging technology that has developed rapidly over the last decade. There have been numerous interdisciplinary challenges imposed on current transportation system by autonomous vehicles. In this paper, we conduct algorithmic study vehicle decision-making process, which a fundamental problem in automation field and root cause of most traffic congestion. We propose perception-and-decision framework, called HEAD, consists enHanced pErception module mAneuver Decision...
Privacy preservation is a crucial problem in resource sharing and collaborating among multi-domains. Based on this problem, we propose role-based access control model for privacy preservation. This scheme avoided the leakage of resources while implementing control, it has advantage lower communication overhead. We demonstrate meets IND-CCA2 semantic security by using random oracle. The simulation result shows better execution efficiency application effects.
To achieve continuous massive data transmission with significantly reduced payload, the users can adopt semantic communication techniques to compress redundant information by transmitting features instead. However, current works on mainly focus high compression ratio, neglecting wireless channel effects including dynamic distortion and multi-user interference, which limit fidelity of communication. address this, this paper proposes a diffusion model (DM)-based enhancer (DMCE) for improving...
Simultaneous speech translation (SimulST) is a demanding task that involves generating translations in real-time while continuously processing input. This paper offers comprehensive overview of the recent developments SimulST research, focusing on four major challenges. Firstly, complexities associated with lengthy and continuous streams pose significant hurdles. Secondly, satisfying requirements presents inherent difficulties due to need for immediate output. Thirdly, striking balance...
This work presents a novel module, namely multi-branch concat (MBC), to process the input tensor and obtain multi-scale feature map. The proposed MBC module brings new degrees of freedom (DoF) for design attention networks by allowing type transformation operators number branches be flexibly adjusted. Two important operators, multiplex split, are considered in this work, both which can represent features at more granular level increase range receptive fields. By integrating (MBA) is...
In automated trust negotiation(ATN), strangers build relationship by disclosing attributes credentials alternately. the recent study of ATN, there was no rigorous formal definition ATN abstract model, and have nothing to do with time behavior. It exist denial service attack which can lead system paralysis. We present basic components model. defines model bringing state-transition system. Based on this formalized basis, behavior will be explored. analyze discuss some semantics describe...
The multi-vehicle pursuit (MVP), as a problem abstracted from various real-world scenarios, is becoming hot research topic in the Intelligent Transportation System (ITS). combination of Artificial Intelligence (AI) and connected vehicles has greatly promoted development MVP. However, existing works on MVP pay little attention to importance information exchange cooperation among pursuing under complex urban traffic environment. This paper proposed graded-Q reinforcement learning with...
The question of how financial development affects economic inequality is a subject much debate. This paper adds to this literature by examining whether banking deregulation income using state-level data from the United States late 20th century. Specifically, we test hypothesis that interstate branch-banking restrictions had an effect on as measured Gini Coefficient and Thiel Index. We conduct our tests fixed-effects OLS models System GMM dynamic panel analysis. Our results suggest branching...
The pursuit-evasion game in Smart City brings a profound impact on the Multi-vehicle Pursuit (MVP) problem, when police cars cooperatively pursue suspected vehicles. Existing studies MVP problems tend to set evading vehicles move randomly or fixed prescribed route. opponent modeling method has proven considerable promise tackling non-stationary caused by adversary agent. However, most of them focus two-player competitive games and easy scenarios without interference environments. This paper...
Many communities have researched the application of novel network architectures such as Content-Centric Networking (CCN) and Software-Defined (SDN) to build future Internet. Another emerging technology which is big data analysis has also won lots attentions from academia industry. splendid researches been done on CCN, SDN, data, all addressed separately in traditional literature. In this paper, we propose a paradigm jointly consider provide architecture internal flow, processing use cases...
This work presents a novel module, namely multi-branch concat (MBC), toprocess the input tensor and obtain multi-scale feature map. The proposedMBC module brings new degrees of freedom (DoF) for design attentionnetworks by allowing type transformation operators numberof branches to be flexibly adjusted. Two important operators,multiplex split, are considered in this work, both which can representmulti-scale features at more granular level increase range receptivefields. By integrating MBC...