A5084370885- Traffic Prediction and Management Techniques
- Traffic control and management
- Transportation Planning and Optimization
- Vehicular Ad Hoc Networks (VANETs)
- Human Mobility and Location-Based Analysis
- Autonomous Vehicle Technology and Safety
- Mobile Crowdsensing and Crowdsourcing
- Privacy-Preserving Technologies in Data
- Traffic and Road Safety
- Transportation and Mobility Innovations
- Urban Transport and Accessibility
- Cryptography and Data Security
- Anomaly Detection Techniques and Applications
- Simulation and Modeling Applications
- Network Security and Intrusion Detection
- Internet Traffic Analysis and Secure E-voting
- Vehicle emissions and performance
- Blockchain Technology Applications and Security
- Video Surveillance and Tracking Methods
- Advanced Image and Video Retrieval Techniques
- Advanced Neural Network Applications
- Advanced Malware Detection Techniques
- Auction Theory and Applications
- IoT and Edge/Fog Computing
- Opportunistic and Delay-Tolerant Networks
Beihang University
2016-2025
Hefei Institute of Technology Innovation
2019-2024
Beijing Transportation Research Center
2020-2024
China Academy of Transportation Sciences
2023
Ji Hua Laboratory
2022-2023
Ministry of Transport
2022
Beijing Institute of Big Data Research
2022
Beijing Advanced Sciences and Innovation Center
2019-2021
Nanjing University of Science and Technology
2020
Traffic Management Research Institute
2020
Predicting the future trajectories of dynamic traffic actors is Gordian knot for autonomous vehicles to achieve collision-free driving. Most existing works suffer from a gap in characterizing evolving interactions scenario components and ensuring physical feasibility predictions, particularly highly heterogeneous scenarios. Therefore, we propose an Enhanced Multi-Stream Interaction Network (EMSIN), which devoted providing accurate trajectory predictions. EMSIN highlights several threads...
As an emerging paradigm for urban sensing, vehicular crowd sensing (VCS) has received increasing attention in recent years. Unlike traditional paradigms, VCS leverages ubiquitous connected vehicles (CVs) and diverse onboard sensors to efficiently collect city-scale data. Despite the considerable benefits of CVs, fast-changing traffic environment attendant human social factors bring significant complexity system make it a typical cyber-physical-social (CPSS), followed by challenge robust...
Recently, short-term traffic prediction under conditions with corrupted or missing data has become a popular topic. Since road section predictive power regarding the adjacent roads at specific location, this paper proposes novel hybrid convolutional long memory neural network model based on critical sections (CRS-ConvLSTM NN) to predict evolution of global networks. The that have most powerful impact subnetwork are identified by spatiotemporal correlation algorithm. Subsequently, speed is...
The rapid development of connected automatic vehicle (CAV) technology makes vehicular <i>ad hoc</i> networks (VANETs) an urgently needed research field. It includes vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) message flows. A roadside unit (RSU) is important infrastructure for V2I communication provides information services CAVs. However, unoptimal RSU deployment may result in RSUs failing to improve the efficiency VANETs compromising capability service most vehicles....
In this paper, we present an adaptive signal control scheme to prevent intersection traffic blockage resulted from vehicle queue spillover. A method identify spillover condition through simplified shockwave analysis is developed. Instead of measuring the length or locating end directly, relies on speed which more feasible measure in practice. The designed potential blockage, and adaptively allocates green time appropriate phases. At end, a simulation study carried out evaluate proposed...
Vehicular platooning is emerging as a promising method that can enhance road utilization, alleviate traffic congestion, and even decrease energy expenditure by shortening the distance between vehicles in platoon. In platooning, platoon leader (PL) required to communicate with members (PMs) issue instructions. this way, PMs are simply expected follow command enjoy their free time. However, when same instruction sent different form of single-hop unicast, ciphertext will go up quantity...
Benefiting from unified sensors and long-term traffic engagement, for-hire vehicles (FHVs) are widely considered the mainstay for vehicular crowd sensing (VCS) tasks. However, incentivizing FHVs to participate in tasks remains a fundamental challenge FHV-enabled VCS systems: one thing, distribution diversity of orders limits participating VCS; another, FHVs' operating states determine whether they free execute To address above issues, this article proposes SHIP, State-aware Hybrid Incentive...
Recently, short-term traffic state prediction for urban transportation networks has become a popular topic. However, due to the uncontrollable and unpredictable elements of special events, it is difficult get abundant data desired predictions under such condition. As k-nearest neighbor (KNN) competitive advantage over other approaches, could predict based on small correlative part data. Thus, event-based KNN (SEKNN) model proposed with three key points presented in this paper. First,...
In this study, we introduce an AR-based Meta-Vehicle Road Collaboration Testing System (AR-MVRTs), a significant advancement in autonomous driving testing. This system utilizes vehicle-road collaboration, Augmented Reality (AR), and Metaverse technologies for high-risk scenario simulation dynamic interaction between virtual data actual vehicles infrastructure, enhancing verification optimization methods. The core contribution is the innovative framework component model, integrating AR with...
Traffic accidents, being a significant contributor to both human casualties and property damage, have long been focal point of research for many scholars in the field traffic safety. However, previous studies, whether focusing on static environmental assessments or dynamic driving analyses, as well pre-accident predictions post-accident rule typically conducted isolation. There has lack an effective framework developing comprehensive understanding application To address this gap, paper...
Cyber attacks pose significant threats to connected autonomous vehicles in intelligent transportation systems. threat intelligence (CTI), which involves collecting and analyzing cyber information, offers a promising approach addressing emerging vehicle enabling proactive security defenses. Obtaining valuable information from enormous cybersecurity data using knowledge extraction technologies achieve CTI modeling is an effective means ensure automotive cybersecurity. However, the lack of...
Autonomous Vehicle Platoon (AVP) is conceived as a promising solution to enhance the traffic capacity and reduce energy consumption in intelligent transportation system. Nevertheless, AVP without security guarantees are prone various attacks, which probably lead life-threatening accidents. Motivated by solving this issue, an outsourced attribute-based access control mechanism with direct revocation for (RFAP) introduced paper. Among them, encryption utilized implement fine-grained during...