A5101934480- Autonomous Vehicle Technology and Safety
- Traffic and Road Safety
- Vehicular Ad Hoc Networks (VANETs)
- Risk and Safety Analysis
- Spine and Intervertebral Disc Pathology
- Metallurgy and Material Forming
- Engineering Structural Analysis Methods
- IoT and GPS-based Vehicle Safety Systems
- IoT and Edge/Fog Computing
- Cervical and Thoracic Myelopathy
- Traffic Prediction and Management Techniques
- Maritime Navigation and Safety
- Transportation and Mobility Innovations
- Traffic control and management
- Structural Integrity and Reliability Analysis
- Mineral Processing and Grinding
- Trade Secret Protection Methods
- Offshore Engineering and Technologies
- Industrial Vision Systems and Defect Detection
- Adversarial Robustness in Machine Learning
- Spinal Fractures and Fixation Techniques
Peking University Third Hospital
2024
Peking University
2024
Shanghai University
2022-2024
Zhengzhou University
2023
Nanjing University of Aeronautics and Astronautics
2017
Nowadays, the online-to-offline (O2O) retailers provide on-demand delivery service for online orders by their own fleets and riders. An intelligent network lays an important foundation to support cost-effective in long run. Drones have great potential revolutionize instant industry regarding cost timeliness, while hazard risks humans environment should be seriously considered through sophisticated design. In this paper, we propose a framework drone-driven design problem with consideration of...
<title>Abstract</title> Purpose Japanese Orthopaedic Association (JOA) Score is widely used to measure the neurological functions of patients with cervical spondylotic myelopathy (CSM). However, there a limitation JOA score system that not determined by directly and may be influenced subjective bias from observers. This study aims develop patient-reported (P-JOA) address this deficiency. Methods prospective cohort involved 120 CSM November 2021 December 2022 in our hospital. We developed...
UAVs have a wide range of applications while there are risks in the operations. In this paper, we identify risk factors influencing drone accidents from perspectives environment, technology, and personnel through analysis accident reports dataset. Moreover, construct Bayesian network that reveals dependency relationship among propagation mechanism leading to accident. terms parameter learning, prior probabilities for each cause estimated based on reported occurrences official pilot...
Abstract With the rapid development of China’s national economy, petrochemical industry is particularly rapid, high-temperature and high-pressure pipelines are widely used in oil gas storage operation industries. The design level becomes key to measuring whether a unit can win fierce market competition, one core technologies stress analysis pressure pipeline. CAESAR II pipeline software more popular international pipe software. Its data input simple graphic display intuitive, which easy for...
Multi-vehicle pursuit (MVP) such as autonomous police vehicles pursuing suspects is important but very challenging due to its mission and safety critical nature. While multi-agent reinforcement learning (MARL) algorithms have been proposed for MVP problem in structured grid-pattern roads, the existing use randomly training samples centralized learning, which leads homogeneous agents showing low collaboration performance. For more of multiple evading vehicles, these typically select a fixed...
Multi-vehicle pursuit (MVP) is one of the most challenging problems for intelligent traffic management systems due to multi-source heterogeneous data and its mission nature. While many reinforcement learning (RL) algorithms have shown promising abilities MVP in structured grid-pattern roads, their lack dynamic effective awareness limits pursuing efficiency. The sparse reward tasks still hinders optimization these RL algorithms. Therefore, this paper proposes a distributed generative...
Flatness is one of the most important specifications for strip products in cold rolling processes. Shape control rolled product often characterized as a complex process with multiple operation conditions, multi-variables, time-varying parameters, strong coupling and nonlinearity. Accurate online shape defect diagnosis still difficult task. This paper proposed frequent pattern mining algorithm based method, aiming to solve bottleneck problem associated Apriori when applied industrial An...
The Criminal Law Amendment (11) changes the criminalization standard for crime of infringing trade secrets from "causing significant losses" to "serious circumstances", but essence boundary between and non-crime is still whether "significant losses have been caused". By comparing four mainstream theories representative extraterritorial legislation, this paper analyzes dimensions: implementation feasibility, economic benefits, scope application, application possibilities. profit method...
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...