A5021146920- Traffic and Road Safety
- Urban Transport and Accessibility
- Lymphoma Diagnosis and Treatment
- Injury Epidemiology and Prevention
- CAR-T cell therapy research
- Automotive and Human Injury Biomechanics
- Traffic Prediction and Management Techniques
- Autonomous Vehicle Technology and Safety
- Transportation Planning and Optimization
- Chronic Lymphocytic Leukemia Research
- Viral-associated cancers and disorders
- Economic and Environmental Valuation
- Traffic control and management
- Infrastructure Maintenance and Monitoring
- Muscle activation and electromyography studies
- COVID-19 epidemiological studies
- Prosthetics and Rehabilitation Robotics
- Protein Degradation and Inhibitors
- Maritime Navigation and Safety
- SARS-CoV-2 and COVID-19 Research
- CNS Lymphoma Diagnosis and Treatment
- Cancer Genomics and Diagnostics
- Histone Deacetylase Inhibitors Research
- HER2/EGFR in Cancer Research
- SARS-CoV-2 detection and testing
Ruijin Hospital
2019-2025
Shanghai Jiao Tong University
2008-2025
Shanghai Institute of Hematology
2016-2025
South China University of Technology
2021-2025
Changsha University
2024
State Key Laboratory of Medical Genomics
2020-2024
Changsha University of Science and Technology
2024
Chongqing University
2024
University of Hong Kong
2016-2022
Chinese University of Hong Kong
2022
Issues related to motorcycle safety in China have not received enough research attention. As such, the causal relationship between injury outcomes of crashes and potential risk factors remains unknown. This study intended investigate motorcyclists involved road traffic China. To account for ordinal nature response unobserved heterogeneity, a mixed ordered logit model was employed. Given that crash occurrence process is different intersections non-intersections, separate models were developed...
Pedestrian red-light violations at signalized crossings are an important traffic safety concern, particularly in densely populated cities. In this study, the authors quantitatively investigated factors associated with pedestrian and injury severity resulting from pedestrian–motor vehicle crashes crossings. Random parameter probit models used to account for individual-specific heterogeneity that arises a set of unmeasured related conditions pedestrians' physical mental status. Data analysis...
As mobile device location data become increasingly available, new analyses are revealing the significant changes of mobility pattern when an unplanned event happened. With different control policies from local and state government, COVID-19 outbreak has dramatically changed behavior in affected cities. This study been investigating impact on number people involved crashes accounting for intensity measures using Negative Binomial (NB) method. Based a comprehensive dataset aggregated New York...
The accurate trajectory prediction of surrounding vehicles is crucial for the sustainability and safety connected autonomous under mixed traffic streams in real world. task challenging because there are all kinds factors affecting motions vehicles, such as individual movements, ambient driving environment especially road conditions, interactions with neighboring vehicles. To resolve above issues, this work proposes a novel Heterogeneous Context-Aware Graph Convolutional Networks following...
Summary The present study intended to (1) investigate the injury risk of pedestrian casualties involved in traffic crashes at signalized intersections Hong Kong; (2) determine effect volumes on severity levels injuries; and (3) explore role spatial correlation econometric crash‐severity models. data from 1889 pedestrian‐related 318 between 2008 2012 were elaborately collected Traffic Accident Database System maintained by Kong Transport Department. To account for cross‐intersection...
With the enormous losses to society that result from highway crashes, gaining a better understanding of risk factors affect traffic crash occurrence has long been prominent focus safety research. In this study, we develop an optimised radial basis function neural network (RBFNN) model approximate nonlinear relationships between frequency and relevant factors. Our case study compares performance RBFNN with traditional negative binomial (NB) back-propagation (BPNN) models for prediction on...
One challenge faced by the random-parameter count models for crash prediction is unavailability of unique coefficients out-of-sample observations. The means distributions are typically used without explicit consideration variances. In this study, virtue Taylor series expansion, we proposed a straightforward yet analytic solution to include both and variances random parameters unbiased prediction. We then theoretically quantified systematic bias arising from omission parameters. Our numerical...
Zonal crash prediction that considers cross-zonal spatial correlation is a frontline research topic, especially in the context of transportation safety planning. This study presents an evaluation models at level traffic analysis zones with four types spatial-proximity structures: 0–1 first-order adjacency, common-boundary length, geometry-centroid distance, and crash-weighted centroid distance. Bayesian conditional autoregressive priors was successfully applied, Hillsborough data were used...