A5078723316- Urban Transport and Accessibility
- Transportation and Mobility Innovations
- Transportation Planning and Optimization
- Evacuation and Crowd Dynamics
- Traffic Prediction and Management Techniques
- Flood Risk Assessment and Management
- Human Mobility and Location-Based Analysis
- Fire effects on ecosystems
- Smart Parking Systems Research
- Disaster Management and Resilience
- Economic and Environmental Valuation
- Traffic control and management
- Sharing Economy and Platforms
- Energy, Environment, and Transportation Policies
- Tropical and Extratropical Cyclones Research
- Data Management and Algorithms
- Structural Health Monitoring Techniques
- Food Safety and Hygiene
- Remote Sensing and Land Use
- Urban and Freight Transport Logistics
- Medical Imaging Techniques and Applications
- Anomaly Detection Techniques and Applications
- Wind and Air Flow Studies
- Seismology and Earthquake Studies
- Vehicular Ad Hoc Networks (VANETs)
University of Science and Technology Liaoning
2025
University of Florida
2020-2025
Guizhou Electromechanical Research and Design Institute
2025
National University of Defense Technology
2024
Florida Coastal School of Law
2020-2023
The University of Texas at Austin
2023
University of North Carolina at Chapel Hill
2020
Georgia Institute of Technology
2019
Johns Hopkins University
2004-2018
University of Michigan
2018
Abstract Objective Policy-makers and practitioners have a need to assess community resilience in disasters. Prior efforts conflated with functioning, combined resistance recovery (the components of resilience), relied on static model for what is inherently dynamic process. We sought develop linked conceptual computational models functioning after disaster. Methods developed system dynamics that predicts The outputted the time course before, during, disaster, which was used calculate...
Accurately forecasting the real-time travel demand for dockless scooter-sharing is crucial planning and operations of transportation systems. Deep learning models provide researchers with powerful tools to achieve this task, but research in area still lacking. This paper thus proposes a novel deep architecture named Spatio-Temporal Multi-Graph Transformer (STMGT) forecast spatiotemporal demand. The proposed model uses graph convolutional network (GCN) based on adjacency graph, functional...
Climate change is increasing the threat of wildfires to populated areas, especially those within wildland-urban interface (WUI). The 2021 Marshall fire forced evacuation over 30,000 people in Boulder, Jefferson and Adams Counties Colorado, US. To improve our understanding wildfire response, we surveyed individuals affected by analyze their decisions resulting behavior. We used linear logistic regression models determine factors influencing individuals' risk perceptions, evacuate or stay,...
Abstract Facing the escalating effects of climate change, it is critical to improve prediction and understanding hurricane evacuation decisions made by households in order enhance emergency management. Current studies this area often have relied on psychology-driven linear models, which frequently exhibited limitations practice. The present study proposed a novel interpretable machine learning approach predict household-level leveraging easily accessible demographic resource-related...
Emerging transportation technologies such as ridesourcing services (i.e. Uber, Lyft, and Via) are disrupting the sector transforming public transit. Some transit observers envision future to be integrated systems with fixed-route running along major corridors servicing lower-density areas. A switch from a conventional service model this kind of Mobility-on-Demand (MOD) system, however, may elicit varied responses residents. This paper evaluates traveler preferences for proposed MOD system...
Abstract Earthquakes pose substantial threats to communities worldwide. Understanding how people respond the fast-changing environment during earthquakes is crucial for reducing risks and saving lives. This study aims people’s protective action decision-making in by leveraging explainable machine learning video data. Specifically, this first collected real-world CCTV footage postings from social media platforms, then identified annotated changes behavioral responses M7.1 2018 Anchorage...