A5100685471- Transportation and Mobility Innovations
- Transportation Planning and Optimization
- Urban Transport and Accessibility
- Traffic Prediction and Management Techniques
- Human Mobility and Location-Based Analysis
- Evacuation and Crowd Dynamics
- Flood Risk Assessment and Management
- Data Management and Algorithms
- Ion-surface interactions and analysis
- Tropical and Extratropical Cyclones Research
- Anomaly Detection Techniques and Applications
- Wind and Air Flow Studies
- Smart Grid Security and Resilience
- Network Security and Intrusion Detection
- 3D Surveying and Cultural Heritage
- Vehicle Routing Optimization Methods
- Opportunistic and Delay-Tolerant Networks
- Solar-Powered Water Purification Methods
- Chemical Synthesis and Characterization
- Vehicular Ad Hoc Networks (VANETs)
- Metal Extraction and Bioleaching
- Infrastructure Maintenance and Monitoring
- 3D Shape Modeling and Analysis
- Remote-Sensing Image Classification
- Smart Grid and Power Systems
University of Florida
2020-2025
Zhejiang University of Technology
2023
Florida Coastal School of Law
2023
Jiyang College of Zhejiang A&F University
2021
Southwest Jiaotong University
2019
Wuhan University of Science and Technology
2016
Chinese Academy of Sciences
2002
Institute of High Energy Physics
2002
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...
Earthquakes are a rapid-onset hazard where advance planning and learning plays key role in mitigating injuries death to individuals. Recent advances earthquake detection have resulted the development of early warning (EEW) systems. These systems can provide predetermined geographic regions that an is progress, which may result individuals receiving seconds before significant shaking felt at their location. This additional time could allow take more effective protective actions during...
Natural hazards, such as wildfires, pose a significant threat to communities worldwide. Realtime forecasting of travel demand during wildfire evacuations is crucial for emergency managers and transportation planners make timely better-informed decisions. However, few studies focus on accurate in large-scale evacuations. To tackle this research gap, the study develops new methodological framework modeling highly granular spatiotemporal trip generation by using (a) GPS data generated mobile...
Artificial Intelligence (AI) and machine learning have been increasingly adopted for travel demand forecasting. The AI-based forecasting models, though generate accurate predictions, may produce prediction biases raise fairness issues. Using such biased models decision-making lead to transportation policies that exacerbate social inequalities. However, limited studies focused on addressing the issues of these models. Therefore, in this study, we propose a novel methodology develop...
Timely and accurate assessment of hurricane-induced building damage is crucial for effective post-hurricane response recovery efforts. Recently, remote sensing technologies provide large-scale optical or Interferometric Synthetic Aperture Radar (InSAR) imagery data immediately after a disastrous event, which can be readily used to conduct rapid assessment. Compared satellite imageries, the penetrate cloud cover more complete spatial cover-age damaged zones in various weather conditions....
Accurately assessing building damage is critical for disaster response and recovery. However, many existing models detecting have poor prediction accuracy due to their limited capabilities of identifying detailed, comprehensive structural and/or non-structural from the street-view image. Additionally, these mainly rely on imagery data classification, failing account other information, such as wind speed, characteristics, evacuation zones, distance hurricane track. To address limitations, in...
Hurricane Ian is the deadliest and costliest hurricane in Florida's history, with 2.5 million people ordered to evacuate. As we witness increasingly severe hurricanes context of climate change, mobile device location data offers an unprecedented opportunity study evacuation behaviors. With a terabyte-level GPS dataset, introduce holistic behavior algorithm case Ian: infer evacuees' departure time categorize them into different behavioral groups, including self, voluntary, mandatory, shadow...
The free-floating bike sharing systems (BSSs) are booming all over the world. How to rebalance bikes is a problem faced by operators. To tackle this problem, firstly, we compare five models predict shared demand and choose time series decision tree model. Then based on prediction results, propose zone-based two-stage rebalancing model an algorithm solve proposed divides research area into two kinds of zones: zones with deficient (ZDB) sufficient (ZSB). objective optimize matching degree...
Real-time forecasting of travel demand during wildfire evacuations is crucial for emergency managers and transportation planners to make timely better-informed decisions. However, few studies focus on accurate in large-scale evacuations. Therefore, this study develops tests a new methodological framework modeling trip generation by using (a) GPS data generated mobile devices (b) state-of-the-art AI technologies. The proposed methodology aims at evacuation trips other types trips. Based the...
Timely and accurate assessment of hurricane-induced building damage is crucial for effective post-hurricane response recovery efforts. Recently, remote sensing technologies provide large-scale optical or Interferometric Synthetic Aperture Radar (InSAR) imagery data immediately after a disastrous event, which can be readily used to conduct rapid assessment. Compared satellite imageries, the penetrate cloud cover more complete spatial coverage damaged zone in various weather conditions....
The security of fieldbus networks is utmost importance for industrial control systems. Within networks, masquerade attacks and illegal device intrusions are two prevalent forms attacks. detection these particularly challenging due to the sophisticated masquerading deception techniques employed by attackers. To address challenges in this paper presents an intrusion localization method based on physical fingerprints. involves constructing a fingerprint model each collecting voltage signals...