A5041224976- Human Mobility and Location-Based Analysis
- Traffic Prediction and Management Techniques
- Transportation Planning and Optimization
- Urban Transport and Accessibility
- Data Management and Algorithms
- Transportation and Mobility Innovations
- Economic and Environmental Valuation
- Data-Driven Disease Surveillance
- Crime Patterns and Interventions
- Vehicle emissions and performance
- Groundwater flow and contamination studies
- Urban and Freight Transport Logistics
- Business Strategy and Innovation
- Vehicular Ad Hoc Networks (VANETs)
- Smart Parking Systems Research
- Geophysics and Gravity Measurements
- Water Quality Monitoring Technologies
- Digital Platforms and Economics
- Groundwater and Isotope Geochemistry
- COVID-19 epidemiological studies
- Anomaly Detection Techniques and Applications
- Infection Control and Ventilation
- Merger and Competition Analysis
- Land Use and Ecosystem Services
- Crime, Illicit Activities, and Governance
University of Hong Kong
2021-2024
Zhejiang University
2024
Singapore-MIT Alliance for Research and Technology
2024
Massachusetts Institute of Technology
2023
Hong Kong Design Centre
2021-2022
Trajectory prediction of vehicles in city-scale road networks is great importance to various location-based applications such as vehicle navigation, traffic management, and recommendations. Existing methods typically represent a trajectory sequence grid cells, segments or intention sets. None them ideal, the cell-based representation ignores network structures other two are less efficient analyzing networks. Moreover, previous models barely leverage spatial dependencies only consider at cell...
For bike sharing systems, demand prediction is crucial to ensure the timely re-balancing of available bikes according predicted demand. Existing methods for are mostly based on its own historical variation, essentially regarding it as a closed system and neglecting interaction between different transportation modes. This particularly important because often used complement travel through other modes (e.g., public transit). Despite some recent progress, no existing method capable leveraging...
Bike sharing is an increasingly popular part of urban transportation systems. Accurate demand prediction the key to support timely re-balancing and ensure service efficiency. Most existing models bike-sharing are solely based on its own historical variation, essentially regarding bike as a closed system neglecting interaction between different transport modes. This particularly important because often used complement travel through other modes (e.g., public transit). Despite some recent...
Dynamic demand prediction is crucial for the efficient operation and management of urban transportation systems. Extensive research has been conducted on single-mode prediction, ignoring fact that demands different modes can be correlated with each other. Despite some recent efforts, existing approaches to multimodal are generally not flexible enough account multiplex networks diverse spatial units heterogeneous spatiotemporal correlations across modes. To tackle these issues, this study...
Due to their reliability, efficiency, and environmental friendliness, metro systems have become a crucial solution transportation challenges associated with urbanization. Many countries constructed or expanded networks over the past decades. During planning stage, accurately predicting station ridership post-expansion, particularly for new stations, is essential enhance effectiveness of infrastructure investments. However, station-level prediction under expansion scenarios (MRP-E) has not...
Short-term route prediction on road networks allows us to anticipate the future trajectories of users, enabling a plethora intelligent transportation applications such as dynamic traffic control or personalized recommendation. Despite recent advances in this area, existing methods focus primarily learning sequential transition patterns, neglecting inherent spatial structural relations that can affect human routing decisions. To fill gap, paper introduces RouteKG, novel Knowledge Graph-based...
Bike sharing is emerging globally as an active, convenient, and sustainable mode of transportation. To plan successful bike-sharing systems (BSSs), many cities start from a small-scale pilot gradually expand the system to cover more areas. For station-based BSSs, this means planning new stations based on existing ones over time, which requires prediction number trips generated by these across whole system. Previous studies typically rely relatively simple regression or machine learning...
Public events, such as concerts and sports games, can be major attractors for large crowds, leading to irregular surges in travel demand. Accurate human mobility prediction public events is thus crucial event planning well traffic or crowd management. While rich textual descriptions about are commonly available from online sources, it challenging encode information statistical machine learning models. Existing methods generally limited incorporating information, handling data sparsity,...
Bike sharing is an increasingly popular part of urban transportation systems. Accurate demand prediction the key to support timely re-balancing and ensure service efficiency. Most existing models bike-sharing are solely based on its own historical variation, essentially regarding bike as a closed system neglecting interaction between different transport modes. This particularly important because often used complement travel through other modes (e.g., public transit). Despite some recent...
Route choice modeling is a fundamental task in transportation planning and demand forecasting. Classical methods generally adopt the discrete model (DCM) framework with linear utility functions high-level route characteristics. While several recent studies have started to explore applicability of deep learning for modeling, they are limited path-based models relatively simple architectures relying on predefined sets. Existing link-based can capture dynamic nature link choices within trip...