7 papers
UrbanVerse: Learning Urban Region Representation Across Cities and Tasks
Fengze Sun, Egemen Tanin, Shanika Karunasekera +3
Recent advances in urban region representation learning have enabled a wide range of applications in urban analytics, yet existing methods remain limited in their capabilities to g…
SEAFormer: A Spatial Proximity and Edge-Aware Transformer for Real-World Vehicle Routing Problems
Saeed Nasehi Basharzad, Farhana Choudhury, Egemen Tanin
Real-world Vehicle Routing Problems (RWVRPs) require solving complex, sequence-dependent challenges at scale with constraints such as delivery time window, replenishment or recharg…
Generalising Traffic Forecasting to Regions without Traffic Observations
Xinyu Su, Majid Sarvi, Feng Liu +2
Traffic forecasting is essential for intelligent transportation systems. Accurate forecasting relies on continuous observations collected by traffic sensors. However, due to high d…
Dynamic Configuration of On-Street Parking Spaces using Multi Agent Reinforcement Learning
Oshada Jayasinghe, Farhana Choudhury, Egemen Tanin +1
With increased travelling needs more than ever, traffic congestion has become a major concern in most urban areas. Allocating spaces for on-street parking, further hinders traffic…
DeepMDV: Global Spatial Matching for Multi-depot Vehicle Routing Problems
Saeed Nasehi, Farhana Choudhury, Egemen Tanin +1
The rapid growth of online retail and e-commerce has made effective and efficient Vehicle Routing Problem (VRP) solutions essential. To meet rising demand, companies are adding mor…
DualCast: A Model to Disentangle Aperiodic Events from Traffic Series
Xinyu Su, Feng Liu, Yanchuan Chang +3
Traffic forecasting is crucial for transportation systems optimisation. Current models minimise the mean forecasting errors, often favouring periodic events prevalent in the traini…