Loading…
Welcome to CTRF’s 60th Annual Conference! Enjoy Ottawa
Wednesday May 28, 2025 9:50am - 10:10am EDT
Accurate predictions of on-street parking availability are vital for enhancing parking guidance systems, reducing drivers' search times, and alleviating traffic congestion and CO2 emissions. Traditional methods for predicting parking occupancy often fail to account for both the spatial dependencies between parking blocks and the impact of exogenous factors such as weather, nearby amenities, and traffic conditions._x000D_
This paper presents a novel simplified spatio-temporal graph neural network (SST-GNN) model that addresses these limitations by integrating exogenous data and leveraging a graph-based representation to capture spatial relationships between parking locations. The model also incorporates a temporal mechanism to account for the dynamic evolution of parking demand. By combining intrinsic and contextual factors, the proposed approach significantly improves prediction accuracy._x000D_
Experimental results on a real-world dataset demonstrate that the (SST-GNN) model outperforms traditional benchmarks in forecasting on-street parking occupancy, showcasing its potential to revolutionize smart parking systems.
Speakers
avatar for Martin Trépanier

Martin Trépanier

Full Professor, Polytechnique Montréal and CIRRELT
Martin Trépanier is a civil engineer and professor at the department of mathematics and industrial engineering of École Polytechnique de Montréal, an engineering school affiliated to the Université de Montréal.  He is the titular of the Chair in the transformation of transportation... Read More →
AA

Ayman Agoube

Polytechnique Montréal
Wednesday May 28, 2025 9:50am - 10:10am EDT
Desmarais 1160 55 Laurier Ave E, Ottawa ON K1N 6N5

Attendees (1)


Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Share Modal

Share this link via

Or copy link