odinhg/Graph-Neural-Networks-INF367A

Traffic prediction with graph neural network using PyTorch Geometric. The implementation uses the MetaLayer class to build the GNN which allows for separate edge, node and global models.

32
/ 100
Emerging

This project helps traffic engineers and urban planners predict future traffic volumes on specific road segments. By taking current traffic data, alongside month, weekday, and hour, it forecasts traffic for the next hour for each station. It's designed for professionals who need accurate short-term traffic flow predictions for operational planning.

No commits in the last 6 months.

Use this if you need to predict hourly traffic volumes across a network of interconnected traffic stations.

Not ideal if you need long-range traffic forecasts or predictions for individual, isolated road segments without network dependencies.

traffic-management urban-planning transportation-analytics traffic-forecasting
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 17 / 25

How are scores calculated?

Stars

31

Forks

10

Language

Python

License

Last pushed

Feb 02, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/odinhg/Graph-Neural-Networks-INF367A"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.