AI-based traffic flow prediction
In this paper we discuss an AI-based model for end-to-end traffic prediction tasks, which combines graph convolutional networks and gated recurrent units. The spatial feature of complex topologies and dynamic temporal features can be well extracted from spatial-temporal traffic data. Experiments wit...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Master by Coursework |
| Language: | English |
| Published: |
Nanyang Technological University
2020
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/143065 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | In this paper we discuss an AI-based model for end-to-end traffic prediction tasks, which combines graph convolutional networks and gated recurrent units. The spatial feature of complex topologies and dynamic temporal features can be well extracted from spatial-temporal traffic data. Experiments with real-time traffic flow data sets show that this model has better performance compared to some baseline models. |
|---|