Skip to content

This work considers combine multi-tricks with highway network to achieve traffic flow prediction accurately.

License

Notifications You must be signed in to change notification settings

zouguojian/Traffic-flow-prediction

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Traffic-flow-prediction

This work considers combining multi-tricks with highway networks to achieve accurate traffic flow prediction.

MODEL ITEM

1. MT-STNet: A Novel Multi-Task Spatiotemporal Network for Highway Traffic Flow Prediction (MT-STNet) [codes link]

  • Note that the MT-STNet program should be reproduced on the TensorFlow version >= 1.13.1. If not, some problems will appear in the running stage.

NOTICE

--->>>>>>> MT-STNet has been accepted by IEEE Transactions on Intelligent Transportation Systems (IEEE T-ITS).

The above codes have been uploaded to the Git-Hub page [codes link].

About

If you find this repository useful in your research, please cite the following paper:

@article{zou2024mt,
  title={MT-STNet: A Novel Multi-Task Spatiotemporal Network for Highway Traffic Flow Prediction},
  author={Zou, Guojian and Lai, Ziliang and Wang, Ting and Liu, Zongshi and Li, Ye},
  journal={IEEE Transactions on Intelligent Transportation Systems},
  volume={25},
  number={7},
  pages={8221--8236},
  year={2024},
  publisher={IEEE}
}