Repository for advanced traffic forecasting models integrating GCN, LSTM/Bi-LSTM, and attention mechanisms for improved accuracy, including weather data processing.
-
Updated
Aug 4, 2024 - Python
Repository for advanced traffic forecasting models integrating GCN, LSTM/Bi-LSTM, and attention mechanisms for improved accuracy, including weather data processing.
LibCity: An Open Library for Urban Spatial-temporal Data Mining
[Neural Networks] RGDAN: A random graph diffusion attention network for traffic prediction
Official repo for the following paper: Traffic Forecasting on New Roads Unseen in the Training Data Using Spatial Contrastive Pre-Training (SCPT) (ECML PKDD DAMI '23)
[CIKM'2023] "STExplainer: Explainable Spatio-Temporal Graph Neural Networks"
[CIKM'2023] "CL4ST: Spatio-Temporal Meta Contrastive Learning"
[Pattern Recognition] Decomposition Dynamic Graph Conolutional Recurrent Network for Traffic Forecasting
M-LibCity: An Open Source Library for Urban Spatio-temporal Prediction Models Based on MindSpore
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.
Dijkstra adjacency distance matrices were calculated for 40 cities from traffic sensor locations provide by UTD19 https://utd19.ethz.ch/.
Fast Temporal Wavelet Graph Neural Networks
[AAAI2023] A PyTorch implementation of PDFormer: Propagation Delay-aware Dynamic Long-range Transformer for Traffic Flow Prediction.
ST-MAN: Spatio-Temporal Multimodal Attention Network for Traffic Prediction (KSEM 2023)
a novel transformer-based architecture named CSTTN for traffic prediction
Recipe Site Traffic Prediction: Utilising machine learning to forecast high traffic recipes on a recipe website. Improve user engagement and traffic with data-driven decisions.
Traffic data processing tools in LibCity
Source codes of CIKM2022 Full Paper "Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities"
Master Thesis at ETH Zurich, 2022.
Learning Multiaspect Traffic Couplings by Multirelational Graph Attention Networks for Traffic Prediction
ALL is a pre-training method based on Federated Meta-Learning and Reinforcement Learning, which is used to address the small-sample issues of parking occupancy prediction.
Add a description, image, and links to the traffic-prediction topic page so that developers can more easily learn about it.
To associate your repository with the traffic-prediction topic, visit your repo's landing page and select "manage topics."