Dynamic Graph Convolutional LSTM application for traffic flow estimation from error-prone measurements: results and transferability analysis - Télécom Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Dynamic Graph Convolutional LSTM application for traffic flow estimation from error-prone measurements: results and transferability analysis

Résumé

The technological advances in the transportation and automotive industry led to the use of new types of sensing systems more cost-effective and adapted to large-scale dense deployment. Those sensing techniques allow continuously gathering traffic measurements times series in different geospatial locations. The accuracy of the obtained raw measurements is often hindered by different factors related to the sensing environment and the sensing process itself and thus fail to capture the short-term traffic variations crucial for real-time traffic monitoring. In this paper, we propose the DGC-LSTM model for area-wide traffic estimation from error-prone measurements time series. The backbone of the DGC-LSTM model is a graph convolutional Long Short Term Memory model with a dynamic adjacency matrix. The adjacency matrix is learned and optimized during the model training. The adjacency matrix values are estimated from the set of contextual features that impact the dynamicity of the dependencies in both the spatial and temporal dimensions. Experiments on a realistic synthetic labelled Bluetooth counts dataset is used for model evaluation. Lastly, we highlight the importance of transfer learning methods to improve the model applicability by ensuring model adaptation to the new deployment site while avoiding the extensive data-labelling effort.
Fichier non déposé

Dates et versions

hal-03559364 , version 1 (06-02-2022)

Identifiants

Citer

Stéphan Clémençon, Safa Boudabous, Houda Labiod, Julian Garbiso. Dynamic Graph Convolutional LSTM application for traffic flow estimation from error-prone measurements: results and transferability analysis. 2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA), Oct 2021, Porto, Portugal. pp.1-10, ⟨10.1109/DSAA53316.2021.9564245⟩. ⟨hal-03559364⟩
40 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More