Understanding Network Traffic States using Transfer Learning

Understanding Network Traffic States using Transfer Learning

Krishnakumari, P.K. (TU Delft Transport and Planning)
Perotti, Alan (ISI Foundation)
Pinto, Viviana (aizoOn)
Cats, O. (TU Delft Transport and Planning)
van Lint, J.W.C. (TU Delft Transport and Planning)

Zhang, Wei-Bin (editor)
Bayen, Alexandre (editor)
Sanchez-Medina, Javier (editor)
Barth, Matthew (editor)

2018

Large-scale network traffic analysis is crucial for many transport applications, ranging from estimation and prediction to control and planning. One of the key issues is how to integrate spatial and temporal analyses efficiently. Deep Learning is gaining momentum as a go-to approach for artificial vision, and transfer learning approaches allow to exploit pretrained models and apply them to new domains. In this paper, we encode traffic states as images and use a pretrained deep convolutional neural network as a feature extractor. Experimental results show how the extracted feature vectors cluster naturally into meaningful network traffic states and illustrate how these network states can be used for traffic state prediction.

http://resolver.tudelft.nl/uuid:11103645-f110-44bf-9d44-516e49414627

https://doi.org/10.1109/ITSC.2018.8569450

IEEE

2019-06-10

978-1-7281-0323-5

Proceedings of the 21st International Conference on Intelligent Transportation Systems (ITSC): 4-7 Nov. 2018, Maui, HI, USA

21st IEEE International Conference on Intelligent Transportation Systems, ITSC 2018, 2018-11-04 → 2018-11-07, Maui, United States

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Institutional Repository

conference paper

© 2018 P.K. Krishnakumari, Alan Perotti, Viviana Pinto, O. Cats, J.W.C. van Lint