Understanding Network Traffic States using Transfer Learning

Panchamy Krishnakumari; Alan Perotti; Viviana Pinto; Oded Cats; Hans van Lint

doi:10.1109/ITSC.2018.8569450

Understanding Network Traffic States using Transfer Learning

Panchamy Krishnakumari, Alan Perotti, Viviana Pinto, Oded Cats, Hans van Lint

Transport and Planning

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

11 Citations (Scopus)

82 Downloads (Pure)

Abstract

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.

Original language	English
Title of host publication	Proceedings of the 21st International Conference on Intelligent Transportation Systems (ITSC)
Subtitle of host publication	4-7 Nov. 2018, Maui, HI, USA
Editors	Wei-Bin Zhang, Alexandre Bayen, Javier Sanchez-Medina, Matthew Barth
Publisher	IEEE
Pages	1396-1401
ISBN (Electronic)	978-1-7281-0323-5
DOIs	https://doi.org/10.1109/ITSC.2018.8569450
Publication status	Published - 2018
Event	21st IEEE International Conference on Intelligent Transportation Systems, ITSC 2018 - Maui, United States Duration: 4 Nov 2018 → 7 Nov 2018 Conference number: 21 https://www.ieee-itsc2018.org/

Conference

Conference	21st IEEE International Conference on Intelligent Transportation Systems, ITSC 2018
Abbreviated title	ITSC 2018
Country/Territory	United States
City	Maui
Period	4/11/18 → 7/11/18
Internet address	https://www.ieee-itsc2018.org/

Bibliographical note

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.

Access to Document

10.1109/ITSC.2018.8569450

08569450Final published version, 843 KB

Cite this

Krishnakumari, P., Perotti, A., Pinto, V., Cats, O., & van Lint, H. (2018). Understanding Network Traffic States using Transfer Learning. In W.-B. Zhang, A. Bayen, J. Sanchez-Medina, & M. Barth (Eds.), Proceedings of the 21st International Conference on Intelligent Transportation Systems (ITSC) : 4-7 Nov. 2018, Maui, HI, USA (pp. 1396-1401). IEEE. https://doi.org/10.1109/ITSC.2018.8569450

@inproceedings{11103645f11044bf9d44516e49414627,

title = "Understanding Network Traffic States using Transfer Learning",

abstract = "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.",

author = "Panchamy Krishnakumari and Alan Perotti and Viviana Pinto and Oded Cats and {van Lint}, Hans",

note = "Green Open Access added to TU Delft Institutional Repository {\textquoteleft}You share, we take care!{\textquoteright} – 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.; 21st IEEE International Conference on Intelligent Transportation Systems, ITSC 2018, ITSC 2018 ; Conference date: 04-11-2018 Through 07-11-2018",

year = "2018",

doi = "10.1109/ITSC.2018.8569450",

language = "English",

pages = "1396--1401",

editor = "Wei-Bin Zhang and Alexandre Bayen and Javier Sanchez-Medina and Matthew Barth",

booktitle = "Proceedings of the 21st International Conference on Intelligent Transportation Systems (ITSC)",

publisher = "IEEE",

address = "United States",

url = "https://www.ieee-itsc2018.org/",

}

Krishnakumari, P, Perotti, A, Pinto, V, Cats, O & van Lint, H 2018, Understanding Network Traffic States using Transfer Learning. in W-B Zhang, A Bayen, J Sanchez-Medina & M Barth (eds), Proceedings of the 21st International Conference on Intelligent Transportation Systems (ITSC) : 4-7 Nov. 2018, Maui, HI, USA. IEEE, pp. 1396-1401, 21st IEEE International Conference on Intelligent Transportation Systems, ITSC 2018, Maui, United States, 4/11/18. https://doi.org/10.1109/ITSC.2018.8569450

Understanding Network Traffic States using Transfer Learning. / Krishnakumari, Panchamy; Perotti, Alan; Pinto, Viviana et al.
Proceedings of the 21st International Conference on Intelligent Transportation Systems (ITSC) : 4-7 Nov. 2018, Maui, HI, USA. ed. / Wei-Bin Zhang; Alexandre Bayen; Javier Sanchez-Medina; Matthew Barth. IEEE, 2018. p. 1396-1401.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Understanding Network Traffic States using Transfer Learning

AU - Krishnakumari, Panchamy

AU - Perotti, Alan

AU - Pinto, Viviana

AU - Cats, Oded

AU - van Lint, Hans

N1 - Conference code: 21

PY - 2018

Y1 - 2018

N2 - 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.

AB - 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.

U2 - 10.1109/ITSC.2018.8569450

DO - 10.1109/ITSC.2018.8569450

M3 - Conference contribution

SP - 1396

EP - 1401

BT - Proceedings of the 21st International Conference on Intelligent Transportation Systems (ITSC)

A2 - Zhang, Wei-Bin

A2 - Bayen, Alexandre

A2 - Sanchez-Medina, Javier

A2 - Barth, Matthew

PB - IEEE

T2 - 21st IEEE International Conference on Intelligent Transportation Systems, ITSC 2018

Y2 - 4 November 2018 through 7 November 2018

ER -

Understanding Network Traffic States using Transfer Learning

Abstract

Conference

Bibliographical note

Access to Document

Fingerprint

Cite this