Real-time multi-sensor multi-source network data fusion using dynamic traffic assignment models

E. Huang; C. Antoniou; Y. Wen; M. Ben-Akiva; J. Lopes; J. Bento

doi:10.1109/ITSC.2009.5309859

Real-time multi-sensor multi-source network data fusion using dynamic traffic assignment models

E. Huang
, C. Antoniou
, Y. Wen
, M. Ben-Akiva
, J. Lopes
, J. Bento

Massachusetts Institute of Technology
Technical University of Lisbon

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

17 Scopus citations

Abstract

This paper presents a model-based data fusion framework that allows systematic fusing of multi-sensor multi-source traffic network data at real-time. Using simulation-based Dynamic Traffic Assignment (DTA) models, the framework seeks to minimize the inconsistencies between observed network data and the model estimates using a variant of the Hooke-Jeeves Pattern Search. An empirical validation is provided on the Brisa A5 Inter-City Motorway in the West coast of Portugal. The real-time network data provided by loop detectors, video cameras and toll counters is collected and fused within DynaMIT, a state-of-the-art DTA system. State estimation is first performed, yielding consistent approximation of the network condition. This is then followed by network state forecast, showing significantly improved Normalized Root Mean Square Error (RMSN) over alternative predictive systems that do not use real-time information to correct themselves.

Original language	English
Title of host publication	2009 12th International IEEE Conference on Intelligent Transportation Systems, ITSC '09
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	533-538
Number of pages	6
ISBN (Print)	9781424455218
DOIs	https://doi.org/10.1109/ITSC.2009.5309859
State	Published - 2009
Externally published	Yes
Event	12th International IEEE Conference on Intelligent Transportation Systems, ITSC 2009 - St. Louis, MO, United States Duration: 4 Oct 2009 → 7 Oct 2009

Publication series

Name	IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC
ISSN (Print)	2153-0009
ISSN (Electronic)	2153-0017

Conference

Conference	12th International IEEE Conference on Intelligent Transportation Systems, ITSC 2009
Country/Territory	United States
City	St. Louis, MO
Period	4/10/09 → 7/10/09

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 11 Sustainable Cities and Communities

Keywords

Multi-sensor fusion
Simulation and modeling
Traffic state analysis and prediction
Travel information and guidance

Access to Document

10.1109/ITSC.2009.5309859

Cite this

Huang, E., Antoniou, C., Wen, Y., Ben-Akiva, M., Lopes, J., & Bento, J. (2009). Real-time multi-sensor multi-source network data fusion using dynamic traffic assignment models. In 2009 12th International IEEE Conference on Intelligent Transportation Systems, ITSC '09 (pp. 533-538). Article 5309859 (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ITSC.2009.5309859

Huang, E. ; Antoniou, C. ; Wen, Y. et al. / Real-time multi-sensor multi-source network data fusion using dynamic traffic assignment models. 2009 12th International IEEE Conference on Intelligent Transportation Systems, ITSC '09. Institute of Electrical and Electronics Engineers Inc., 2009. pp. 533-538 (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC).

@inproceedings{0424240f5d694bfa85b40ebc0cd7c6c0,

title = "Real-time multi-sensor multi-source network data fusion using dynamic traffic assignment models",

abstract = "This paper presents a model-based data fusion framework that allows systematic fusing of multi-sensor multi-source traffic network data at real-time. Using simulation-based Dynamic Traffic Assignment (DTA) models, the framework seeks to minimize the inconsistencies between observed network data and the model estimates using a variant of the Hooke-Jeeves Pattern Search. An empirical validation is provided on the Brisa A5 Inter-City Motorway in the West coast of Portugal. The real-time network data provided by loop detectors, video cameras and toll counters is collected and fused within DynaMIT, a state-of-the-art DTA system. State estimation is first performed, yielding consistent approximation of the network condition. This is then followed by network state forecast, showing significantly improved Normalized Root Mean Square Error (RMSN) over alternative predictive systems that do not use real-time information to correct themselves.",

keywords = "Multi-sensor fusion, Simulation and modeling, Traffic state analysis and prediction, Travel information and guidance",

author = "E. Huang and C. Antoniou and Y. Wen and M. Ben-Akiva and J. Lopes and J. Bento",

year = "2009",

doi = "10.1109/ITSC.2009.5309859",

language = "English",

isbn = "9781424455218",

series = "IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "533--538",

booktitle = "2009 12th International IEEE Conference on Intelligent Transportation Systems, ITSC '09",

note = "12th International IEEE Conference on Intelligent Transportation Systems, ITSC 2009 ; Conference date: 04-10-2009 Through 07-10-2009",

}

Huang, E, Antoniou, C, Wen, Y, Ben-Akiva, M, Lopes, J & Bento, J 2009, Real-time multi-sensor multi-source network data fusion using dynamic traffic assignment models. in 2009 12th International IEEE Conference on Intelligent Transportation Systems, ITSC '09., 5309859, IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, Institute of Electrical and Electronics Engineers Inc., pp. 533-538, 12th International IEEE Conference on Intelligent Transportation Systems, ITSC 2009, St. Louis, MO, United States, 4/10/09. https://doi.org/10.1109/ITSC.2009.5309859

Real-time multi-sensor multi-source network data fusion using dynamic traffic assignment models. / Huang, E.; Antoniou, C.; Wen, Y. et al.
2009 12th International IEEE Conference on Intelligent Transportation Systems, ITSC '09. Institute of Electrical and Electronics Engineers Inc., 2009. p. 533-538 5309859 (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Real-time multi-sensor multi-source network data fusion using dynamic traffic assignment models

AU - Huang, E.

AU - Antoniou, C.

AU - Wen, Y.

AU - Ben-Akiva, M.

AU - Lopes, J.

AU - Bento, J.

PY - 2009

Y1 - 2009

N2 - This paper presents a model-based data fusion framework that allows systematic fusing of multi-sensor multi-source traffic network data at real-time. Using simulation-based Dynamic Traffic Assignment (DTA) models, the framework seeks to minimize the inconsistencies between observed network data and the model estimates using a variant of the Hooke-Jeeves Pattern Search. An empirical validation is provided on the Brisa A5 Inter-City Motorway in the West coast of Portugal. The real-time network data provided by loop detectors, video cameras and toll counters is collected and fused within DynaMIT, a state-of-the-art DTA system. State estimation is first performed, yielding consistent approximation of the network condition. This is then followed by network state forecast, showing significantly improved Normalized Root Mean Square Error (RMSN) over alternative predictive systems that do not use real-time information to correct themselves.

AB - This paper presents a model-based data fusion framework that allows systematic fusing of multi-sensor multi-source traffic network data at real-time. Using simulation-based Dynamic Traffic Assignment (DTA) models, the framework seeks to minimize the inconsistencies between observed network data and the model estimates using a variant of the Hooke-Jeeves Pattern Search. An empirical validation is provided on the Brisa A5 Inter-City Motorway in the West coast of Portugal. The real-time network data provided by loop detectors, video cameras and toll counters is collected and fused within DynaMIT, a state-of-the-art DTA system. State estimation is first performed, yielding consistent approximation of the network condition. This is then followed by network state forecast, showing significantly improved Normalized Root Mean Square Error (RMSN) over alternative predictive systems that do not use real-time information to correct themselves.

KW - Multi-sensor fusion

KW - Simulation and modeling

KW - Traffic state analysis and prediction

KW - Travel information and guidance

UR - https://www.scopus.com/pages/publications/72449196756

U2 - 10.1109/ITSC.2009.5309859

DO - 10.1109/ITSC.2009.5309859

M3 - Conference contribution

AN - SCOPUS:72449196756

SN - 9781424455218

T3 - IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC

SP - 533

EP - 538

BT - 2009 12th International IEEE Conference on Intelligent Transportation Systems, ITSC '09

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 12th International IEEE Conference on Intelligent Transportation Systems, ITSC 2009

Y2 - 4 October 2009 through 7 October 2009

ER -

Huang E, Antoniou C, Wen Y, Ben-Akiva M, Lopes J, Bento J. Real-time multi-sensor multi-source network data fusion using dynamic traffic assignment models. In 2009 12th International IEEE Conference on Intelligent Transportation Systems, ITSC '09. Institute of Electrical and Electronics Engineers Inc. 2009. p. 533-538. 5309859. (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC). doi: 10.1109/ITSC.2009.5309859

Real-time multi-sensor multi-source network data fusion using dynamic traffic assignment models

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this