ESTIMATION OF NETWORK-WIDE TRAFFIC SPEEDS AND FLOWS WITH HETEROGENEOUS DATA

Shaojie Liu; Mei Lam Tam; William H.K. Lam; Wei Ma; H. W. Ho; Hao Fu

ESTIMATION OF NETWORK-WIDE TRAFFIC SPEEDS AND FLOWS WITH HETEROGENEOUS DATA

Shaojie Liu, Mei Lam Tam, William H.K. Lam, Wei Ma, H. W. Ho, Hao Fu

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

Abstract

This paper proposes a model-based data-driven approach for simultaneously estimating network-wide traffic speeds and flows. In the proposed model, heterogeneous traffic data from multiple types of traffic detectors (point detectors and automatic vehicle identification detectors) on observed links are used. Fundamental diagrams of link speeds and flows are also considered. The spatial variance and covariance of link speeds and flows are incorporated into the proposed model to estimate the traffic speeds and flows on unobserved links (i.e., the links without traffic detectors) within the entire study network. The proposed model is formulated as a Kullback- Leibler (KL) divergence-based optimization problem that minimizes the KL divergence between the probability density functions of the observed and estimated link densities. A numerical example is presented to demonstrate the applications of the proposed model.

Original language	English
Title of host publication	Proceedings of the 26th International Conference of Hong Kong Society for Transportation Studies, HKSTS 2022
Editors	Sisi Jian, Sen Li, Hong K. Lo
Publisher	Hong Kong Society for Transportation Studies Limited
Pages	224-230
Number of pages	7
ISBN (Electronic)	9789881581402
Publication status	Published - 2022
Event	26th International Conference of Hong Kong Society for Transportation Studies, HKSTS 2022 - Hong Kong, Hong Kong Duration: 12 Dec 2022 → 13 Dec 2022

Publication series

Name	Proceedings of the 26th International Conference of Hong Kong Society for Transportation Studies, HKSTS 2022

Conference

Conference	26th International Conference of Hong Kong Society for Transportation Studies, HKSTS 2022
Country/Territory	Hong Kong
City	Hong Kong
Period	12/12/22 → 13/12/22

Keywords

fundamental diagrams
KL divergence
Network-wide traffic speed-flow estimation
spatial variance and covariance

ASJC Scopus subject areas

Transportation

Cite this

Liu, S., Tam, M. L., Lam, W. H. K., Ma, W., Ho, H. W., & Fu, H. (2022). ESTIMATION OF NETWORK-WIDE TRAFFIC SPEEDS AND FLOWS WITH HETEROGENEOUS DATA. In S. Jian, S. Li, & H. K. Lo (Eds.), Proceedings of the 26th International Conference of Hong Kong Society for Transportation Studies, HKSTS 2022 (pp. 224-230). (Proceedings of the 26th International Conference of Hong Kong Society for Transportation Studies, HKSTS 2022). Hong Kong Society for Transportation Studies Limited.

Liu, Shaojie ; Tam, Mei Lam ; Lam, William H.K. et al. / ESTIMATION OF NETWORK-WIDE TRAFFIC SPEEDS AND FLOWS WITH HETEROGENEOUS DATA. Proceedings of the 26th International Conference of Hong Kong Society for Transportation Studies, HKSTS 2022. editor / Sisi Jian ; Sen Li ; Hong K. Lo. Hong Kong Society for Transportation Studies Limited, 2022. pp. 224-230 (Proceedings of the 26th International Conference of Hong Kong Society for Transportation Studies, HKSTS 2022).

@inproceedings{2d259e09ee8041a083d86d18e62aec1f,

title = "ESTIMATION OF NETWORK-WIDE TRAFFIC SPEEDS AND FLOWS WITH HETEROGENEOUS DATA",

abstract = "This paper proposes a model-based data-driven approach for simultaneously estimating network-wide traffic speeds and flows. In the proposed model, heterogeneous traffic data from multiple types of traffic detectors (point detectors and automatic vehicle identification detectors) on observed links are used. Fundamental diagrams of link speeds and flows are also considered. The spatial variance and covariance of link speeds and flows are incorporated into the proposed model to estimate the traffic speeds and flows on unobserved links (i.e., the links without traffic detectors) within the entire study network. The proposed model is formulated as a Kullback- Leibler (KL) divergence-based optimization problem that minimizes the KL divergence between the probability density functions of the observed and estimated link densities. A numerical example is presented to demonstrate the applications of the proposed model.",

keywords = "fundamental diagrams, KL divergence, Network-wide traffic speed-flow estimation, spatial variance and covariance",

author = "Shaojie Liu and Tam, {Mei Lam} and Lam, {William H.K.} and Wei Ma and Ho, {H. W.} and Hao Fu",

note = "Publisher Copyright: {\textcopyright} 2022 Proceedings of the 26th International Conference of Hong Kong Society for Transportation Studies, HKSTS 2022. All Rights reserved.; 26th International Conference of Hong Kong Society for Transportation Studies, HKSTS 2022 ; Conference date: 12-12-2022 Through 13-12-2022",

year = "2022",

language = "English",

series = "Proceedings of the 26th International Conference of Hong Kong Society for Transportation Studies, HKSTS 2022",

publisher = "Hong Kong Society for Transportation Studies Limited",

pages = "224--230",

editor = "Sisi Jian and Sen Li and Lo, {Hong K.}",

booktitle = "Proceedings of the 26th International Conference of Hong Kong Society for Transportation Studies, HKSTS 2022",

}

Liu, S, Tam, ML, Lam, WHK, Ma, W, Ho, HW & Fu, H 2022, ESTIMATION OF NETWORK-WIDE TRAFFIC SPEEDS AND FLOWS WITH HETEROGENEOUS DATA. in S Jian, S Li & HK Lo (eds), Proceedings of the 26th International Conference of Hong Kong Society for Transportation Studies, HKSTS 2022. Proceedings of the 26th International Conference of Hong Kong Society for Transportation Studies, HKSTS 2022, Hong Kong Society for Transportation Studies Limited, pp. 224-230, 26th International Conference of Hong Kong Society for Transportation Studies, HKSTS 2022, Hong Kong, Hong Kong, 12/12/22.

ESTIMATION OF NETWORK-WIDE TRAFFIC SPEEDS AND FLOWS WITH HETEROGENEOUS DATA. / Liu, Shaojie; Tam, Mei Lam; Lam, William H.K. et al.
Proceedings of the 26th International Conference of Hong Kong Society for Transportation Studies, HKSTS 2022. ed. / Sisi Jian; Sen Li; Hong K. Lo. Hong Kong Society for Transportation Studies Limited, 2022. p. 224-230 (Proceedings of the 26th International Conference of Hong Kong Society for Transportation Studies, HKSTS 2022).

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - ESTIMATION OF NETWORK-WIDE TRAFFIC SPEEDS AND FLOWS WITH HETEROGENEOUS DATA

AU - Liu, Shaojie

AU - Tam, Mei Lam

AU - Lam, William H.K.

AU - Ma, Wei

AU - Ho, H. W.

AU - Fu, Hao

PY - 2022

Y1 - 2022

N2 - This paper proposes a model-based data-driven approach for simultaneously estimating network-wide traffic speeds and flows. In the proposed model, heterogeneous traffic data from multiple types of traffic detectors (point detectors and automatic vehicle identification detectors) on observed links are used. Fundamental diagrams of link speeds and flows are also considered. The spatial variance and covariance of link speeds and flows are incorporated into the proposed model to estimate the traffic speeds and flows on unobserved links (i.e., the links without traffic detectors) within the entire study network. The proposed model is formulated as a Kullback- Leibler (KL) divergence-based optimization problem that minimizes the KL divergence between the probability density functions of the observed and estimated link densities. A numerical example is presented to demonstrate the applications of the proposed model.

AB - This paper proposes a model-based data-driven approach for simultaneously estimating network-wide traffic speeds and flows. In the proposed model, heterogeneous traffic data from multiple types of traffic detectors (point detectors and automatic vehicle identification detectors) on observed links are used. Fundamental diagrams of link speeds and flows are also considered. The spatial variance and covariance of link speeds and flows are incorporated into the proposed model to estimate the traffic speeds and flows on unobserved links (i.e., the links without traffic detectors) within the entire study network. The proposed model is formulated as a Kullback- Leibler (KL) divergence-based optimization problem that minimizes the KL divergence between the probability density functions of the observed and estimated link densities. A numerical example is presented to demonstrate the applications of the proposed model.

KW - fundamental diagrams

KW - KL divergence

KW - Network-wide traffic speed-flow estimation

KW - spatial variance and covariance

UR - http://www.scopus.com/inward/record.url?scp=85175401482&partnerID=8YFLogxK

M3 - Conference article published in proceeding or book

AN - SCOPUS:85175401482

T3 - Proceedings of the 26th International Conference of Hong Kong Society for Transportation Studies, HKSTS 2022

SP - 224

EP - 230

BT - Proceedings of the 26th International Conference of Hong Kong Society for Transportation Studies, HKSTS 2022

A2 - Jian, Sisi

A2 - Li, Sen

A2 - Lo, Hong K.

PB - Hong Kong Society for Transportation Studies Limited

T2 - 26th International Conference of Hong Kong Society for Transportation Studies, HKSTS 2022

Y2 - 12 December 2022 through 13 December 2022

ER -

Liu S, Tam ML, Lam WHK, Ma W, Ho HW, Fu H. ESTIMATION OF NETWORK-WIDE TRAFFIC SPEEDS AND FLOWS WITH HETEROGENEOUS DATA. In Jian S, Li S, Lo HK, editors, Proceedings of the 26th International Conference of Hong Kong Society for Transportation Studies, HKSTS 2022. Hong Kong Society for Transportation Studies Limited. 2022. p. 224-230. (Proceedings of the 26th International Conference of Hong Kong Society for Transportation Studies, HKSTS 2022).

ESTIMATION OF NETWORK-WIDE TRAFFIC SPEEDS AND FLOWS WITH HETEROGENEOUS DATA

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this