Tensor Recovery Based Non-Recurrent Traffic Congestion Recognition

Huachun Tan; Qin Li; Yuankai Wu; Bin Ran; Baodi Liu

doi:10.1061/9780784479292.054

Tensor Recovery Based Non-Recurrent Traffic Congestion Recognition

Huachun Tan
, Qin Li
, Yuankai Wu
, Bin Ran
, Baodi Liu

Advanced Research Institute of Multidisciplinary Science

Beijing Institute of Technology
Department of Civil and Environmental Engineering, University of Wisconsin-Madison
China University of Petroleum

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

3 Citations (Scopus)

Abstract

It is critical to detect and recognize non-recurrent traffic congestion (NRC), which brings unexpected delays to commuters, companies and traffic operators. In this paper, we propose a tensor recovery based non-recurrent traffic congestion recognition (TR-NRC) model to detect and recognize non-recurrent traffic congestion by decomposing the observed travel time tensor into a low-rank tensor and a sparse tensor. A tensor model can fully utilize the intrinsic multiple correlations of travel time data. The sparse tensor represents unexpected congestion. Values of sparse tensors reveal the distribution of unexpected delays compared to expected travel time. The recovered low-rank tensor structure expresses the distribution of general expected travel time as an auxiliary product, which was unattainable in the traditional detection methods. Experimental results show that compared to previous matrix recovery based methods, our proposed method can not only detect unexpected congestion, but can also recognize the congestion patterns more effectively.

Original language	English
Title of host publication	CICTP 2015 - Efficient, Safe, and Green Multimodal Transportation - Proceedings of the 15th COTA International Conference of Transportation Professionals
Editors	Xuedong Yan, Yu Zhang, Yafeng Yin
Publisher	American Society of Civil Engineers (ASCE)
Pages	591-603
Number of pages	13
ISBN (Electronic)	9780784479292
DOIs	https://doi.org/10.1061/9780784479292.054
Publication status	Published - 2015
Event	15th COTA International Conference of Transportation Professionals: Efficient, Safe, and Green Multimodal Transportation, CICTP 2015 - Beijing, China Duration: 24 Jul 2015 → 27 Jul 2015

Publication series

Name	CICTP 2015 - Efficient, Safe, and Green Multimodal Transportation - Proceedings of the 15th COTA International Conference of Transportation Professionals

Conference

Conference	15th COTA International Conference of Transportation Professionals: Efficient, Safe, and Green Multimodal Transportation, CICTP 2015
Country/Territory	China
City	Beijing
Period	24/07/15 → 27/07/15

UN SDGs

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

SDG 9 Industry, Innovation, and Infrastructure

Keywords

Lowrank tensor
No-recurrent traffic congestion recognition
Sparse tensor
Tensor recovery

Access to Document

10.1061/9780784479292.054

Cite this

Tan, H., Li, Q., Wu, Y., Ran, B., & Liu, B. (2015). Tensor Recovery Based Non-Recurrent Traffic Congestion Recognition. In X. Yan, Y. Zhang, & Y. Yin (Eds.), CICTP 2015 - Efficient, Safe, and Green Multimodal Transportation - Proceedings of the 15th COTA International Conference of Transportation Professionals (pp. 591-603). (CICTP 2015 - Efficient, Safe, and Green Multimodal Transportation - Proceedings of the 15th COTA International Conference of Transportation Professionals). American Society of Civil Engineers (ASCE). https://doi.org/10.1061/9780784479292.054

Tan, Huachun ; Li, Qin ; Wu, Yuankai et al. / Tensor Recovery Based Non-Recurrent Traffic Congestion Recognition. CICTP 2015 - Efficient, Safe, and Green Multimodal Transportation - Proceedings of the 15th COTA International Conference of Transportation Professionals. editor / Xuedong Yan ; Yu Zhang ; Yafeng Yin. American Society of Civil Engineers (ASCE), 2015. pp. 591-603 (CICTP 2015 - Efficient, Safe, and Green Multimodal Transportation - Proceedings of the 15th COTA International Conference of Transportation Professionals).

@inproceedings{677cff5ba4cb46f8a65e594125ba0d03,

title = "Tensor Recovery Based Non-Recurrent Traffic Congestion Recognition",

abstract = "It is critical to detect and recognize non-recurrent traffic congestion (NRC), which brings unexpected delays to commuters, companies and traffic operators. In this paper, we propose a tensor recovery based non-recurrent traffic congestion recognition (TR-NRC) model to detect and recognize non-recurrent traffic congestion by decomposing the observed travel time tensor into a low-rank tensor and a sparse tensor. A tensor model can fully utilize the intrinsic multiple correlations of travel time data. The sparse tensor represents unexpected congestion. Values of sparse tensors reveal the distribution of unexpected delays compared to expected travel time. The recovered low-rank tensor structure expresses the distribution of general expected travel time as an auxiliary product, which was unattainable in the traditional detection methods. Experimental results show that compared to previous matrix recovery based methods, our proposed method can not only detect unexpected congestion, but can also recognize the congestion patterns more effectively.",

keywords = "Lowrank tensor, No-recurrent traffic congestion recognition, Sparse tensor, Tensor recovery",

author = "Huachun Tan and Qin Li and Yuankai Wu and Bin Ran and Baodi Liu",

note = "Publisher Copyright: {\textcopyright} ASCE.; 15th COTA International Conference of Transportation Professionals: Efficient, Safe, and Green Multimodal Transportation, CICTP 2015 ; Conference date: 24-07-2015 Through 27-07-2015",

year = "2015",

doi = "10.1061/9780784479292.054",

language = "English",

series = "CICTP 2015 - Efficient, Safe, and Green Multimodal Transportation - Proceedings of the 15th COTA International Conference of Transportation Professionals",

publisher = "American Society of Civil Engineers (ASCE)",

pages = "591--603",

editor = "Xuedong Yan and Yu Zhang and Yafeng Yin",

booktitle = "CICTP 2015 - Efficient, Safe, and Green Multimodal Transportation - Proceedings of the 15th COTA International Conference of Transportation Professionals",

address = "United States",

}

Tan, H, Li, Q, Wu, Y, Ran, B & Liu, B 2015, Tensor Recovery Based Non-Recurrent Traffic Congestion Recognition. in X Yan, Y Zhang & Y Yin (eds), CICTP 2015 - Efficient, Safe, and Green Multimodal Transportation - Proceedings of the 15th COTA International Conference of Transportation Professionals. CICTP 2015 - Efficient, Safe, and Green Multimodal Transportation - Proceedings of the 15th COTA International Conference of Transportation Professionals, American Society of Civil Engineers (ASCE), pp. 591-603, 15th COTA International Conference of Transportation Professionals: Efficient, Safe, and Green Multimodal Transportation, CICTP 2015, Beijing, China, 24/07/15. https://doi.org/10.1061/9780784479292.054

Tensor Recovery Based Non-Recurrent Traffic Congestion Recognition. / Tan, Huachun; Li, Qin; Wu, Yuankai et al.
CICTP 2015 - Efficient, Safe, and Green Multimodal Transportation - Proceedings of the 15th COTA International Conference of Transportation Professionals. ed. / Xuedong Yan; Yu Zhang; Yafeng Yin. American Society of Civil Engineers (ASCE), 2015. p. 591-603 (CICTP 2015 - Efficient, Safe, and Green Multimodal Transportation - Proceedings of the 15th COTA International Conference of Transportation Professionals).

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

TY - GEN

T1 - Tensor Recovery Based Non-Recurrent Traffic Congestion Recognition

AU - Tan, Huachun

AU - Li, Qin

AU - Wu, Yuankai

AU - Ran, Bin

AU - Liu, Baodi

N1 - Publisher Copyright: © ASCE.

PY - 2015

Y1 - 2015

N2 - It is critical to detect and recognize non-recurrent traffic congestion (NRC), which brings unexpected delays to commuters, companies and traffic operators. In this paper, we propose a tensor recovery based non-recurrent traffic congestion recognition (TR-NRC) model to detect and recognize non-recurrent traffic congestion by decomposing the observed travel time tensor into a low-rank tensor and a sparse tensor. A tensor model can fully utilize the intrinsic multiple correlations of travel time data. The sparse tensor represents unexpected congestion. Values of sparse tensors reveal the distribution of unexpected delays compared to expected travel time. The recovered low-rank tensor structure expresses the distribution of general expected travel time as an auxiliary product, which was unattainable in the traditional detection methods. Experimental results show that compared to previous matrix recovery based methods, our proposed method can not only detect unexpected congestion, but can also recognize the congestion patterns more effectively.

AB - It is critical to detect and recognize non-recurrent traffic congestion (NRC), which brings unexpected delays to commuters, companies and traffic operators. In this paper, we propose a tensor recovery based non-recurrent traffic congestion recognition (TR-NRC) model to detect and recognize non-recurrent traffic congestion by decomposing the observed travel time tensor into a low-rank tensor and a sparse tensor. A tensor model can fully utilize the intrinsic multiple correlations of travel time data. The sparse tensor represents unexpected congestion. Values of sparse tensors reveal the distribution of unexpected delays compared to expected travel time. The recovered low-rank tensor structure expresses the distribution of general expected travel time as an auxiliary product, which was unattainable in the traditional detection methods. Experimental results show that compared to previous matrix recovery based methods, our proposed method can not only detect unexpected congestion, but can also recognize the congestion patterns more effectively.

KW - Lowrank tensor

KW - No-recurrent traffic congestion recognition

KW - Sparse tensor

KW - Tensor recovery

UR - https://www.scopus.com/pages/publications/84953302751

U2 - 10.1061/9780784479292.054

DO - 10.1061/9780784479292.054

M3 - Conference contribution

AN - SCOPUS:84953302751

T3 - CICTP 2015 - Efficient, Safe, and Green Multimodal Transportation - Proceedings of the 15th COTA International Conference of Transportation Professionals

SP - 591

EP - 603

BT - CICTP 2015 - Efficient, Safe, and Green Multimodal Transportation - Proceedings of the 15th COTA International Conference of Transportation Professionals

A2 - Yan, Xuedong

A2 - Zhang, Yu

A2 - Yin, Yafeng

PB - American Society of Civil Engineers (ASCE)

T2 - 15th COTA International Conference of Transportation Professionals: Efficient, Safe, and Green Multimodal Transportation, CICTP 2015

Y2 - 24 July 2015 through 27 July 2015

ER -

Tan H, Li Q, Wu Y, Ran B, Liu B. Tensor Recovery Based Non-Recurrent Traffic Congestion Recognition. In Yan X, Zhang Y, Yin Y, editors, CICTP 2015 - Efficient, Safe, and Green Multimodal Transportation - Proceedings of the 15th COTA International Conference of Transportation Professionals. American Society of Civil Engineers (ASCE). 2015. p. 591-603. (CICTP 2015 - Efficient, Safe, and Green Multimodal Transportation - Proceedings of the 15th COTA International Conference of Transportation Professionals). doi: 10.1061/9780784479292.054

Tensor Recovery Based Non-Recurrent Traffic Congestion Recognition

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this