STLP-OD: Spatial and Temporal Label Propagation for Traffic Outlier Detection

Juhua Pu; Yue Wang; Xinran Liu; Xiangliang Zhang

doi:10.1109/ACCESS.2019.2916853

STLP-OD: Spatial and Temporal Label Propagation for Traffic Outlier Detection

Juhua Pu, Yue Wang, Xinran Liu, Xiangliang Zhang

Research output: Contribution to journal › Article › peer-review

10 Scopus citations

Abstract

This paper focuses on the detection of non-recurrent traffic anomaly caused by unexpected or transient incidents, such as traffic accidents, celebrations, and disasters. Comparing to existing approaches, it considers the spatial and temporal propagation of traffic anomalies from one road to other neighbor roads by proposing an STLP-OD framework. The experimental results on a real data set show that the proposed approach can improve the accuracy of traffic outlier detection baselines significantly.

Original language	English (US)
Pages (from-to)	63036-63044
Number of pages	9
Journal	IEEE Access
Volume	7
DOIs	https://doi.org/10.1109/ACCESS.2019.2916853
State	Published - 2019

Bibliographical note

KAUST Repository Item: Exported on 2020-10-01
Acknowledgements: This work was supported in part by the National Key Research and Development Program of China under Grant 2017YFB1002000,
Science Technology and Innovation Commission of Shenzhen Municipality JCYJ20180307123659504, and the State Key Laboratory of
Software Development Environment.

UN SDGs

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

Access to Document

10.1109/ACCESS.2019.2916853

https://repository.kaust.edu.sa/bitstream/10754/655896/1/08715411.pdf

Cite this

@article{5aef441dd0de43d2be7bf129af826d07,

title = "STLP-OD: Spatial and Temporal Label Propagation for Traffic Outlier Detection",

abstract = "This paper focuses on the detection of non-recurrent traffic anomaly caused by unexpected or transient incidents, such as traffic accidents, celebrations, and disasters. Comparing to existing approaches, it considers the spatial and temporal propagation of traffic anomalies from one road to other neighbor roads by proposing an STLP-OD framework. The experimental results on a real data set show that the proposed approach can improve the accuracy of traffic outlier detection baselines significantly.",

author = "Juhua Pu and Yue Wang and Xinran Liu and Xiangliang Zhang",

note = "KAUST Repository Item: Exported on 2020-10-01 Acknowledgements: This work was supported in part by the National Key Research and Development Program of China under Grant 2017YFB1002000, Science Technology and Innovation Commission of Shenzhen Municipality JCYJ20180307123659504, and the State Key Laboratory of Software Development Environment.",

year = "2019",

doi = "10.1109/ACCESS.2019.2916853",

language = "English (US)",

volume = "7",

pages = "63036--63044",

journal = "IEEE Access",

issn = "2169-3536",

publisher = "Institute of Electrical and Electronics Engineers",

}

TY - JOUR

T1 - STLP-OD: Spatial and Temporal Label Propagation for Traffic Outlier Detection

AU - Pu, Juhua

AU - Wang, Yue

AU - Liu, Xinran

AU - Zhang, Xiangliang

N1 - KAUST Repository Item: Exported on 2020-10-01 Acknowledgements: This work was supported in part by the National Key Research and Development Program of China under Grant 2017YFB1002000, Science Technology and Innovation Commission of Shenzhen Municipality JCYJ20180307123659504, and the State Key Laboratory of Software Development Environment.

PY - 2019

Y1 - 2019

N2 - This paper focuses on the detection of non-recurrent traffic anomaly caused by unexpected or transient incidents, such as traffic accidents, celebrations, and disasters. Comparing to existing approaches, it considers the spatial and temporal propagation of traffic anomalies from one road to other neighbor roads by proposing an STLP-OD framework. The experimental results on a real data set show that the proposed approach can improve the accuracy of traffic outlier detection baselines significantly.

AB - This paper focuses on the detection of non-recurrent traffic anomaly caused by unexpected or transient incidents, such as traffic accidents, celebrations, and disasters. Comparing to existing approaches, it considers the spatial and temporal propagation of traffic anomalies from one road to other neighbor roads by proposing an STLP-OD framework. The experimental results on a real data set show that the proposed approach can improve the accuracy of traffic outlier detection baselines significantly.

UR - http://hdl.handle.net/10754/655896

UR - https://ieeexplore.ieee.org/document/8715411/

UR - http://www.scopus.com/inward/record.url?scp=85066454040&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2019.2916853

DO - 10.1109/ACCESS.2019.2916853

M3 - Article

SN - 2169-3536

VL - 7

SP - 63036

EP - 63044

JO - IEEE Access

JF - IEEE Access

ER -

STLP-OD: Spatial and Temporal Label Propagation for Traffic Outlier Detection

Abstract

Bibliographical note

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this