Spatio-temporal clustering for non-recurrent traffic congestion detection on urban road networks

Anbaroğlu, Berk; Heydecker, Benjamin; Cheng, Tao

doi:10.1016/j.trc.2014.08.002

Cited by 125 publications

(72 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous researches highlight that the major source of travel time variability is NRC events (Noland and Polak 2002). Consequently, understanding how much of the total congestion is due to NRC has been studied thoroughly (Chow et al 2014;Dowling et al 2004;Skabardonis, Varaiya, and Petty 2003); however, research on detecting NRC events has only recently gained importance (Anbaroglu, Heydecker, and Cheng 2014).…”

Section: Introductionmentioning

confidence: 99%

Non-recurrent traffic congestion detection on heterogeneous urban road networks

Anbaroğlu

Cheng

Heydecker

2015

Transportmetrica A: Transport Science

Self Cite

View full text Add to dashboard Cite

This paper proposes two novel methods for non-recurrent congestion (NRC) event detection on heterogeneous urban road networks based on link journey time (LJT) estimates. Heterogeneity exists on urban road networks in two main aspects: variation in link lengths and data quality. The proposed NRC detection methods are referred to as percentile-based NRC detection and space-time scan statistics (STSS) based NRC detection. Both of these methods capture the heterogeneity of an urban road network by modelling the LJTs with a lognormal distribution. Empirical analyses are conducted on London's urban road network consisting of 424 links for the 20 weekdays of October 2010. Various parameter settings are tested for both of the methods, and the results favour STSS-based NRC detection method over the percentile-based NRC detection method. Link-based analyses demonstrate the effectiveness of the proposed methods in capturing the heterogeneity of the analysed road network.

show abstract

Section: Introductionmentioning

confidence: 99%

Non-recurrent traffic congestion detection on heterogeneous urban road networks

Anbaroğlu

Cheng

Heydecker

2015

Transportmetrica A: Transport Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…On the other hand, STSS based NRC detection performs poorer with respect to the detection of high-confidence episodes. For London's urban road network, empirical analyses demonstrate that a high-confidence episode occurs whenever the estimated LJTs are at least 40% higher than their expected values for at least a minimum duration of 25 minutes (Anbaroglu et al, 2014). These outcomes adds further support to the analyses conducted for normal travel demand, that the STSS based NRC detection is more conservative in detecting NRCs compared to Percentile based NRC detection (Anbaroğlu et al, 2015).…”

Section: Resultsmentioning

confidence: 70%

How Travel Demand Affects Detection of Non-Recurrent Traffic Congestion on Urban Road Networks

Anbaroğlu

Heydecker

Cheng

2016

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Occurrence of non-recurrent traffic congestion hinders the economic activity of a city, as travellers could miss appointments or be late for work or important meetings. Similarly, for shippers, unexpected delays may disrupt just-in-time delivery and manufacturing processes, which could lose them payment. Consequently, research on non-recurrent congestion detection on urban road networks has recently gained attention. By analysing large amounts of traffic data collected on a daily basis, traffic operation centres can improve their methods to detect non-recurrent congestion rapidly and then revise their existing plans to mitigate its effects. Space-time clusters of high link journey time estimates correspond to non-recurrent congestion events. Existing research, however, has not considered the effect of travel demand on the effectiveness of non-recurrent congestion detection methods. Therefore, this paper investigates how travel demand affects detection of non-recurrent traffic congestion detection on urban road networks. Travel demand has been classified into three categories as low, normal and high. The experiments are carried out on London's urban road network, and the results demonstrate the necessity to adjust the relative importance of the component evaluation criteria depending on the travel demand level.

show abstract

“…They found that each incident type's EBT behavior followed specific patterns based on characteristics of the incidents. (Anbaroglu et al, 2014) designed a nonrecurrent congestion events detection methodology to accurately account for large urban corridor non-recurrent congestion. The authors developed a Link Journey Time measure, concluding that those at least 40% higher than expected were probably caused by non-recurring events.…”

Section: Literature Reviewmentioning

confidence: 99%

Development of Congestion Causal Pie Charts for Arterial Roadways

Soltani-Sobh¹,

Ostojic²,

Stevanović³

et al. 2017

IJTTE

View full text Add to dashboard Cite

Urban congestion is being increased by a rapid growth in travel demand and a limited ability to expand physical infrastructure. If transportation agencies could accurately quantify the impacts of various congestion causes, they would be able to prioritize their strategies more efficiently. The Federal Highway Administration developed a well-known congestion causal pie chart in 2004, but this development process did not have extensive access to field data. Recent advancements in both traffic measurement technologies and data-driven analysis are making it possible to quantify congestion impacts more accurately. However, an assessment of congestion causes on signalized arterials presents many challenges, due to complexity of the required data and the interaction of traffic demand and control. The objective of this study is to create congestion pie charts which demonstrate the proportion of average experienced delay components on arterial corridors. A multivariate linear regression model of observed delay is used to demonstrate contributing factors to arterial street congestion. The methodology is explained using a section of Broward Boulevard in Fort Lauderdale, FL. The findings from the model demonstrate that a considerable part of arterial congestion can be attributed to travel demands and intersection signals.

show abstract

Spatio-temporal clustering for non-recurrent traffic congestion detection on urban road networks

Cited by 125 publications

References 26 publications

Non-recurrent traffic congestion detection on heterogeneous urban road networks

Non-recurrent traffic congestion detection on heterogeneous urban road networks

How Travel Demand Affects Detection of Non-Recurrent Traffic Congestion on Urban Road Networks

Development of Congestion Causal Pie Charts for Arterial Roadways

Contact Info

Product

Resources

About