Detection of Incidents and Events in Urban Networks

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

46 Downloads (Pure)

Abstract

Although there is a large variation in traffic flow patterns, we can distinguish two main types: recurrent and non-recurrent patterns. A recurrent pattern repeats itself with a known period and is therefore predictable. An example is the rush hour peak, but also the peak in travel demand which is caused by a weekly event, like a professional football match. Non recurrent patterns are caused by single events and incidents. Although these are relatively rare, they often have a very negative impact on the traffic situation (e.g. Smith et al. 2003). An important issue for policy makers therefore has been to reduce these negative effects. Much effort has gone into the development of incident detection algorithms (e.g. Browne et al. 2005, Koppelman & Lin 1996) which form a crucial part of incident management. These algorithms use real-time measurements of volume, occupancy and/or speed to detect incidents. There are several types of detection algorithms. Some of them are based on neural networks (e.g. Liu et al. 2004, Ritchie & Cheu 1993). In other algorithms an incident is declared when the data fulfill certain pre-selected criteria. In time-serie algorithms for example an incident is detected when the measurements differ significantly from the predictions (e.g. Stephanedes et al. 1992, Dudek et al. 1974). With the McMaster algorithm different traffic situations (e.g. incidents) are distinguished based on the location of measurements in the occupancy – flow volume diagram (e.g. Hall et al. 1993). Finally, in decision structure algorithms incidents are detected when measurements exceed thresholds in a decision tree (e.g. Ash 1997, Payne & Tignor 1978). In The Netherlands a decision structure algorithm has been developed for the Dutch motorways which appears to be quite successful (Knibbe et al. 2005). Complementary, in this paper we introduce a prediction scheme for recurrent events and an incident detection algorithm based on data from a Dutch city. For our detection algorithm we only use volume data. In section 2 we describe the data and in section 3 we introduce our incident detection method.
Original languageUndefined
Title of host publicationProceedings of the 7th European Congress and Exhibition on Intelligent Transport Systems and Services, 4-6 June 2008, Geneva
Editors ITS
Place of PublicationBrussels, Belgium
PublisherErtico/ ITSinEuropa
Pages-
Number of pages10
Publication statusPublished - 4 Jun 2008
Event7th European Congress and Exhibition on Intelligent Transport Systems and Services, ITS 2008 - Geneva, Switzerland
Duration: 4 Jun 20086 Jun 2008
Conference number: 7

Publication series

Name
PublisherErtico/ ITSinEuropa

Conference

Conference7th European Congress and Exhibition on Intelligent Transport Systems and Services, ITS 2008
Abbreviated titleITS
CountrySwitzerland
CityGeneva
Period4/06/086/06/08

Keywords

  • IR-76962
  • METIS-249255

Cite this

Thomas, T., & van Berkum, E. C. (2008). Detection of Incidents and Events in Urban Networks. In ITS (Ed.), Proceedings of the 7th European Congress and Exhibition on Intelligent Transport Systems and Services, 4-6 June 2008, Geneva (pp. -). Brussels, Belgium: Ertico/ ITSinEuropa.
Thomas, Tom ; van Berkum, Eric C. / Detection of Incidents and Events in Urban Networks. Proceedings of the 7th European Congress and Exhibition on Intelligent Transport Systems and Services, 4-6 June 2008, Geneva. editor / ITS. Brussels, Belgium : Ertico/ ITSinEuropa, 2008. pp. -
@inproceedings{d87fcaa4870f45a589ff2287af095a43,
title = "Detection of Incidents and Events in Urban Networks",
abstract = "Although there is a large variation in traffic flow patterns, we can distinguish two main types: recurrent and non-recurrent patterns. A recurrent pattern repeats itself with a known period and is therefore predictable. An example is the rush hour peak, but also the peak in travel demand which is caused by a weekly event, like a professional football match. Non recurrent patterns are caused by single events and incidents. Although these are relatively rare, they often have a very negative impact on the traffic situation (e.g. Smith et al. 2003). An important issue for policy makers therefore has been to reduce these negative effects. Much effort has gone into the development of incident detection algorithms (e.g. Browne et al. 2005, Koppelman & Lin 1996) which form a crucial part of incident management. These algorithms use real-time measurements of volume, occupancy and/or speed to detect incidents. There are several types of detection algorithms. Some of them are based on neural networks (e.g. Liu et al. 2004, Ritchie & Cheu 1993). In other algorithms an incident is declared when the data fulfill certain pre-selected criteria. In time-serie algorithms for example an incident is detected when the measurements differ significantly from the predictions (e.g. Stephanedes et al. 1992, Dudek et al. 1974). With the McMaster algorithm different traffic situations (e.g. incidents) are distinguished based on the location of measurements in the occupancy – flow volume diagram (e.g. Hall et al. 1993). Finally, in decision structure algorithms incidents are detected when measurements exceed thresholds in a decision tree (e.g. Ash 1997, Payne & Tignor 1978). In The Netherlands a decision structure algorithm has been developed for the Dutch motorways which appears to be quite successful (Knibbe et al. 2005). Complementary, in this paper we introduce a prediction scheme for recurrent events and an incident detection algorithm based on data from a Dutch city. For our detection algorithm we only use volume data. In section 2 we describe the data and in section 3 we introduce our incident detection method.",
keywords = "IR-76962, METIS-249255",
author = "Tom Thomas and {van Berkum}, {Eric C.}",
note = "Paper 2734, 10 p. (CD ROM)",
year = "2008",
month = "6",
day = "4",
language = "Undefined",
publisher = "Ertico/ ITSinEuropa",
pages = "--",
editor = "ITS",
booktitle = "Proceedings of the 7th European Congress and Exhibition on Intelligent Transport Systems and Services, 4-6 June 2008, Geneva",

}

Thomas, T & van Berkum, EC 2008, Detection of Incidents and Events in Urban Networks. in ITS (ed.), Proceedings of the 7th European Congress and Exhibition on Intelligent Transport Systems and Services, 4-6 June 2008, Geneva. Ertico/ ITSinEuropa, Brussels, Belgium, pp. -, 7th European Congress and Exhibition on Intelligent Transport Systems and Services, ITS 2008, Geneva, Switzerland, 4/06/08.

Detection of Incidents and Events in Urban Networks. / Thomas, Tom; van Berkum, Eric C.

Proceedings of the 7th European Congress and Exhibition on Intelligent Transport Systems and Services, 4-6 June 2008, Geneva. ed. / ITS. Brussels, Belgium : Ertico/ ITSinEuropa, 2008. p. -.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Detection of Incidents and Events in Urban Networks

AU - Thomas, Tom

AU - van Berkum, Eric C.

N1 - Paper 2734, 10 p. (CD ROM)

PY - 2008/6/4

Y1 - 2008/6/4

N2 - Although there is a large variation in traffic flow patterns, we can distinguish two main types: recurrent and non-recurrent patterns. A recurrent pattern repeats itself with a known period and is therefore predictable. An example is the rush hour peak, but also the peak in travel demand which is caused by a weekly event, like a professional football match. Non recurrent patterns are caused by single events and incidents. Although these are relatively rare, they often have a very negative impact on the traffic situation (e.g. Smith et al. 2003). An important issue for policy makers therefore has been to reduce these negative effects. Much effort has gone into the development of incident detection algorithms (e.g. Browne et al. 2005, Koppelman & Lin 1996) which form a crucial part of incident management. These algorithms use real-time measurements of volume, occupancy and/or speed to detect incidents. There are several types of detection algorithms. Some of them are based on neural networks (e.g. Liu et al. 2004, Ritchie & Cheu 1993). In other algorithms an incident is declared when the data fulfill certain pre-selected criteria. In time-serie algorithms for example an incident is detected when the measurements differ significantly from the predictions (e.g. Stephanedes et al. 1992, Dudek et al. 1974). With the McMaster algorithm different traffic situations (e.g. incidents) are distinguished based on the location of measurements in the occupancy – flow volume diagram (e.g. Hall et al. 1993). Finally, in decision structure algorithms incidents are detected when measurements exceed thresholds in a decision tree (e.g. Ash 1997, Payne & Tignor 1978). In The Netherlands a decision structure algorithm has been developed for the Dutch motorways which appears to be quite successful (Knibbe et al. 2005). Complementary, in this paper we introduce a prediction scheme for recurrent events and an incident detection algorithm based on data from a Dutch city. For our detection algorithm we only use volume data. In section 2 we describe the data and in section 3 we introduce our incident detection method.

AB - Although there is a large variation in traffic flow patterns, we can distinguish two main types: recurrent and non-recurrent patterns. A recurrent pattern repeats itself with a known period and is therefore predictable. An example is the rush hour peak, but also the peak in travel demand which is caused by a weekly event, like a professional football match. Non recurrent patterns are caused by single events and incidents. Although these are relatively rare, they often have a very negative impact on the traffic situation (e.g. Smith et al. 2003). An important issue for policy makers therefore has been to reduce these negative effects. Much effort has gone into the development of incident detection algorithms (e.g. Browne et al. 2005, Koppelman & Lin 1996) which form a crucial part of incident management. These algorithms use real-time measurements of volume, occupancy and/or speed to detect incidents. There are several types of detection algorithms. Some of them are based on neural networks (e.g. Liu et al. 2004, Ritchie & Cheu 1993). In other algorithms an incident is declared when the data fulfill certain pre-selected criteria. In time-serie algorithms for example an incident is detected when the measurements differ significantly from the predictions (e.g. Stephanedes et al. 1992, Dudek et al. 1974). With the McMaster algorithm different traffic situations (e.g. incidents) are distinguished based on the location of measurements in the occupancy – flow volume diagram (e.g. Hall et al. 1993). Finally, in decision structure algorithms incidents are detected when measurements exceed thresholds in a decision tree (e.g. Ash 1997, Payne & Tignor 1978). In The Netherlands a decision structure algorithm has been developed for the Dutch motorways which appears to be quite successful (Knibbe et al. 2005). Complementary, in this paper we introduce a prediction scheme for recurrent events and an incident detection algorithm based on data from a Dutch city. For our detection algorithm we only use volume data. In section 2 we describe the data and in section 3 we introduce our incident detection method.

KW - IR-76962

KW - METIS-249255

M3 - Conference contribution

SP - -

BT - Proceedings of the 7th European Congress and Exhibition on Intelligent Transport Systems and Services, 4-6 June 2008, Geneva

A2 - ITS, null

PB - Ertico/ ITSinEuropa

CY - Brussels, Belgium

ER -

Thomas T, van Berkum EC. Detection of Incidents and Events in Urban Networks. In ITS, editor, Proceedings of the 7th European Congress and Exhibition on Intelligent Transport Systems and Services, 4-6 June 2008, Geneva. Brussels, Belgium: Ertico/ ITSinEuropa. 2008. p. -