An intelligent system to enhance traffic safety analysis

Traffic phenomena are characterized by complexity and uncertainty, hence require sophisticated information management to identify patterns relevant to safety. Traffic information systems have emerged with the aim to ease traffic congestion and improve road safety. However, assessment of traffic safe...

Full description

Bibliographic Details
Main Authors: Gregoriades, A., Mouskos, K., Ruiz-Juri, N., Parker, N., Hadjilambrou, I., Krishna, Aneesh
Other Authors: Eugen Borcoci
Format: Conference Paper
Published: IARIA 2011
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/49220
_version_ 1848758190819246080
author Gregoriades, A.
Mouskos, K.
Ruiz-Juri, N.
Parker, N.
Hadjilambrou, I.
Krishna, Aneesh
author2 Eugen Borcoci
author_facet Eugen Borcoci
Gregoriades, A.
Mouskos, K.
Ruiz-Juri, N.
Parker, N.
Hadjilambrou, I.
Krishna, Aneesh
author_sort Gregoriades, A.
building Curtin Institutional Repository
collection Online Access
description Traffic phenomena are characterized by complexity and uncertainty, hence require sophisticated information management to identify patterns relevant to safety. Traffic information systems have emerged with the aim to ease traffic congestion and improve road safety. However, assessment of traffic safety and congestion requires significant amount of data which in most cases is not available. This work illustrates an approach that aims to alleviate this problem through the integration of two mature technologies namely, simulation basedDynamic Traffic Assignment (DTA) and Bayesian Belief Networks (BBN). The former generates traffic information that is utilised by a Bayesian engine to quantify accident risk. Dynamic compilation of accident risks is used to gives rise to overall traffic safety. Preliminary results from this research have been validated.
first_indexed 2025-11-14T09:40:03Z
format Conference Paper
id curtin-20.500.11937-49220
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T09:40:03Z
publishDate 2011
publisher IARIA
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-492202023-02-02T07:57:35Z An intelligent system to enhance traffic safety analysis Gregoriades, A. Mouskos, K. Ruiz-Juri, N. Parker, N. Hadjilambrou, I. Krishna, Aneesh Eugen Borcoci Petre Dini Traffic Safety Bayesian Belief Networks Dynamic Traffic Assignment Traffic phenomena are characterized by complexity and uncertainty, hence require sophisticated information management to identify patterns relevant to safety. Traffic information systems have emerged with the aim to ease traffic congestion and improve road safety. However, assessment of traffic safety and congestion requires significant amount of data which in most cases is not available. This work illustrates an approach that aims to alleviate this problem through the integration of two mature technologies namely, simulation basedDynamic Traffic Assignment (DTA) and Bayesian Belief Networks (BBN). The former generates traffic information that is utilised by a Bayesian engine to quantify accident risk. Dynamic compilation of accident risks is used to gives rise to overall traffic safety. Preliminary results from this research have been validated. 2011 Conference Paper http://hdl.handle.net/20.500.11937/49220 IARIA restricted
spellingShingle Traffic Safety
Bayesian Belief Networks
Dynamic Traffic Assignment
Gregoriades, A.
Mouskos, K.
Ruiz-Juri, N.
Parker, N.
Hadjilambrou, I.
Krishna, Aneesh
An intelligent system to enhance traffic safety analysis
title An intelligent system to enhance traffic safety analysis
title_full An intelligent system to enhance traffic safety analysis
title_fullStr An intelligent system to enhance traffic safety analysis
title_full_unstemmed An intelligent system to enhance traffic safety analysis
title_short An intelligent system to enhance traffic safety analysis
title_sort intelligent system to enhance traffic safety analysis
topic Traffic Safety
Bayesian Belief Networks
Dynamic Traffic Assignment
url http://hdl.handle.net/20.500.11937/49220