Short-term traffic predictions on large urban traffic networks: Applications of network-based machine learning models and dynamic traffic assignment models

Author

Fusco, Gaetano ; Colombaroni, Chiara ; Comelli, Luciano ; Isaenko, Natalia

Author_Institution

Dept. of Civil, Constructional & Environ. Eng., Sapienza Univ. of Rome, Rome, Italy

fYear

2015

fDate

3-5 June 2015

Firstpage

93

Lastpage

101

Abstract

The paper discusses the issues to face in applications of short-term traffic predictions on urban road networks and the opportunities provided by explicit and implicit models. Different specifications of Bayesian Networks and Artificial Neural Networks are applied for prediction of road link speed and are tested on a large floating car data set. Moreover, two traffic assignment models of different complexity are applied on a sub-area of the road network of Rome and validated on the same floating car data set.

Keywords

belief networks; learning (artificial intelligence); neural nets; road traffic; traffic engineering computing; Bayesian networks; Italy; Rome; artificial neural networks; dynamic traffic assignment models; explicit model; implicit model; network-based machine learning models; road link speed prediction; short-term traffic prediction; urban traffic networks; Artificial neural networks; Bayes methods; Forecasting; Measurement uncertainty; Predictive models; Reliability; Roads; Bayesian Networks; Dynamic Traffic Assignment; Floating Car Data; Neural Networks; Short-term traffic predictions;

fLanguage

English

Publisher

ieee

Conference_Titel

Models and Technologies for Intelligent Transportation Systems (MT-ITS), 2015 International Conference on

Conference_Location

Budapest

Print_ISBN

978-9-6331-3140-4

Type

conf

DOI

10.1109/MTITS.2015.7223242

Filename

7223242