Short Term Traffic Flow Prediction for a Non Urban Highway Using Artificial Neural Network

This study applies Artificial Neural Network (ANN) for short term prediction of traffic flow using past traffic data. The model incorporates traffic volume, speed, density, time and day of week as input variables. Speed of each category of vehicles was considered separately as input variables in con...

Full description

Saved in:
Bibliographic Details
Published inProcedia, social and behavioral sciences Vol. 104; pp. 755 - 764
Main Authors Kumar, Kranti, Parida, M., Katiyar, V.K.
Format Journal Article
LanguageEnglish
Published Elsevier Ltd 02.12.2013
Subjects
heterogeneous traffic
multi-layer perceptron
sensitivity
speed
traffic flow
sensitivity
heterogeneous traffic
multi-layer perceptron
traffic flow
speed
Online AccessGet full text

Cover

More Information
Summary:This study applies Artificial Neural Network (ANN) for short term prediction of traffic flow using past traffic data. The model incorporates traffic volume, speed, density, time and day of week as input variables. Speed of each category of vehicles was considered separately as input variables in contrast to previous studies reported in literature which consider average speed of combined traffic flow. Results show that Artificial Neural Network has consistent performance even if time interval for traffic flow prediction was increased from 5minutes to 15minutes and produced good results even though speeds of each category of vehicles were considered separately as input variables.
ISSN:1877-0428
1877-0428
DOI:10.1016/j.sbspro.2013.11.170