Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Classification and Prediction of Traffic Flow Based on Real Data Using Neural Networks

Classification and Prediction of Traffic Flow Based on Real Data Using Neural Networks Abstract This paper presents a method of classification of time series of traffic flow, on the section of the main road leading into the city of Gliwice. Video detectors recorded traffic volume data was used, covering the period of one year in 5-minute intervals - from June 2011 to May 2012. In order to classify the data a statistical analysis was performed, which resulted in the proposition of splitting the daily time series into four classes. The series were smoothed to obtain hourly flow rates. The classification was performed using neural networks with different structures and using a variable number of input data. The purpose of classification is the prediction of traffic flow rates in the afternoon basing on the morning traffic and the assessment of daily traffic volumes for a particular day of the week. The results can be utilized by intelligent urban traffic management systems. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Archives of Transport de Gruyter

Classification and Prediction of Traffic Flow Based on Real Data Using Neural Networks

Archives of Transport , Volume 24 (4) – Dec 1, 2012

Loading next page...
 
/lp/de-gruyter/classification-and-prediction-of-traffic-flow-based-on-real-data-using-kQGfzWuzrv
Publisher
de Gruyter
Copyright
Copyright © 2012 by the
ISSN
0866-9546
DOI
10.2478/v10174-012-0032-2
Publisher site
See Article on Publisher Site

Abstract

Abstract This paper presents a method of classification of time series of traffic flow, on the section of the main road leading into the city of Gliwice. Video detectors recorded traffic volume data was used, covering the period of one year in 5-minute intervals - from June 2011 to May 2012. In order to classify the data a statistical analysis was performed, which resulted in the proposition of splitting the daily time series into four classes. The series were smoothed to obtain hourly flow rates. The classification was performed using neural networks with different structures and using a variable number of input data. The purpose of classification is the prediction of traffic flow rates in the afternoon basing on the morning traffic and the assessment of daily traffic volumes for a particular day of the week. The results can be utilized by intelligent urban traffic management systems.

Journal

Archives of Transportde Gruyter

Published: Dec 1, 2012

There are no references for this article.