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

Journal Title: Archives of Transport - Year 2012, Vol 24, Issue 4

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.

Authors and Affiliations

Teresa Pamuła

Keywords

Related Articles

DEVELOPMENT OF MODELS FOR DETERMINING THE TRAFFIC VOLUME FOR THE ANALYSIS OF ROADS EFFICIENCY

The article presents different methods of estimating DHV, including traditional Factor Approach, developed Regression Models and Artificial Neural Networks models. As explanatory variables: quantitative variables (AADT a...

The safety assurance method of railway control systems using object oriented languages

The paper deals with introduction of safety rules to the software designed for railway control systems. The basic assumption is related to software designed using high level language UML with possibility of modelling, ve...

The method for increasing the efficiency of equipment’s maintenance in railway traction power supply systems

Purpose. To develop the method for increasing the efficiency of the equipment’s maintenance and repair system, ensuring necessary level of operational reliability of the equipment, safety and reliability of the electric...

Operational problems of 2+1 bypass road sections

The paper presents several problems of designing trunk-road bypasses of towns, which can be very helpful in improving their traffic performance. Such roads perform supplementary functions to the operation of network of m...

PROECOLOGICAL APPROACH TO MODELLING TRAFFIC ORGANIZATION IN NATIONAL TRANSPORT SYSTEM

The paper presents a general approach to modelling traffic organization within the network of national transport system and with taking into account environmental aspects. General description of the model and necessary d...

Download PDF file
  • EP ID EP70067
  • DOI 10.2478/v10174-012-0032-2
  • Views 117
  • Downloads 0

How To Cite

Teresa Pamuła (2012). Classification and Prediction of Traffic Flow Based on Real Data Using Neural Networks. Archives of Transport, 24(4), 519-529. https://europub.co.uk/articles/-A-70067