|Title:||Vehicular traffic data analysis and its benefits to prevent traffic congestion|
|Proceedings:||Proceedings of the IPLnet 2004 Workshop|
|Conference details:||IPLnet 2004 Workshop, Murten, Switzerland, September 7-8, 2004|
|Publisher / Ed. Institution :||IPLnet|
|License (according to publishing contract) :||Licence according to publishing contract|
|Type of review:||Not specified|
|Subjects :||Verkehr; Pattern recognition; Wavelet|
|Subject (DDC) :||380: Communications and transportation|
|Abstract:||Traffic and traffic congestions in particular have an increasing economic impact at a national as well as a regional level. Data available from surveys performed on the Swiss freeway network show a surge in the accumulated yearly hours of congestion between the years 1994 and 2003. Congestions have different causes. However, the three major reasons identified are capacity overloads, incidents and temporary building sites where mainly the capacity overloads had a strong increase over the last years. Therefore, the focus of this paper is on this topic. In this paper, we present two data analysis methods, which are applied to vehicular traffic data. The goal of the first method is to estimate link travel times based on a re-identification algorithm applied on single vehicle data. The second approach seeks for incident detection using discrete wavelet transformation (DWT) technique. Both methods are implemented within a MATLAB®-environment and are intended to be a basis for other, superior algorithms to be developed for 'Intelligent Transportation Systems (ITS)'. Their feasibility as well as their benefit is shown using real data. Moreover, a comparison of the estimated points in time of the beginning and the end of the congestion observed is conducted. The results show good consistence and thus represent a promising basis for further research on these topics.|
|Departement:||School of Engineering|
|Organisational Unit:||Institute of Data Analysis and Process Design (IDP)|
|Publication type:||Conference Paper|
|Appears in Collections:||Publikationen School of Engineering|
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.