Average annual daily traffic (AADT) is important in transportation engineering and planning, and although the State of Louisiana collects AADT on a regular basis on state-maintained highways, most parishes and smaller municipalities do not have the resources to collect AADT frequently. Because the roads under the jurisdiction of parishes and municipalities account for three-fourths of the entire state road network, a practical method to estimated AADT must be developed. Before model development, previous studies into AADT estimation and their results are to be further analyzed. Roadway, demographic, and economic data for selected parishes in Louisiana is collected and processed to remove any data not necessary in model development, and afterwards, parish-specific and combination data models using this data are developed to compare to the observed AADT at a particular count station. Parish selection is based on population, number of existing count stations within the parish, and if an Interstate Highway traverses the parish. Because of the varying characteristics among the data in the selected parishes, parish-specific models for the rural parish roads are developed, and Poisson is selected as the regression model due to discrete data. Results for all Poisson models developed show that the models tend to overestimate AADT for lower observed AADT and underestimate AADT for higher observed AADT. Because of this, support vector regression (SVR) was used, and this method greatly improved the estimation of AADT in comparison to the Poisson regression as shown using certain goodness-of-fit parameters.
|Commitee:||Khattak, Mohammad, McManis, Kenneth|
|School:||University of Louisiana at Lafayette|
|School Location:||United States -- Louisiana|
|Source:||MAI 54/04M(E), Masters Abstracts International|
|Subjects:||Civil engineering, Transportation planning|
|Keywords:||Average annual daily traffic, Louisiana, Roads, Rural, Traffic|
Copyright in each Dissertation and Thesis is retained by the author. All Rights Reserved
The supplemental file or files you are about to download were provided to ProQuest by the author as part of a
dissertation or thesis. The supplemental files are provided "AS IS" without warranty. ProQuest is not responsible for the
content, format or impact on the supplemental file(s) on our system. in some cases, the file type may be unknown or
may be a .exe file. We recommend caution as you open such files.
Copyright of the original materials contained in the supplemental file is retained by the author and your access to the
supplemental files is subject to the ProQuest Terms and Conditions of use.
Depending on the size of the file(s) you are downloading, the system may take some time to download them. Please be