In spite of the most up-to-date investigation of the relevant techniques to analyze the traffic characteristics and traffic operations at a toll plaza, there has not been any note worthy explorations evaluating delay from toll transaction data and using Artificial Neural Networks (ANN) at a toll plaza. This thesis lays an emphasis on the application of ANN techniques to estimate the total vehicular delay according to the lane type at a toll plaza. This is done to avoid the laborious task of extracting data from the video recordings at a toll plaza. Based on the lane type a general methodology was developed to estimate the total vehicular delay at a toll plaza using ANN. Since there is zero delay in an Electronic Toll Collection (ETC) lane, ANN models were developed for estimating the total vehicular delay in a manual lane and automatic coin machine lane. Therefore, there are two ANN models developed in this thesis. These two ANN models were trained with three hours of data and validated with one hour of data from AM and PM peak data. The two ANN models were built with the dependent and independent variables. The dependent variables in the two models were the total vehicular delay for both the manual and automatic coin machine lane. The independent variables are those, which influence delay. A correlation analysis was performed to see if there exists any strong relationship between the dependent (outputs) and independent variables (inputs). These inputs and outputs are fed into the ANN models. The MATLABTB code was written to run the two ANN models. ANN predictions were good at estimating delay in manual lane, and delay in automatic coin machine lane.
| Identifer | oai:union.ndltd.org:ucf.edu/oai:stars.library.ucf.edu:etd-1362 |
| Date | 01 January 2005 |
| Creators | Muppidi, Aparna |
| Publisher | STARS |
| Source Sets | University of Central Florida |
| Language | English |
| Detected Language | English |
| Type | text |
| Format | application/pdf |
| Source | Electronic Theses and Dissertations |
Page generated in 0.0109 seconds