Master of Science in Civil Engineering (MSCE)
Civil and Environmental Engineering
The goal of the research was to develop a new predictive tool for assessing the performance of traffic sign retroreflectivity and to compare the developed tool with the existing linear regression models. Retroreflectivity decreases as sign sheeting ages. Currently Louisiana Department of Transportation and Development (LADOTD) replace signs with low reflectivity based on driver complaints. This practice might have resulted in premature sign replacement (removal of signs with several years of in-service life still remaining) or in non-replacement of signs that are not in compliance with LADOTD minimum reflectivity standards. In this study, both neural network models and regression models were developed to predict reflectivity of Engineering and High Intensity Grade signs. The LADOTD traffic sign inventory data of Ascension Parish traffic signs were used for model development, validation and comparison. The performance of the developed neural network models (NN models) was compared to the developed regression models (R2 models) and also to the existing retroreflectivity regression models (R1 models) developed by Wolshon et al. The R1 models were developed for traffic signs placed along Interstate and State Highway routes in the districts of New Orleans, Baton Rouge, Lafayette, and Shreveport. Also, the usability of the neural network models developed in the study was analyzed based on the data collected by Wolshon et al to develop the linear regression R1 models. The results of this study demonstrated the feasibility of using ANNs in predicting the retroreflectivity of Type I and Type III sign sheeting. The independent variables found to be statistically significant variables in explaining the performance of traffic signs retroreflectivity included age of the sign, sheeting type, and background color of sign sheeting. A comparison of the models developed with two different specifications involving different sets of independent variables showed that the models including all the variables (i.e., Age, Edge of Pavement Distance, Sign Orientation, Sign Background Color, and Sheeting Type) increased the explanatory power of the models by little. However, it was recommended to use of all deterioration variables whose effects are not non-existent.
Document Availability at the Time of Submission
Release the entire work immediately for access worldwide.
Swargam, Nagajyothi, "Development of a neural network approach for the assessment of the performance of traffic sign retroreflectivity" (2004). LSU Master's Theses. 440.