| Artificial neural networks are one of the recently explored advanced technologies which show promise in the area of transportation engineering. However, in contrast to the availability of a large number of successful application demonstrations, it is hard to find studies in the literature that provide systematic examinations of the-state-of-the-art, the application domains, and the applicability of artificial neural networks to transportation problems. On the other hand, some unseen artificial neural networks development has been motivated by transportation engineering objectives. Therefore, this document presents examinations of artificial neural network applications in transportation engineering as well as the development of a neural network paradigm for the purpose of roadway traffic signal control for isolated intersections.; The characteristics, properties, and application domains of artificial neural networks and their relationship to neural science and other artificial intelligence techniques, such as expert systems, are reviewed. The review attempts to project the application domains of artificial neural networks in a general sense. Then, through a literature study, the state-of-the-art in application of artificial neural networks to transportation problems is described. Through examinations of numerous applications, the applicability, justifications, advantages and limitations of artificial neural networks for transportation problems are summarized as well.; The next generation of roadway transportation systems will be formed of so-called intelligent transportation systems. It is anticipated that the software component of such intelligent transportation systems will rely on multiple advanced technologies, including artificial neural networks. This document also provides an assessment of the application potential of artificial neural networks to intelligent transportation systems.; To better demonstrate the use of artificial neural networks in solving different types of transportation problems, a number of real-world applications are presented in detail. These applications, which utilize existing artificial neural network techniques, cover several aspects of transportation engineering, including demand study, facilities maintenance, planning and management.; Artificial neural networks are still under development. New advantages, from which transportation engineering can choose, are expected to be revealed as the development progresses. This dissertation dedicates a large amount of attention to the creation of an operation-time weights changing neural network paradigm for creating a traffic signal control system for an isolated intersection. This system focuses on adaptive, "human-thinking-like," and self-organizing performance. Thorough validation of the control mechanism is included.; Finally, this document summarizes the application domains and applicability, advantages and limitations of artificial neural networks in transportation engineering; presents an evaluation of the neural signal control system; and provides recommendations for future studies in this area. |
