A software called Optimal Traffic Signal Control System (OTSCS) was developed by us for testing the feasibility of dynamically controlling a traffic signal by finding optimal signal timing to minimize delay at signalized intersections. It also was designed as a research tool to study the learning behavior of artificial neural networks and the properties of heuristic search methods. It consists of a level-of-service evaluation model that is based on an artificial neural network and a heuristic optimization model that interacts with the level-of-service evaluation model. This article discusses the latter model, named the Optimal Traffic Signal Timing Model (OTSTM). The OTSTM was applied to determine optimal signal timing of twophase traffic signals to evaluate the model's performance. Two search methods were employed: a depth-first search method (an enumeration method) and a direction-search method that we developed. It was found that the OTSTM with the direction search resulted in "optimal" signal timings similar to the depth-first search, which would always produce a global optimal timing. Yet the cost of the direction search, as measured by the CPU time of the computer used for analysis, was found to be much less than the cost of obtaining an optimal solution by the depth-first search cases-more than 10 times less. The study showed that once

No abstract

The effects of architecture, learning mode, and learning rate on the performance of a level-of-service (LOS) analysis model using an artificial neural network (ANN) are discussed. Multilayer LOSANN models demonstrated improved quality of learning and testing over single-layered models in evaluating level of service of signalized intersections given geometric, traffic, and traffic signal control data. At present, LOSANN takes delay data from Highway Capacity Software (HCS) outputs; hence its accuracy is constrained by the accuracy of the HCS analyses. However, if delays can be determined directly by field observation, the relationships (or patterns) between field-measured delays and the traffic, geometric, and signal control conditions can be fed to LOSANN. Then the neural network-based model can evaluate the level of service at a higher level of accuracy, and such models can be used as part of advanced traffic management systems to automate LOS analyses.

No abstract

No abstract