MICROCOMPUTERS IN TRANSPORTATION. DEVELOPMENT OF SELF-ORGANIZING TRAFFIC CONTROL SYSTEM USING NEURAL NETWORK MODEL

The paper describes the development of a self-organizing traffic control system using a neural network model, a multilayer network model. The neural network inputs the control variables, such as split lengths and offsets, and outputs the measures of effectiveness, such as performance indexes. The operation consists of two processes: a training process that builds an input-output relationship between the control variables and the measures of effectiveness and an optimization process that optimizes the control variables. The details of the study are described, and the conclusions drawn from the study are presented.