A NEURAL NETWORK MODEL FOR DATA FUSION IN ADVANCE

As current state of the art technology on smart cars and Smart Highways is processing, applications of advanced technologies in transportation engineering are becoming more and more important. The process of collecting, organizing, and estimating current travel times from numerous data sources is termed data fusion in intelligent vehicle highways systems. Travel time data fusion is essentially a traffic flow pattern recognition and travel time estimation problem. We consider neural network models as viable technology for solving the travel time data fusion problem. This paper describes the ability of a counterpropagation neural network model to classify input traffic flow patterns and output current travel time estimates.