Development of Models for Children—Pedestrian Crossing Speed at Signalized Crosswalks

Modeling the behavior of pedestrians is an important tool in analysis their and consequently ensuring safety pedestrian traffic. Children show specific traffic which related to cognitive development, parameters that affect are very different. The aim this paper develop a model children-pedestrian’s speed at signalized crosswalk. For same set data collected city Osijek—Croatia, two models were developed based on neural network multiple linear regression. In both cases 300 measured children crosswalks primary roads located near school. As parameters, include selected infrastructure features children’s characteristics movements. validated type crosswalks, using methodology other urban environments—the Rijeka, Croatia Enna Italy. It was shown model, for Osijek, can be applied with sufficient reliability cities, while regression applicable relatively satisfactory only Rijeka. A comparative statistical indicators these showed better results achieved by model.