Neural network architecture for the estimation of drivers' route choice

The artificial neural network has recently been applied in many areas including transport engineering and planning. However, since the general neural network considers all the listed variables in a batch, the network seemed to be unsophisticated. A more sophisticated neural network model therefore had to be developed. In this study, a sophisticated neural network model was developed for drivers' route choice model. Its performance was then compared with the performance of the Logit model. For the development of the neural network model, two different neural network models-the general neural network model and the customized neural network model whose architecture is similar to the Logit models-were considered. The results showed that the customized neural network could perform better than other models in terms of prediction accuracy and goodness-of-fit.