Comparison of neural and conventional approaches to mode choice analysis

This paper describes a new approach to behavioral mode choice modeling usin g neurofuzzy models. The new approach combines the learning ability of arti ficial neural networks and the transparent nature of fuzzy logic. The appro ach is found to be highly adaptive and efficient in investigating nonlinear relationships among different variables. In addition, the approach only se lects the variables that significantly influence the mode choice and displa ys the stored knowledge in terms of fuzzy linguistic rules. This allows the modal decisionmaking process to be examined and understood in great detail . The neurofuzzy model is tested on the U.S. freight transport market using information on individual shipper and individual shipments. Shipments are disaggregated at the five-digit Standard Transportation Commodity Code leve l. Results obtained from this exercise an compared with similar results obt ained from the conventional legit mode choice model and the standard back-p ropagation artificial neural network. The advantages of using the neurofuzz y approach are described.