Logit model versus fuzzy logic model for representing gap-acceptance behavior

Gap-acceptance behavior at unsignalized intersections has been extensively studied in the field of traffic theory and engineering using various methods. The acceptance or rejection of a certain gap is considered the result of a driver’s decision process, affected by subjective and imprecise estimates of a set of explanatory variables considered as input. Classical probabilistic models (e.g. Logit models) and fuzzy system theory have been proposed in the past in order to describe the gap-acceptance behavior. On the basis of experimental data collected at a priority junction, this paper presents a comparative analysis made using the so-called ROC (Receiver Operating Characteristic) curve analysis. The statistical equivalence of results indicates that Fuzzy models can be considered an alternative to the use of Logit models.