The effect of crisp variables on fuzzy models of gap-acceptance behaviour

This paper describes the application of a neuro-fuzzy system approach to the modelling of gap-acceptance behaviour at priority intersections. This approach consists of defining an adaptive neural network functionally equivalent to a fuzzy system, and subjecting this network to a learning process based on experimental input-output data. This allows one to use directly objective evidence in the identification of the fuzzy system knowledge base (membership functions and inference rules), thus avoiding any discretionary evaluation inherent in the alternative expert judgement approach.