This paper considers the problem of characterize the way people drive applied to driver assistance systems and integrated safety systems without using direct driver signals. To make this, is proposed the design of a driver behaviors classifier based on a previous intelligent driving diagnosis system development by us [1]. This, take into account signals that can be acquired by a GPS data logging system: position, velocity, accelerations and steering angle. The classifier proposed, present the structure of an intelligent driver behaviors model based on neural networks and using as inputs statistical transformations of the driving diagnosis time signals: steering profiles, pedals uses, speeding and getting out of the lane and road. The validation of this classifier is developed in two applications: driver identification for security systems and to classify a driver into one of two categories, aggressive and moderate. The proposed approach has been implemented in real environment and its performance tested in simulation runs. Experimental results presented in this paper shows that our intelligent driving diagnosis system is able to classify different kinds of drivers with a high degree of reliability.