Intelligent erratic driving diagnosis based on artificial neural networks

Abstract

This paper presents an intelligent system to perform an erratic driving diagnosis. The proposed approach takes into account the analysis of the signals that could be acquired from modern on-board diagnostic systems (OBD-II), global positioning systems (GPS) and other localization sensors. Diagnosis of erratic driving could be essential to reduce accident rates, because of several applications that may result based on it. The overall process can be summarized in three steps. First, extraction of suitable signals (throttle, brake, steering, velocity, location) related to driver actions. Secondly, mathematical processing of the above signals for a proper utilization by the intelligent system. Finally, driving faults detection and overall performance rating based on artificial neural networks. Experimental results show the feasibility and reliability of the proposed approach in different driving situations.