Driver Behavior Profiling Using Machine Learning

The drivers’ behavior influences the traffic on road and this, in turn, influences energy consumed by the vehicles and emission of pollutants from the vehicles. So it is necessary to identify drivers’ characteristics to profile their behavior correctly. A large amount of data is needed for the analysis which is collected by the on-board unit present on the vehicle. On-board unit has sensors that are used to collect the required data. The comparative performance of different machine learning algorithms is evaluated on the data collected by the on-board unit and in turn helps in profiling drivers’ behavior. The experimental result shows that the support vector machine gives an accuracy of 99.4% among the remaining classifier.