Find in Library

For many people, driving a vehicle is an indispensable part of everyday life. However, sometimes everyday life does not go as expected, as a lot of accidents happen on the public roads. Most of the accidents are due to inattentive driver behavior. Modern driver monitoring systems evaluate driver behavior by means of distinctive sensor technology and, if necessary, indicate undesirable driving behavior. However, many roadworthy vehicles do not have the possibility to implement such systems. Therefore, it seems to be interesting to investigate the implementation of such systems on the basis of commodity hardware, e.g. smartphones, because nowadays almost every driver has a powerful smartphone equipped with many sensors. Furthermore, advances in machine learning made it possible to analyze large amounts of data and to generate new conclusions. This work is dedicated to the topic of how machine learning can be used for driver behavior recognition by improving an already existing driver monitoring system with machine learning techniques. We propose to use Microsoft Azure platform to analyze the data generated by a Driver Monitoring System.