AI-Based Driving Data Analysis for Behavior Recognition in Vehicle Cabin

Driving a vehicle is an indispensable part of their everyday life for many people. However, sometimes this everyday life does not go as expected, as a lot of accidents happen on the public roads, and most of these 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 based on commodity hardware, e.g., smartphones, because nowadays almost every driver has a powerful smartphone equipped with many sensors at hand in the vehicle. Furthermore, recent advances in Machine Learning (ML) made it possible to analyze large amounts of data and to generate new outcomes. In this work we discuss how ML can be used for driver behavior recognition by improving an already existing threshold-based driver monitoring system with different ML-based techniques, Neural Networks and Random Forests, and evaluate their performance. We propose to use Microsoft Azure platform to analyze data generated by a Driver Monitoring System (DMS). Our results indicate ML as a useful technique for learning and adapting threshold-based reasoning about individual drivers' states.