Distributed Adaptive Recommendation & Time-stamp based Estimation of Driver-Behaviour

Abstract

Driver behavior analysis is one of the critical issues that need to be addressed to prevent traffic accidents. It contributes to many real-time applications, such as usage-based pricing (UBI), pay-as-you-drive (PAY-D), and insurance premium calculations. Driver Behavior Profiling-Prognosis (DBP-P) is considered a quantitative risk assessment parameter in road accidents and is a fusion of two sub-processes, behavior scoring and classification of driving patterns. The selection of features like speed or acceleration is the essential and decisive factor in automobile driving behaviour. Though there exists a number of such schemes in the literature, most of them primarily focus on independently on each vehicle and score them. This goal, however, does not clearly indicate any driver's driving quality or its risk of collision with other vehicles. Therefore, to overcome the limitations of the literature, this paper proposes a relative, adaptive, and distributed driver behaviour profiling technique, named Distributed Adaptive Recommendation & Time-stamp based Estimation of Driver-Behaviour (DARTED), to generate driving scores to quantify and classify driver behavior as good or bad. Moreover, the driver scores can be computed at each timestamp with a classified label that can be used in various applications aiming for collision analysis. The experimental results indicate that the proposed method achieves significant accuracy in different traffic scenarios. The model may be helpful to researchers for study and enhance understanding and many real-time industrial applications.