Driving behaviour identification based on OBD speed and GPS data analysis

Abstract

Vehicle accidents, particularly in small and large urban areas, are rising tremendously day by day worldwide. As a recent research subject in automaton transportation, the subsequent collision has become a vital issue and emergency. Internet of things (IoT) and the Internet of Vehicles (IoV) have become very popular these days because of their versatility, and robust cybersecurity underpin these new connected services. Aggressive driving among improper driving behaviours is a mainly responsible cause of traffic accidents that endanger human safety and property. Identifying dangerous driving is a significant step in changing this situation by analyzing data recorded through different gathering devices. The focus of aggressive recognition research has recently shifted to the use of vehicle motion data, which has emerged as a new technique for understanding the phenomenon of traffic. As aggressive driving refers to abrupt changes in actions, it is possible to classify them based on the vehicle's movement data. This paper presents a method to identify driving behaviours categorized into four groups: dangerous, aggressive, safe and normal behaviour to reduce the risk of accidents based on real-time data recorded from vehicles and reference data provided by previous researchers. Comparison and statistical methods have been done to determine the best way to collect driving data based on independent-samples t-test using Statistical Package for the Social Sciences (SPSS) statistics to compare the means between groups on the same continuous, dependent variable. Results have also shown that a small difference of speed between the mobile application and the On-Board Diagnostics (OBD-II) speed with t(4024.1) = 1.8, p =.071, which can be considered acceptable. Furthermore, the OBD-II adapter and mobile application speed were significantly different from the independent GPS device with t(3184.9) = 10.8, p = 0 and t(4416.5) = 13.2, p = 0. Consequently, it is expected to improve drivers' awareness of their driving behaviours.