Detecting Aggressive Driving Behavior Using Spectral Kurtosis and MEMS Accelerometers

Abstract

World Health Organization has shown that nearly 1.25 million people die in road traffic accidents each year. In fact, the American Automobile Association conducted a research showing that unsafe driving accounted for more than 56% of road accident fatalities. Due to the explosion of sharing economy, we can easily hail a ride at anywhere and anytime in most urban cities. Such ride-hailing platforms, e.g., Uber, benefit our everyday travel and ensure efficient use of vehicles. However, the riding experience differs a lot among drivers, and sometimes they may even adopt aggressive driving behaviors to arrive earlier. In order to make driving safer, monitoring the traffic system by investing in loop detectors, road-side speed indicators, or constant vigilance through CCTVs throughout a city can become pretty expensive. This becomes a vital issue when states lag behind in driver safety improvement programmes and proper road maintenance due to financial crunches along with disregard of drivers toward traffic safety rules. So, a cost-effective and real-time solution for road safety monitoring was very much in need since smart transportation system is one of the most essential components for realizing a smart city.