A paper titled “Classification and Evaluation of Driving Behaviour Safety Levels: A Driving Simulation Study”  authored by Kui Yang, Costantinos Antoniou and George Yannis has been published in IEEE. The proposed methodology focuses on determining the optimal aggregation time interval, finding the optimal number of safety levels for driving behavior, classifying the safety levels, and evaluating the driving safety levels in real time. Support vector machines, decision trees and naïve Bayes classifiers were then developed as classification models. The accuracy of the combination of k-means clustering and decision trees proved to be the best with three clusters.