Comparison of clustering techniques for traffic accident detection

Transportation infrastructure in intelligent transportation systems (ITSs) is complemented with information and communication technologies to achieve better passenger safety and reduced transportation time, fuel consumption, and vehicle wear and tear. This paper shows how data mining techniques are used in ITSs for accident detection and prevention on motorways. In traffic, vehicles show similar behavior to that of vehicles in closed neighborhoods. Vehicles that show different behaviors than neighbor vehicles in cases like accidents, inappropriate lane changes, and speeding can be considered as anomalies and detected. In this paper, a traffic accident is simulated and the effectiveness of different clustering techniques is examined for detecting traffic accident. We show that if velocity and position values of each vehicle are given, vehicles' behavior can be analyzed and accidents can be detected easily. The success of the proposed algorithms is demonstrated in a highway scenario by means of simulations. Simulations showed that data mining tools successfully detected accidents with an average accident detection rate of 100% and a false alarm rate of 0% using DBSCAN and hierarchical clustering.