A new system for traffic incident detection using fuzzy logic and majority voting

This paper presents a system to detect lane-blocking traffic incidents which are amongst major causes of traffic jam. The proposed system uses fuzzy logic to identify traffic status as normal and abnormal. Mean speed and standard deviation of inter-arrival time are used as inputs to the fuzzy inference system (FIS), and then, the majority voting is applied to the outputs of FIS to improve detection rate and mean time to detection. Furthermore, based on simulation results, we show that the proposed lane-blocking detection system is very suitable for realtime implementation.