A fuzzy clustering-based approach to automatic freeway incident detection and characterization

Automatic incident detection and characterization is urgently required in the development of advanced technologies used for reducing non-recurrent traffic congestion on freeways. This paper presents a new method which is constructed primarily on the basis of the fuzzy clustering theories to identify automatically freeway incidents. The proposed approach is capable of distinguishing the time-varying patterns of incident-induced traffic states from the patterns of incident-free traffic states, and characterizing incidents with respect to the onset and end time steps of incidents, incident location, the temporal and spatial change patterns of incident-related traffic variables in response to the impacts of incidents on freeway traffic flows in real time. Lane traffic count and density are the two major types of input data, which can be readily collected from point detectors. Based on the spatial and temporal relationships of the collected raw traffic data, several time-varying state variables are defined, and then evaluated quantitatively and qualitatively to determine the decision variables used for real-time incident characterization. Utilizing the specified decision variables, the proposed fuzzy clustering-based algorithm executes recurrently three major procedures: (1) identification of traffic flow conditions, (2) recognition of incident occurrence, and (3) incident characterization. In this study, data used for model tests are generated from the CORSIM traffic simulator. Our preliminary test results indicate that the proposed approach is promising, and, in expectation, can be integrated with any published real-time incident detection technologies. Importantly, this study may contribute significantly to the applications of fuzzy clustering techniques, and stimulate more related research.