Graph Based Approach to Real-Time Metro Passenger Flow Anomaly Detection

Real-time anomaly detection of passenger flows in the metro system is very important to maintain the URT system's normal operation and ensure passengers' safety. This paper proposes a novel abnormal passenger flow detection method based on smart card data. The method constructs a graphic model whose topological structure can capture the spatial distribution of anomalous passenger flow. It further incorporates external information (e.g. geographical information) to depict the latent passenger flow's spatial dependence embedded in URT system. Considering abnormal flows may only exist in local regions of the metro system, a detection statistic is constructed by using graph community detection. The statistic also incorporates an adaptive sampling strategy for further signal selection and noise filter. It can be efficiently solved via a Min-Cut-based algorithm and can provide real-time solutions to anomaly detection and diagnosis. Preliminary experimental results demonstrate the efficiency of our method.