Supervision on abnormal activities in vehicle inspection service by anomaly detection in bipartite graph

Anomaly detection in bipartite graph is of great use in many real applications and therefore it attracts numerous research efforts. This work formulates the supervision on abnormal activities in vehicle inspection stations as an anomaly detection problem in weighted bipartite graph. Relevance scores and normality scores are computed for registration districts and inspection stations. The suspicion of an inspection station involving abnormal behaviors is evaluated according to the distribution of the normality scores. Experimental results on real datasets are given, showing the effectiveness of the proposed method.