Real‐time passenger flow anomaly detection in metro system

Real-time passenger-flow anomaly detection at all metro stations is a very critical task for advanced Internet management. Robust principal component analysis (RPCA) based method has often been employed of multivariate time series data. However, it ignores the spatio-temporal features regular patterns, resulting in decrease accuracy detection. In this paper, RT-STRPCA model integrating temporal periodicity and spatial similarity proposed to address above issues. detects anomalies by decomposing observation data into normal component. The constraints are taken account extract more accurately. real-time realized sliding window. performance evaluated on synthetic datasets real-world datasets. experimental results demonstrate that achieves accurate than baseline approaches result verify utility effectiveness method.