Multimodel anomaly detection on spatio-temporal logistic datastream with open anomaly detection architecture

作者：

Highlights：

• Trajectory Based Anomaly Detection takes into account the vehicle’s route.

• Anomaly detection based on driver behavior addresses driving characteristics.

• Driver and trajectory based anomaly analysis was carried out together.

• This work based on stream processing so the anomalies are detected in near-real-time.

摘要

•Trajectory Based Anomaly Detection takes into account the vehicle’s route.•Anomaly detection based on driver behavior addresses driving characteristics.•Driver and trajectory based anomaly analysis was carried out together.•This work based on stream processing so the anomalies are detected in near-real-time.

论文关键词：Logistics,Big data,Streaming data,Anomaly detection,Trajectory anomaly detection,Driver identification,Driver behavior anomaly detection

论文评审过程：Received 3 April 2021, Revised 31 May 2021, Accepted 8 August 2021, Available online 14 August 2021, Version of Record 18 August 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115755