Anomaly detection using depth learning on time series data related to application information

摘要

A method and system for detecting and correcting anomalies in comparison with a previous time series segment of a sensor (204), a new time series segment generated by a sensor in a cyberphysical system Including generating similarity measures for each previous time series segment.Based on the similarity measure, it is determined that a new time series represents an abnormal behavior (206).Corrective measures are performed for the cyber physics system to correct the abnormal behavior (208).