HAPS: Hierarchical abnormal event processing over data streams

Many distributed real-time applications, such as electric device monitoring, object tracking and disaster monitoring, require effective and efficient techniques to detect abnormal events of interest in the physical world. Despite the simplicity in implementation, the existing threshold-based approach to event detection suffers from limited expressive power and poor tolerance to missing values and errors in sensor data. In this paper, we present a hierarchical abnormal event detection framework for data streams. We formalize the event specification and develop efficient matching methods in three different levels. An overview about a typical active real-time database (ARTDB) is also provided. Furthermore, HAPS can be implemented on ARTDB by using objects and ECA rules in it. To illustrate the benefits of HAPS for abnormal event detection over data stream, an example application is presented.