Detecting Anomalies in Data Streams using Statecharts
Vasile-Marian Scuturici, Dan-Mircea Suciu, Romain Vuillemot, Aris M. Ouksel, Lionel Brunie
The environment around us is progressively equipped with various sensors, producing data continuously. The applications using these data face many challenges, such as data stream integration over an attribute (such as time) and knowledge extraction from raw data. In this paper we propose one approach to face those two challenges. First, data streams integration is performed using statecharts which represents a resume of data produced by the corresponding data producer. Second, we detect anomalous events over temporal relations among statecharts. We describe our approach in a demonstration scenario, that is using a visual tool called Patternator.