Detecting Anomalies in Sensor Signals using Database Technology

Abstract

Signals are usually post-processed in order to enhance their accuracy and reliability. For instance, sensor data frommoving objects data are often processed by tracking systems which allows for enhancing the provided kinematic information. In high-level fusion systems, this kinematic information can be combined with additional domain-specific data which allows for detecting object behavior and threat patterns. These systems contribute to situation awareness by employing patterns which characterize situations of interest. The used patterns may vary over time and depend on the specific questions to be investigated.Database systems provide a flexible way of combining data, and continuous queries allowing an ongoing automatic evaluation of search patterns. In this chapter, we present a way of using database systems as the central component in a higher-level fusion system. We discuss how patterns for the detection of anomalies in tracking scenarios can be expressed in relational algebra. Finally, we present an application of such a system for monitoring and analyzing air traffic using a commercial database management system.

Original document

The different versions of the original document can be found in:

• http://publica.fraunhofer.de/documents/N-219846.html

• http://www.springerlink.com/index/pdf/10.1007/978-3-642-28696-4_7,

http://dx.doi.org/10.1007/978-3-642-28696-4_7

• https://link.springer.com/chapter/10.1007%2F978-3-642-28696-4_7,

https://core.ac.uk/display/56817166,

https://rd.springer.com/chapter/10.1007/978-3-642-28696-4_7,

https://academic.microsoft.com/#/detail/23409289