Detecting Reporting Anomalies in Streaming Sensing Systems
Shiree Hughes, Yuheng Du, Jason O. Hallstrom · Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering · 2015
Sensor networks must be monitored to identify and correct problems as they occur.We present a comparison of two approaches to monitoring deployed sensors.The first relies on configuration parameters to define expected reporting behavior.The second automatically identifies normal reporting patterns based on a combination of configuration parameters and an analysis of reporting times.Using these patterns, the system notifies personnel of possible malfunctions.We present empirical evaluations in the context of the Intelligent River R system [11].