A probabilistic model for anomaly detection in remote sensor streams

Graduation date: 2008Remote sensors are becoming the standard for observing and recording ecological data in the field. Such sensors can record data at fine temporal resolutions, and they can operate under extreme conditions prohibitive to human access. Unfortunately, sensor data streams exhibit many kinds of errors ranging from corrupt communications to partial or total sensor failures. This means that the raw data stream must be cleaned before it can be used by domain scientists. In our\ud application environment---the H.J. Andrews Experimental Forest---this data cleaning is performed manually. This thesis introduces a Dynamic Bayesian Network model for analyzing sensor observations and distinguishing sensor failures from valid data for the case of air temperature measured at a 15-minute time resolution. The model combines an accurate distribution of seasonal, long-term trends and temporally localized, short-term temperature variations with a single generalized fault model. Experiments with\ud historical data show that the precision and recall of the method is comparable to that of the domain expert