Event Classification and Filtering of False Alarms in Wireless Sensor Networks

In this paper the classification of discrete events, computed on tiny wireless sensor nodes, is investigated. Three different classifiers are evaluated: a Bayesian classifier, a fuzzy logic controller (FLC), and a neural network approach. The target applications pose several requirements on the classifiers. No a priori knowledge about the event classes is available. Events are only observable as collections of raw sensor data. Accordingly, event classes need to be learned from that raw (training) data. As a consequence, pre-labeling of the events is not possible either. In our work, event classes are learned by a k-means clustering algorithm. Any subsequent classifier training is based on these extracted event classes. Thus, the resulting classifiers are completely self-learning. Event classes are learned from emitted signal strength estimations, which are collected and processed by dynamically established tracking groups. The resulting event estimates are reported to a base station, where the classifiers are trained. The learned classifier parameters are then downloaded onto the sensor nodes, where any subsequent classification and filtering is performed.