Hypothesis testing and decision theoretic approach for fault detection in wireless sensor networks

Abstract

Sensor networks aim at monitoring their surroundings for event detection and object tracking. In practice, due to failure or death of sensors, false signal can be transmitted. In this article, we consider the problem of fault detection in wireless sensor networks, in particular, addressing both the noise-related measurement error and sensor fault simultaneously in fault detection. We assume that the sensors are placed at the centre of a square (or hexagonal) cell in the region of interest (ROI) and, if the event occurs, it occurs at a particular cell of the ROI. We propose fault detection schemes that consider error probabilities in the optimal event detection process. We develop the schemes under the consideration of Neyman–Pearson hypothesis test and Bayes test.