Spatio-temporal Event Detection: A Hierarchy Based Approach for Wireless Sensor Network

Event detection with wireless sensor network (WSN) is an important task required in various applications. The existing approaches consider the spatial and temporal correlation of sensor data separately or not in a cohesive way. In this paper an event detection scheme is introduced, which adopts a hierarchical architecture to efficiently integrate the spatial and temporal correlation of the sensor data. Also, a fusion algorithm considering both the weight of the sensors and spatial information is used in Markov random field to properly fuse the decisions of the sensor nodes. The simulation results demonstrate that the proposed scheme can effectively increase the detection precision and reduce communication cost, in comparison with the existing schemes.