Optimization of Hierarchical Data Fusion in Wireless Sensor Networks

In Wireless Sensory Networks (WSN), data fusion technology is one of the important measures of reducing the data traffic, saving the energy of the nodes and prolonging network lifetime. In order to compress the data and improve the accuracy of the incident identification, a new hierarchical data fusion algorithm of WSN is proposed. On the side of sink nodes, the data from the sensor nodes is compressed by the least-square algorithm with a limited window, which reduces the communication traffic between sink nodes and the monitoring center; on the side of monitoring center, the incident identification accuracy is improved in D-S evidence theory recognition framework, by using the triangular fuzzy membership function to obtain the basic probability assignment (BPA) value.