Data Fusion Algorithm of Wireless Sensor Based on Combination between Cluster Head Election Improvement and Neural Network

Wireless Sensor Network (WSN) communication is limited by node energy consumption. How to minimize the energy consumption during transmission is of great importance to prolong the service life of network. A data fusion algorithm based on neural network (NNDFA) is designed in the paper. The algorithm combines the BP neural network with the improved routing protocol of wireless sensor network. By training the weights of each layer of the neural network, it extracts the same features from the original data and sends the feature data to the Sink node. Thus, it can reduce the amount of data transmission, save energy consumption and prolong the network life. It is proved by the simulation result that the algorithm effectively reduces the number of data transmission and prolongs service life of network in comparison with LEACH algorithm and BP neural network.