Fault diagnosis of node in wireless sensor network based on the interval-numbers rough neural network

This paper proposed a new fault diagnosis method of node in WSN based on the interval-numbers rough neural network. Firstly, this method established the most simple decision-making table of the fault diagnosis by the improved discriminate matrix, then applied rough decision-making analysis method constructed a interval-value information decision-making system of WSN node, and constructed the rough neuron of the input layer; Finally, constructed the fault diagnosis system based on the three-layers feed-forward rough neural network with the interval numbers. The simulation results show that this method made the rate of diagnostic accuracy to 99.24% when the computing time was greatly reduced, and it has high practical value.