An Improve Information Fusion Algorithm Based on BP Neural Network and D-S Evidence Theory

BP neural network and DS evidence theory have gotten a wide range of applications in the field of information fusion. According to the BP neural network have low recognition rate and poor network stability, what is more, it is difficult to get D-S evidence theory of basic probability distribution function, This paper design a kind of improved algorithm, which combined group neural network and D-S evidence theory. The improved algorithm make full use of the advantages. The simulation results show that this algorithm have a better effect both in recognition rate and anti-noise capacity.