An Algorithm of Data Fusion Based on Improved BP Natural Network

Data fusion based on feed-forward natural network can get the goal of minimum error, as well as reduce redundant data to transmit and save energy consumption. BP neutral network is considered as one of the most mature algorithm, but the traditional BP algorithm converges slowly and easy traps in a local minimum value, so new improved BP algorithm named algebraic algorithm is put forward. The algebraic algorithm can make a complex nonlinear optimization problems turn to a simple algebraic equation, and the error function will equal to zero. Results show that the algebraic algorithm is higher precision and efficiency than BP algorithm.