Construction of a Smart City Network Information Security Evaluation Model Based on GRA-BPNN

In this study, we propose an optimized network information security evaluation GRA-BPNN model based on gray correlation analysis method combined with BP neural model, and make corresponding optimization for index. Simulation experiments are conducted to analyze the experimental simulation results show that test sample values reach best training performance at 7th iteration after 13 iterations, R-values in regression of all above 0.99, data well-fitted. When number iterations reaches 13, gradient is 0.00067928, value Mu 0.001, validity 6. The scores 0.028 higher than GRA method, which line expected error, score also proves more comprehensive specific its scoring consideration.