APDE-RBF neural network based network security situation prediction method

Abstract

The invention belongs to the technical field of network security and particularly relates to an APDE-RBF (Affinity Propagation Differential Evolution-Radial Basic Function) neural network based network security situation prediction method. The APDE-RBF neural network based network security situation prediction method comprises the steps of dividing and clustering sample data by utilizing an AP clustering algorithm to obtain the number of nodes of hidden layers of the center and network of the RBF; obtaining population diversity by using AP clustering, changing a zoom factor and a crossover probability of a DE algorithm adaptively and optimizing the width and connection weight of the RBF; meanwhile, performing chaotic search on elite individuals and population diversity center of each generation of population in order to avoid falling into local optimization and jumping out of a local extreme point; and determining a final RBF network model, inputting a test dataset and outputting a situation prediction value. The APDE-RBF neural network based network security situation prediction method aims at improving the prediction precision for the network security situation while enhancing the generalization ability.

Description

technical field [0001] The invention belongs to the technical field of network security, and in particular relates to a network security situation prediction method based on a radial basis function (Affinity Propagation Differential evolution-Radial Basis Function, APDE-RBF) neural network based on an attractor propagation differential evolution algorithm. Background technique [0002] According to the "35th China Internet Development Status Report" issued by the China Internet Network Information Center in January 2015, by the end of December 2014, 46.3% of the total Internet users in my country had encountered network security problems, indicating that personal Internet use in my country is limited. The security situation is not optimistic. With the increasingly prominent and serious network security problems, some traditional security defense technologies have been unable to do what they want. In order to solve the above problems, the research on network security situation...

AI Technical Summary

Problems solved by technology

[0005] The more commonly used models of statistical methods are: autoregressive model, moving average model and autoregressive moving average model. However, these models have the following limitations: the time series data is required to be stable, and if it is multiple regression, the variables are also required to be independent ; The gray prediction method is suitable for monotonically changing time series, and it is difficult to predict the time series with large fluctuations; in 1987, Lapdes et al. first applied the neural network to the learning and prediction of the time series simulation data generated by the computer, but the neural network exists Slow convergence speed, difficult structure selection, easy to fall into local minimum and other problems. At the same time, because the method is greatly affected by the complexity of network structure and sample complexity, the phenomenon of over-learning or low generalization ability will occur; Markov The model requires a large number of complex mathematical formula derivations, and it is difficult to establish an accurate prediction model; Support Vector Machine (SVM for short) is difficult to implement for large-scale training samples, and the convergence speed is slow

Images