Network Security Situation Assessment Based on PCA-IFOA-PNN
Huan Wang, Lejiang Guo, Hao Lü, Jingxiang Gao · 2023
At present, all kinds of trained neural networks have been widely used in network security situation assessment, but there are some problems such as slow convergence speed and low assessment accuracy. Aiming at the problem of network security situation assessment based on the existing neural network, a network security situation assessment method based on improved probabilistic neural network is proposed. Firstly, the original collected network situation data is processed, and the principal component analysis (PCA) is used to reduce the data dimension. Secondly, the improved fruit fly optimization algorithm (IFOA) is used to optimize the smoothing factor of probabilistic neural network (PNN). Finally, the network security situation is assessed by the optimized PNN. Experiments demonstrate that the proposed method is more accurate than the traditional neural network for network security situation assessment, and the training speed is faster.