基于改进人工鱼群算法优化SVR的预测模型

Improved Artificial Artificial Fish Swarm Algorithm to Optimize SVR Prediction Model

为了降低参数的设定对支持向量机确度的影响,鉴于人工鱼群算法具有易陷入局部最优、收敛速度慢等问题,提出了一种基于改进人工鱼群算法(AFSA)的支持向量机的网络安全态势预测模型,并与GA-LSSVM、PSO-LSSVM及ABC-LSSVM模型进行对比分析。结果表明:文中提出的改进AFSA优化SVM模型性能优于其他比照模型,具有较高的预测精度,对网络安全态势值预测具有较好的效果。

In order to reduce the influence of parameter setting on the support vector machine accuracy,a new artificial fish swarm algorithm(AFSA)based support vector machine was proposed,in view of the problem that the artificial fish swarm algorithm was easy to fall into local optimum and the convergence speed is slow.The network security situation prediction model is compared with GASVM,PSO-SVM and ABC-SVM models.The results show that the improved AFSA optimized SVM model proposed in this paper is better than other comparison models and has higher prediction accuracy.It has a good effect on the prediction of network security situation value.