摘要
研究了一种群智能优化神经网络算法的网络流量检测模型。使用QAPSO算法对RBF神经网络的基函数中心、基函数的宽度以及输出层与隐含层的连接权值进行优化。通过实例对该文研究的检测模型进行分析,使用采集的数据对网络流量识别系统进行训练和性能测试。将该文的研究方法和基于常规PSO算法、基于HPSO算法进行对比,结果表明,该文研究的检测方法具有更快的识别速度以及更好的识别准确率,避免了出现陷入局部最优解的情况发生。
The application of swarm intelligence optimizing neural network in network security and a network traffic detec- tion model based on neural network algorithm are studied in this paper. QAPSO algorithm is Used to optimize the basis function center and base function width of RBF neural network, and the connection weights of the output layer and the hidden layer as well. The detection model studied in this paper is analyzed by means of an example. The collected data is used to train the net- work traffic identification system and test its performance. The method researched in this paper is compared with the algorithms based on the conventional PSO and HPSO. The results show that the detection method has a faster recognition speed and better recognition accuracy, and can avoid the occurrence of local optimal solutions.
出处
《现代电子技术》
北大核心
2016年第20期12-14,19,共4页
Modern Electronics Technique
基金
国家自然科学基金(60873139)
关键词
网络流量检测
群智能算法
RBF神经网络
网络安全
network traffic detection
swarm intelligence algorithm
RBF neural network
network security
