随着网络技术的快速发展,网络入侵也越发频繁,而传统网络入侵检测技术存在偏差高、过早收敛等问题.因此,研究提出了一种基于二进制飞蛾扑火优化算法(Binary Moth-Flame Optimization integrated with Particle swarm optimization,BPMFO)的网络入侵检测模型.首先,通过对网络数据进行预处理,可以提取出代表网络入侵行为的特征;其次,通过BPMFO算法对特征进行优化;最后,利用飞蛾扑火算法(Moth-Flame Optimization,MFO)、飞蛾扑火优化算法(Moth-Flame Optimization integrat-ed with Particle swarm optimization,PMFO)和BPMFO在已知的攻击数据集中进行对比.结果表明,采用BPMFO算法可以有效地提高网络入侵检测的精度和效率.
Research on network intrusion detection based on BPMFO algorithm
With the rapid development of network technology,network intrusion has become more frequent,and the traditional network intrusion detection techniques have problems such as high bias and premature convergence.Therefore,the study proposes a network intrusion detection model based on the Binary Moth-Flame Optimization integrated with Particle swarm optimization(BPMFO)algorithm.Firstly,by prepro-cessing the network data,the features representing the network intrusion behavior can be extracted.Second-ly,the features are optimized by BPMFO algorithm.Finally,using Moth-Flame Optimization(MFO),Moth-Flame Optimization integrated with Particle swarm optimization,PMFO)and BPMFO in the known at-tack dataset for comparison.The results show that the use of BPMFO algorithm can effectively improve the accuracy and efficiency of network intrusion detection.
万方数据
维普
