蝙蝠算法优化最二乘支持向量机的网络入侵检测

Network intrusion detection based on least square support vector machine and bat algorithm

针对最小二支持向量机(LSSVM)参数选择难题,提出一种蝙蝠(BA)算法优化的LSSVM网络入侵检测模型(BA-LSSVM)。首先将LSSVM参数编码为蝙蝠个体,并以网络入侵检测正确率作为参数目标优化函数,然后通过模拟蝙蝠飞行过程找到LSSVM最优参数,最后根据最优参数建立网络入侵检测模型。在Matlab2012平台采用KDD CUP 99数据集进行仿真测试。仿真结果表明,相对于其它网络入侵检测模型,BA-LSSVM提高了网络入侵检测检测率,加快了网络入侵检测速度。

In order to obtain network intrusion detection rate,a novel network intrusion detection model based on least square support vector machine optimized by bat algorithm is proposed.Firstly,parameters of LSSVM are coded as bats individual,and network intrusion detection rate is taken as objection optimization function,and then the optimal parameters of the LSSVM are selected by simulating the bat flying,finally,network intrusion detection model is established according to the optimal parameters.The simulation test is carried out on the Matlab 2012 platform using KDD CUP 99 data sets,and the results show that the proposed mode has improved detection rate and intrusion detection speed compared with other network intrusion detection models.