杜鹃鸟搜索算法优化最小二乘支持向量机的网络入侵检测模型
Network Intrusion Detection Model Based on Least Squares Support Vector Machine Optimized by Modify Cuckoo Search Algorithm
-
摘要: 为了提高网络入侵检测率,提出一种改进杜鹃鸟搜索(MCS)算法优化最小二乘支持向量机(LSSVM)的入侵检测模型(MCS-LSSVM)。首先将LSSVM的参数作为杜鹃鸟的鸟巢位置,然后通过模拟杜鹃鸟种群寄生繁衍机制,找到鸟巢最优位置,并转化成LSSVM最优参数,最后采用最优参数建立最优建立入侵检测模型,并采用KDD CUP 99数据集进行仿真测试。仿真结果表明,MCS-LSSVM不仅提高了网络入侵的检测率,而且减少了训练时间,提高网络入侵检测效果。Abstract: In order to improve detection rate of the network intrusion, this paper proposes a intrusion detection model (MCS-LSSVM)which the least square support vector machine (LSSVM) is optimized by improved cuckoo search(MCS) algorithm.Firstly,the parameters of LSSVM are taken as a nest location of cuckoo,and then the cuckoo species parasitic generation mechanism is used to find the optimal nest and transformed into LSSVM optimal parameters,finally,the optimal parameters is used to establish intrusion detection models.The simulation results show that the proposed model not only improves the detection rate of network intrusion,and shorten the training time to improve the network intrusion detection effect.
下载:
