摘要
针对支持向量机(SVM)应用于网络入侵检测时特征选择及分类器参数优化问题,利用改进的二进制量子引力搜索算法(IBQGSA)对入侵特征集及SVM参数进行组合寻优。将入侵特征集及SVM参数看作是二进制量子引力搜索算法中的量子个体并进行组合编码,在使用量子旋转门更新个体位移时,引入动态的位移更新策略,确保算法收敛到全局极值,设计与进化程度及个体适应度值相关的自适应变异概率,提升量子非门变异操作时算法的自适应变异能力。利用KDD CUP 99数据集进行仿真实验,实验结果表明,所提算法能有效地获取最佳特征子集及分类器参数组合,检测效果更好。
Aiming at problems of the feature selection and parameter optimization of SVM in the network intrusion detection, the improved binary quantum-inspired gravity search algorithm （IBQGSA） was used to optimize the combination of the intrusion feature set and the SVM parameter. The intrusion feature set and SVM parameter were encoded into a quantum individual. The dynamic displacement update strategy was introduced to ensure that the algorithm converged to the global extremum when the quantum rotation gate was used to update the individual displacement, and the adaptive mutation probability based on population evolutionary degree and individual fitness value was designed to improve the adaptive mutation ability when the quantum non-gate was used to implement the mutation operation. Experiments were carried out on KDD CUP 99 data sets, results of the simulation show that the proposed algorithm can obtain the best combination of feature subset and classifier parameter and can get better detection results.
作者
李丛
闫仁武
丁勇
王云
LI Cong YAN Ren-wu DING Yong WANG Yun(Taizhou Institute of Science and Technology, Nanjing University of Science and Technology, Taizhou 225300, China School of Computer Science and Engineering, Jiangsu University of Science and Technology, Zhenjiang 212003, China)
出处
《计算机工程与设计》
北大核心
2017年第8期2227-2234,共8页
Computer Engineering and Design
基金
国家自然科学基金项目(61305058)
江苏省自然科学基金项目(15KJB520016)
关键词
二进制量子引力搜索
支持向量机
特征选择
参数优化
入侵检测
improved binary quantum-inspired gravity search algorithm
support vector machine
feature selection
parameter optimization
intrusion detection
