改进的人工蜂群优化支持向量机算法在入侵检测中的应用

摘要

Aiming at the problem that the traditional parameters optimization algorithm may fall into locally optimal solution, a optimization method of parameter of Support Vector Machine (SVM) which applied Crossover Mutation Artificial Bee Colony(CMABC) is proposed to solve this problem and applied to intrusion detection, which is based on Artificial Bee Colony (ABC) algorithm.By introducing Crossover Mutation operator to improve ABC algorithm and dividing bee colony according to different fitness value, the locally optimal solution is effectively avoided and the convergence speed is improved.The standard test function is used to verify the effectiveness of the algorithm, what's more, the performance of the proposed algorithm is simulated by adopting NSL-KDD datasets of intrusion detection.Finally, the experimental results show that the proposed method is an efficient way to improve the classification performance of intrusion detection.%针对基于传统的参数优化算法在优化过程中会不同程度地陷入局部最优解的问题,在人工蜂群ABC(Artificial Bee Colony)算法的基础上提出基于交叉突变人工蜂群CMABC(Crossover Mutation ABC)算法的支持向量机SVM参数优化方法,并将其应用于入侵检测.通过引入交叉突变算子对人工蜂群算法进行改进,根据适应度值的优劣将蜂群进行划分,有效地避免了陷入局部最优,提高了收敛速度.利用标准测试函数验证了算法的有效性,并采用NSL-KDD入侵检测数据集进行仿真实验,验证了该方法的有效性.实验结果表明,该方法能有效提高入侵检测的分类性能.