Abstract: Concerning the clustering optimization in intrusion detection, Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) were used to optimize clustering and comparative analysis was also completed. In this analysis, binary code was adopted and elimination criterion took the account of the maximum number of iteration and the quality of convergence. Fitness function which combines the characteristic of jnter-cluster distance and intra-cluster distance was defined. Finally, the experiments with KDDCUP 1999 data set using Matlab 6.5 tools show that PSO is superior to GA in the value and speed of fitness function convergence.

Key words: genetic algorithm, particle swarm optimization, intrusion detection, clustering, evolution, optimization

摘要： 针对入侵检测中的聚类最优化问题,使用遗传算法和粒子群算法的优化特性进行全局最优化并作对比分析。分析采用二进制编码,终止条件同时考虑最大迭代次数和收敛度,适应度函数的定义结合了类内距和类间距的特征。最后使用KDD CUP1999数据集在Matlab 6.5中进行了仿真。实验结果表明粒子群算法在适应度的收敛值和收敛速度上均优于遗传算法。

关键词: 遗传算法, 粒子群算法, 入侵检测, 聚类, 进化, 最优化