关于克隆选择算法优化检测器的研究

Study on Detector Optimization in Clonal Selection Algorithm

否定选择算法能降低入侵检测系统的误报率,但必须和其他免疫算法结合起来使用.本文提出了一种含有否定选择算子和遗传算子的克隆选择算法,通过克隆选择算法产生多样子代检测器,并且从中选择比其父代更优的检测器去取代父代检测器,这样一代一代循环,使检测系统具有更好的覆盖空间.实验表明,该算法在提高检测率,降低误报率方面是有效的.

Though negative selection algorithm can improve detection rate of the intrusion detection system, it must be used with other immune - algorithms. This paper proposes a clonal selection algorithm with negative selection operator and genetic operator. The new clonal algorithm could produce various detectors, choose superior detectors to substitute for its parent generation detectors and iterate like this. The iteration enables the detection system to have better covering space. The results from the corresponding experiments show that the algorithm is efficient in increasing correctness and decreasing misdiagnoses.