自适应检测器生成算法研究

Algorithmic research on generating adaptive detectors

基于小生境策略的否定选择算法利用在搜索空间中计算检测器之间的海明距离,构建小生境;一个与亲合力函数相关的适应度函数的提出,能更客观地反映各检测器的匹配能力,即能更准确地反映检测器集合的检测能力;利用进化策略,进行遗传操作,而生成多样性和通用性的最佳检测器集。同时该算法可以减少生成检测器的时间开销。

A negative selection algorithm with niching strategy can generate diversity and generality of detector sets. By calculating Hamming distance between two arbitrary detectors in search space, niching of detectors is built. A new approach to define the fitness function is proposed. The fitness function is a relational function of the detector＇s affinity function. And computational time can be reduced.