摘要： 静态克隆选择算法用于产生检测特定“非我”的检测器。该文通过引入亲和力阈值参数改进静态克隆选择算法，使其匹配规则能够灵活表示“或”关系，且只须部分匹配即可高效提取能识别“非我”的部分样本特征。自我/非我区别的模拟实验结果表明，与静态克隆选择算法相比，该算法能更有效地产生部分分类规则。

关键词: 人工免疫系统, 克隆选择, 匹配规则, 亲和力阈值

Abstract: Static Clonal Selection Algorithm(SCSA) is proposed to generate detectors to intrusion detection. By combining gene expression with partial match rule which is important in negative selection algorithm, this paper presents a new expression which can express classification rules with OR operator. Based on the proposed expression, an augmented SCSA is proposed. It is tested by simulation experiment for self/nonself discrimination. Results show that the algorithm with optimized match threshold spends less time and is more effective to generate detector with partial classification rules than SCSA, which generates detector with full conjunctive rules with ‘and’.

Key words: artificial immune system, clonal selection, match rule, optimized match threshold

中图分类号: 

• TP301.6