摘要
对多目标组合优化的组卷问题,借鉴生物免疫系统原理中抗体多样性产生及保持机理,定义多目标选择熵和浓度调节选择概率概念,利用自适应免疫遗传算法,运用抗体克隆、高变异策略,实现组卷问题的多目标优化。该算法充分体现了pareto最优解的概念,具有并行搜索及个体编码长度动态调整、pareto最优个体保存于群体外(免疫记忆)并不断更新等特点。
An algorithm is proposed to solve grouping test paper by using optimization of compounding multiobjective. In order to do so, this paper introduces the mechanism of producing and preserving the diversity of antibodies in organismal immune system into evolutionary algorithm. The conceptions of multiobjective selection entropy and selection probability based on concentration adjustment are defined, and strategies of antibody clonal selection and high are introduced. This algorithm fully realizes conception of optimal pareto, and is characterized by parallel search and dynamic adjustment of length of individual coding, optimal pareto individual storing outside mass(immune memory) and constant modification.
出处
《计算机工程》
CAS
CSCD
北大核心
2008年第14期203-205,215,共4页
Computer Engineering
基金
山西省教育科学"十一五"规划课题基金资助项(GH-06206)
关键词
人工免疫系统
多目标优化
进化计算
artificial immune system
multiobjective optimization
evolutionary algorithm