摘要
一般的交互式遗传算法只支持单用户评估,得到的结果只能反应单个用户的偏好,而交互式遗传算法设计的产品需要满足尽可能多的用户的需求.为此,提出一种适合于群体设计的多用户交互式遗传算法.给出了算法的三个主要模块——种群初始化模块、单种群模块和多种群模块的详细设计.最后,将该算法和一般的单用户交互式遗传算法分别应用于服装设计系统进行对比实验,验证了该算法在群体设计中的有效性.
General interactive genetic algorithms allow only one user to participate in evaluation for candidate solutions,so their results can only reflect one user＇s preference.But we should try to meet as many users＇ needs as possible when designing products.To solve this problem,a multi-user interactive genetic algorithm（MUIGA） applicable for group design was proposed.And the detailed design of the three key modules-population initialization module,single-population module and multi-population module was given.Finally,the proposed algorithm and the general single-user interactive genetic algorithm were applied to a fashion design system,respectively.The experimental results were compared to validate the feasibility of MUIGA in group design.
基金
国家自然科学基金委员会海外青年学者合作研究基金(60428202)资助
关键词
交互式遗传算法
多用户
种群初始化模块
单种群模块
多种群模块
群体设计
服装设计系统
interactive genetic algorithm
multi-user
population initialization module
single-population module
multi-population module
group design
fashion design system
