交互式遗传算法中用户评估方法研究

RESEARCH ON USER EVALUATION APPROACHES IN INTERACTIVE GENETIC ALGORITHMS

交互式遗传算法是针对一些应用领域存在的适应度函数难以明确表达的问题 ,通过用户参与遗传操作过程 ,对进化个体进行评估以代替计算过程的一种改进方法 .但交互式遗传算法存在的一个主要问题是当遗传操作的收敛速度慢时 ,用户需对大量个体进行评估 ,尤其是在个体间相似程度较高时 ,容易产生疲劳现象 .针对这种问题 ,本文提出了两种方法来提高收敛性 ,缩短评估过程 ,从而最终解决用户疲劳问题 .

Interactive GA is an improved method well suited for solving the problem whose fitness function is hard to express explicitly,while evaluation of individuals is easy for users to perform .However there exists a significant problem for IGA which is that users have to evaluate large number of individuals when the convergence speed of genetic operations is too slow.Furthermore,users tend to be tired especially when the similarity among some individuals is relatively high.To deal with this problem,two approaches are proposed to speed up the evaluation process to improve the convergence and thus the problem of tiredness for users can be solved.The experimental results obtained on the problems of human face recognition show that our approaches can effectively solve the problem.