摘要
通过对当前自动组卷方法的分析,将小生境技术引入到遗传算法自动组卷中,以期望解决遗传算法组卷的早熟问题,提出一种基于小生境遗传算法的组卷方法.该方法采用功能段结构的整数编码方式,可以克服常规采用二进制编码搜索空间过大和编码长度过长的缺点,提高求解速度和精度,同时减少迭代次数加快算法收敛.在组卷模型中以题型、题量和分值为基础,在形成初始种群和进化的过程中始终保持题型、题量和分值不变,从而简化优化目标.试验结果显示,该方法能有效限制种群中相似个体的过多复制,从而维持群体的多样性,抑制出现早熟现象,改进遗传算法在自动组卷中应用的效率,其运行时间更短,误差更小.
The niche technology was introduced into auto-generating test papers with genetic algorithm by means of analyzing the method of present auto-generating test paper in anticipation of solving the problem of prematurity of test paper with genetic algorithm,so that a test papers method was presented on the basis of niche genetic algorithm.In this method the integer coding mode with function-block structure was used to eliminate the defect of excessive searching space and code length in the conventional binary coding mode, and the speed as well as the accuracy of solution was improved. Meantime, the number of iteration cycle was decreased and the convergence accelerated. In the test papers model, the subject type, subject amount, and score value were taken as a basis and they were kept unchanged all the time during the process of initial species group formation and evolution, so that the optimization object was simplifieck Experimental result showed that this method was able to prevent successfully the excessive similar individuals in the species group from duplicating, keep the variety of the group, and restrain the occurrence of premature phenomenon. The efficiency of genetic algorithm application in auto-generating test papers was improved, operational time was even shorter, and error was even less.
出处
《兰州理工大学学报》
CAS
北大核心
2009年第4期94-97,共4页
Journal of Lanzhou University of Technology
关键词
遗传算法
整数编码
自动组卷
小生境
genetic algorithm
integer coding
auto-generating test papers
niche
