机器组卷问题的遗传-蚂蚁算法研究  

Algorithm study based on genetic algorithm and ant algorithm in auto-generating examination paper

作　　者：雷虎[1] 尹树华[1] 

机构地区：[1]西安翻译学院,陕西西安710105

出　　处：《电子设计工程》2014年第12期37-40,共4页Electronic Design Engineering

基　　金：陕西高等教育教学改革研究(重点)项目资助(13BZ69)

摘　　要：计算机智能组卷的关键技术在于组卷算法,蚂蚁算法在初期信息素缺乏导致搜索时间较长;遗传算法需要在一组解中寻找最优解而产生大量的重复数据,导致算法效率较低。为了开发出一个具有高效性和鲁棒性的组卷算法,提出了一种融合遗传算法与蚂蚁算法的机器组卷算法,算法利用遗传算子操作的全局收敛快的特点,将最优结果作为蚂蚁算法的初始信息素分布,按照蚂蚁算法的并行反馈信息、求解效率高的特点进行信息更新求得最优解,优势互补。实验表明,算法在收敛性和寻优性都有很好的效果。The key of Computer auto-examination system lies on Auto-generating Examination Paper algorithm, pheromone lack of Ant algorithm in the initial leads to search for a long time, Genetic algorithm needing to find the optimal solution in a set of solutions will generate a large amounts of duplicate data, and algorithm efficiency is low.In order to achieve the efficient Auto-generating Examination Paper algorithm, this paper proposes a algorithm based on genetic algorithm and ant algorithm, to obtain the optimal results by speed of genetic operator as the initial information of ant algorithm and to update the information according to the ant algorithm of parallel feedback information, the efficiency high characteristic, finding the optimal solution . Simulation shows that the algorithm has a good effect in convergence and optimization.

关 键 词：遗传算法 蚂蚁算法 融合 机器组卷 

分 类 号：TN911[电子电信—通信与信息系统]