贝叶斯网络结构学习的蜂群算法  

Learning Bayesian Network Structure Base on Artificial Bee Colony Algorithm

作　　者：汪春峰[1] 靳利[2] 

机构地区：[1]河南师范大学数学与信息科学学院,河南新乡453007 [2]河南机电高等专科学校基础部,河南新乡453000

出　　处：《小型微型计算机系统》2014年第6期1417-1421,共5页Journal of Chinese Computer Systems

基　　金：国家自然科学基金项目(11171094)资助;国家级科研项目培育基金(2013PL02)资助;河南师范大学博士科研启动课题项目(qd12103)资助;河南师范大学校级骨干教师培养项目资助;河南省科技攻关研究计划项目(142102210058)资助;河南师范大学青年科学基金项目(2013qk02)资助

摘　　要：因贝叶斯网构建的核心是贝叶斯网络结构学习,所以如何有效的进行结构学习就成为了构建最优贝叶斯网络结构的基础.针对贝叶斯网络结构学习问题,首先通过利用贝叶斯网络结构本身所具有的表示特性,构造并求解一无约束优化问题,对所要搜索的网络结构空间规模进行缩减;然后,制定一些蜂群算法在结构空间中可进行搜索的基本规则,提出了应用于了贝叶斯网络结构学习的蜂群算法.由于蜂群算法是在缩减后的空间中搜索最优贝叶斯网络结构的,所以算法的效率比较高.数值试验显示本文方法具有很好的学习能力,可以在较短时间内学习到精度较高的贝叶斯网络结构.Since bayesian network structure learning plays a very important role in the processing of Bayesian network＇s construction, an effective structure learning algorithm is the base of constructing the optimum Bayesian network. For Bayesian network structure learning problem, by utilizing its characterization and constructing an unconstrained optimization problem, the searching space is reduced firstly; then, through developing some basic rules which can guarantee Artificial Bee Colony （ ABC ） algorithm to search in the space of network structure, ABC algorithm is first used to learn Bayesian network structure. Since this algorithm searchs the optimal Bayesian network structure in the reduced space, the efficiency is relatively high. Numerical experiments show that this method has good learning ability, and can learn the Bayesian network structure with high accuracy in a short period of time.

关 键 词：人工蜂群算法 贝叶斯网络结构学习 无约束优化 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]