基于人工蜂群算法的贝叶斯网络结构学习  

Structure learning of Bayesian networks by use of the artificial bee colony algorithm

作　　者：张平[1] 刘三阳[1] 朱明敏[1] 

机构地区：[1]西安电子科技大学数学与统计学院,陕西西安710071

出　　处：《智能系统学报》2014年第3期325-329,共5页CAAI Transactions on Intelligent Systems

基　　金：国家自然科学基金资助项目(61075055);西安电子科技大学基本科研业务基金资助项目(K5051270013)

摘　　要：从数据集中学习贝叶斯网络结构是一个NP难问题。针对此问题提出基于遗传算子的人工蜂群算法。首先,将贝叶斯网络结构映射为一种二进制编码;其次,根据贝叶斯网络的结构特点,设计了蜜源的更新策略,从而将学习贝叶斯网络结构的过程转化为蜂群寻找最优蜜源的过程。实验结果表明,该算法应用于贝叶斯网络结构学习中的有效性。The learning structure of Bayesian networks from a data set is an NP-hard problem. To deal with this problem,an artificial bee colony algorithm based on genetic operators is proposed in this paper. The structure of the Bayesian network is mapped to binary encoding,and the updated strategy of nectar is designed according to the characteristics of the Bayesian network structure. Thus the process of structure learning of the Bayesian network is transformed into the process of the bee colony finding the optimal nectar. The experimental results show that the algorithm is valid in the structure learning of Bayesian networks.

关 键 词：贝叶斯网络 NP难 人工蜂群算法 遗传算子 结构学习 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]