摘要
离散动态贝叶斯网络参数学习的难点在于:隐藏节点的片间转移概率获得及观测数据发生不同程度缺失。针对上述问题,提出基于目标缺失数据估计的前向递归参数学习算法。该算法利用离散动态贝叶斯网络中各观测变量与隐藏变量之间的对应关系,采用支持向量机建立观测变量间的非线性函数关系完成缺失数据估计,此基础上利用完整数据集和前向递归算法完成片内和片间参数更新。以空中目标识别为仿真背景,通过与期望最大算法对比,验证了该算法的学习效率和精度两个方面的优势。
The difficulty of discrete dynamic Bayesian network parameter learning lies in: obtaining the transition probability of hidden nodes between slices,lack of observational data in varying degrees.Focusing on the above problems,the forward recursive parameters learning algorithm based on target data missing estimation is proposed.The algorithm uses the correspondent relation between the observed variables and hidden variables in discrete dynamic Bayesian network,using support vector machine to establish a nonlinear function between observed variables for completing the missing data estimation.A complete data set and the forward recursive algorithm are applied to complete parameters updating in inter-slice and in-slice.On the background of aerial target recognition,the advantages of the proposed method at efficiency and accuracy are illustrated compared with the expectative maximization method.
出处
《系统工程与电子技术》
EI
CSCD
北大核心
2011年第8期1885-1890,共6页
Systems Engineering and Electronics
基金
国家自然科学基金(60774064)资助课题
关键词
参数学习
离散动态贝叶斯网络
数据缺失
前向递归
parameter learning
discrete dynamic Bayesian network
data missing
forward recursion