摘要
本文在隐藏马尔科夫的基础上介绍了耦合隐藏马尔科夫模型,基于隐藏马尔科夫的算法计算了耦合隐藏马尔科夫模型的对数似然函数,提出了耦合隐藏马尔科夫模型的EM算法及Viterbi算法,用以估计模型的参数及隐藏状态序列,最后利用实例讨论了该算法的准确性及有效性.
This paper introduces the hidden Markov model and coupled hidden Markov model.We calculate the log likelihood function of coupled hidden Markov model on the basis of hidden Markov model, and propose EM algorithm and Viterbi algorithm to estimate the parameters of the model and the hidden state series. In addition, we apply certain example to discuss the accuracy and effectiveness of this algorithm.
作者
胡淑兰
张璇
李慧菁
HU Shulan;ZHANG Xuan;LI Huijing(Zhongnan University of Economics and Law (School of Statistics and Mathematics), Wuhan 430073,China;Shanghai University of Finance and Economics (School of Statistics and Management), Shanghai 200433, China)
出处
《应用数学》
CSCD
北大核心
2018年第2期449-456,共8页
Mathematica Applicata
基金
国家社科基金资助(17BTJ034)