期刊
IEEE TRANSACTIONS ON FUZZY SYSTEMS
卷 22, 期 2, 页码 395-405出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TFUZZ.2013.2259496
关键词
Dempster-Shafer theory; evidence theory; evidential expectation-maximization ((EM)-M-2) algorithm; hidden Markov models (HMMs); partially supervised learning; soft labels; uncertain data
资金
- French National Center for Scientific Research under the administrative authority of the French Ministry of Research
- French Government, through the program Investments for the future [ANR-11-IDEX-0004-02, ANR-11-LABX-01-01]
This paper addresses the problem of parameter estimation and state prediction in hidden Markov models (HMMs) based on observed outputs and partial knowledge of hidden states expressed in the belief function framework. The usual HMM model is recovered when the belief functions are vacuous. Parameters are learned using the evidential expectation-maximization algorithm, a recently introduced variant of the expectation-maximization algorithm for maximum likelihood estimation based on uncertain data. The inference problem, i.e., finding the most probable sequence of states based on observed outputs and partial knowledge of states, is also addressed. Experimental results demonstrate that partial information about hidden states, when available, may substantially improve the estimation and prediction performances.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据