The parameter’s MCMC estimation of HMMs with transition density function
Chengwen Zhu, Yu Ge, Lina Lu, Zhang Tian, Chuizhen Zeng · Proceedings of the 2nd International Conference on Computer Science and Electronics Engineering (ICCSEE 2013) · 2013
The parameter estimation of HMM is critical to all its applications.The classic B-W algorithm is not flexible with the initial parameters and is easy to fall into the local optimal solution.Bayes estimation of it makes posterior risk minimization, and make full use of the experience, history information and other information other than samples, is useful in many cases.Employs the great computational power of MCMC, the MCMC estimation of HMM parameter can be more effective.