This paper proposes a variant of EM (expectation-maximization) algorithm for Markovian arrival process (MAP) and phase-type distribution (PH) parameter estimation. Especially, we derive the deterministic annealing EM ...
详细信息
This paper proposes a variant of EM (expectation-maximization) algorithm for Markovian arrival process (MAP) and phase-type distribution (PH) parameter estimation. Especially, we derive the deterministic annealing EM (daem) algorithm for MAP/PH parameter estimation. The daem algorithm is one of the methods to overcome a local maxima problem associated with the conventional EM algorithm. This paper derives concrete E- and M-step formulas for MAP parameter estimation from inter-arrival time data and PH parameter estimation from point samples in the framework of daem algorithm. Numerical examples demonstrate the daem algorithm for Markov-modulated Poisson process (MMPP) and several classes of PH distribution.
In this paper, a new method is proposed for the probabilistic load flow calculation in power systems. The proposed method is based on a hybrid technique that consists of Markov Chain Mont Carlo (MCMC), deterministic a...
详细信息
ISBN:
(纸本)9781612848570
In this paper, a new method is proposed for the probabilistic load flow calculation in power systems. The proposed method is based on a hybrid technique that consists of Markov Chain Mont Carlo (MCMC), deterministic annealing expectation maximization (daem) algorithm to evaluate the effect of uncertainties of input variables on the output ones and in the nonlinear load flow. MCMC is useful for generating the samples from an arbitrary probabilistic distribution function (PDF) to reflect the non-Gaussian PDF and the nonlinear correlation. daem evaluates the maximum likelihood estimate of the non-Gaussian PDF. The proposed method is successfully applied to a sample system.
This paper investigates the effectiveness of the daem (Deterministic Annealing EM) algorithm in acoustic modeling for speaker and speech recognition. Although the EM algorithm has been widely used to approximate the M...
详细信息
This paper investigates the effectiveness of the daem (Deterministic Annealing EM) algorithm in acoustic modeling for speaker and speech recognition. Although the EM algorithm has been widely used to approximate the ML estimates, it has the problem of initialization dependence. To relax this problem, the daem algorithm has been proposed and confirmed the effectiveness in artificial small tasks. In this paper, we applied the daem algorithm to practical speech recognition tasks: speaker recognition based on GMMs and continuous speech recognition based on HMMs. Experimental results show that the daem algorithm can improve the recognition performance as compared to the standard EM algorithm with conventional initialization algorithms, especially in the flat start training for continuous speech recognition.
暂无评论