SUMMARY In this article we investigate the relationship between the two popular algorithms, the EM algorithm and the Gibbs sampler. We show that the approximate rate of convergence of the Gibbs sampler by Gaussian approximation is equal to that of the corresponding EM type algorithm. This helps in implementing either of the algorithms as improvement strategies for one algorithm can be directly ...

An optimal maximal ratio combiner (MRC) based on the expectation-maximization (EM) algorithm is developed for noisy constant envelope signals transmitted over a Rayleigh fading channel. Instead of using a transmitted pilot signal with the data to estimate the combiner gains, the EM algorithm is used to perform this estimation. In the developed MRC, estimation of the transmitted data sequence is...

In this correspondence, we compare the expectation maximization (EM) algorithm with another iterative approach, namely, the iterative conditional estimation (ICE) algorithm, which was formally introduced in the field of statistical segmentation of images. We show that in case the probability density function (PDF) belongs to the exponential family, the EM algorithm is one particular case of the...

In this paper, a new design algorithm for estimating the parameters of Gaussian Mixture Models is presented. The method is based on the matching pursuit algorithm. Speaker Identification is considered as an application area. The estimated GMM performs as good as the EM algorithm based model. Computational complexity of the proposed method is much lower than the EM algorithm.

This laboratory explores the use of the expectation-maximization (EM) algorithm for the estimate of parameters. In particular, we will use the EM algorithm for two applications: clustering, and hidden Markov model training. You are encouraged to implement your solutions to this laboratory in Matlab. For an original derivation of the monotone convergence of the likelihood for the EM algorithm, t...

In data mining applications, there are various kinds of missing values in experimental datasets. Non-substitution or inappropriate treatment of missing values has a high probability to cause a lot of warnings or errors. Besides, many classification algorithms are very sensitive to the missing values. Because of these, handling the missing values is an important phase in many classification or d...

We examine methods for clustering in high dimensions. In the first part of the paper, we perform an experimental comparison between three batch clustering algorithms: the Expectation–Maximization (EM) algorithm, a “winner take all” version of the EM algorithm reminiscent of the K-means algorithm, and model-based hierarchical agglomerative clustering. We learn naive-Bayes models with a hidden ro...

Recently, mobile location estimation is drawing considerable attention in the field of wireless communications. Among different mobile location estimation methods, the one which estimates the location of mobile stations with reference to the wave propagation model is drawing much attention on the grounds that it is applicable to different kinds of cellular network. However, the signal propagati...

It is well known that the likelihood sequence of the EM algorithm is nondecreasing and convergent (Dempster, Laird and Rubin (1977)), and that the limit points of the EM algorithm are stationary points of the likelihood (Wu (1982)), but the issue of the convergence of the EM sequence itself has not been completely settled. In this paper we close this gap and show that under general, simple, ver...

As an automatic method of determining model complexity using the training data alone, Bayesian linear regression provides us a principled way to select hyperparameters. But one often needs approximation inference if distribution assumption is beyond Gaussian distribution. In this paper, we propose a Bayesian linear regression model with Student-t assumptions (BLRS), which can be inferred exactl...