the forecasting of hydrological variables, such as streamflow, plays an important role in water resource planning and management. recently, the development of stochastic models is regarded as a major step for this purpose. streamflow forecasting using the arima model can be conducted when unknown parameters are estimated correctly because parameter estimation is one of the crucial steps in mode...

The article considers a new approach for small area estimation based on a joint modelling of mean and variances. Model parameters are estimated via expectation–maximization algorithm. The conditional mean squared error is used to evaluate the prediction error. Analytical expressions are obtained for the conditional mean squared error and its estimator. Our approximations are second-order correc...

Information geometry of partial likelihood is constructed and is used to derive the em-algorithm for learning parameters of a conditional distribution model through information -theoretic projections. To construct the coordinates of the information geometry, an Expectation-Maximization (EM) framework is described for the distribution learning problem using the Gaussian mixture probability model...

Iterative image reconstruction algorithms have been widely used in the field of positron emission tomography (PET). However, such algorithms are sensitive to noise artifacts so that the reconstruction begins to degrade when the number of iterations is high. In this paper, we propose a new algorithm to reconstruct an image from the PET emission projection data by using the conditional entropy ma...

We propose a new algorithm for semi-supervised learning in the bipartite ranking framework. It is based on the maximization of a so-called normalized Rayleigh coefficient, which differs from the usual Rayleigh coefficient of Fisher’s linear discriminant in that the actual covariance matrices are used instead of the scatter matrices. We show that if the class conditional distributions are Gaussi...

Data noise is present in many machine learning problems domains, some of these are well studied but others have received less attention. In this paper we propose an algorithm for constructing a kernel Fisher discriminant (KFD) from training examples with noisy labels. The approach allows to associate with each example a probability of the label being flipped. We utilise an expectation maximizat...

In an earlier paper we provided easily-calculated expressions for the gradient of the profiled log-likelihood and log-restricted-likelihood for single-level mixed-effects models. We also showed how this gradient is related to the update of an ECME (expectation conditional maximization either) algorithm for such single level models. In this paper we extend those results to mixed-effects models w...

In this paper we present a statistical transliteration technique that is language independent. This technique uses statistical alignment models and Conditional Random Fields (CRF). Statistical alignment models maximizes the probability of the observed (source, target) word pairs using the expectation maximization algorithm and then the character level alignments are set to maximum posterior pre...

We propose a general approach for estimating the parameters of latent variable probability models to maximize conditional likelihood and discriminant criteria. Unlike joint likelihood, these objectives are better suited for classiication and regression. The approach utilizes and extends the previously introduced CEM framework (Conditional Expectation Maximization), which reformulates EM to hand...