Estimating the relative proportions of SARS-CoV-2 strains from wastewater samples

Wastewater surveillance has become essential for monitoring the spread of SARS-CoV-2. The quantification of SARS-CoV-2 RNA in wastewater correlates with the Covid-19 caseload in a community. However, estimating the proportions of different SARS-CoV-2 strains has remained technically difficult. We present a method for estimating the relative proportions of SARS-CoV-2 strains from wastewater samples. The method uses an initial step to remove unlikely strains, imputation of missing nucleotides using the global SARS-CoV-2 phylogeny, and an Expectation-Maximization (EM) algorithm for obtaining maximum likelihood estimates of the proportions of different strains in a sample. Using simulations with a reference database of >3 million SARS-CoV-2 genomes, we show that the estimated proportions accurately reflect the true proportions given sufficiently high sequencing depth and that the phylogenetic imputation is highly accurate and substantially improves the reference database.

The Discrete Gaussian Expectation Maximization (Gradient) Algorithm for Differential Privacy

In this paper, we give a modified gradient EM algorithm; it can protect the privacy of sensitive data by adding discrete Gaussian mechanism noise. Specifically, it makes the high-dimensional data easier to process mainly by scaling, truncating, noise multiplication, and smoothing steps on the data. Since the variance of discrete Gaussian is smaller than that of the continuous Gaussian, the difference privacy of data can be guaranteed more effectively by adding the noise of the discrete Gaussian mechanism. Finally, the standard gradient EM algorithm, clipped algorithm, and our algorithm (DG-EM) are compared with the GMM model. The experiments show that our algorithm can effectively protect high-dimensional sensitive data.

Lognormal and log-logistic distribution mixture analysis and application

In this paper, we analyze a mixture of Lognormal and Log-Logistic distribution. We estimate the parameters of the introduced distribution by using the expectation-maximization (EM) algorithm. Various phenomena in the field of medicine and economy could be modeled by this mixture. In this paper, it is used to construct new mortality model for determining the unisex premium rates in life insurance. The application of the model is illustrated in the case of Serbian population and its advantages are presented in the context of life insurance premium calculation.

Application of EM-Algorithm for Approximation of Correlated Traffic Probabilities Density by Hyperexponents

An accurate assessment of the quality of service parameters in modern information communication networks is a very important task. This paper proposes the use of hyperexponential distributions to solve the problem of approxi-mating an arbitrary probability density in the G/G/1 system for the case when the approximation by a system of the type H2/H2/1 is assumed. To determine the parameters of the probability density of the hyperexponential distribu-tion, it is proposed to use EM- algorithm that provides fairly simple use cases for uncorrelated flows. In this paper, we propose a variant of the EM algorithm implementation for determining the parameters of the hyperexponential distribution in the presence of correlation properties of the analyzed flow.

Fast Computation of the EM Algorithm for Mixture Models

Mixture models become increasingly popular due to their modeling flexibility and are applied to the clustering and classification of heterogeneous data. The EM algorithm is largely used for the maximum likelihood estimation of mixture models because the algorithm is stable in convergence and simple in implementation. Despite such advantages, it is pointed out that the EM algorithm is local and has slow convergence as the main drawback. To avoid the local convergence of the EM algorithm, multiple runs from several different initial values are usually used. Then the algorithm may take a large number of iterations and long computation time to find the maximum likelihood estimates. The speedup of computation of the EM algorithm is available for these problems. We give the algorithms to accelerate the convergence of the EM algorithm and apply them to mixture model estimation. Numerical experiments examine the performance of the acceleration algorithms in terms of the number of iterations and computation time.

Univariate and bivariate extensions of the generalized exponential distributions

The main aim of this paper is to introduce a new class of continuous generalized exponential distributions, both for the univariate and bivariate cases. This new class of distributions contains some newly developed distributions as special cases, such as the univariate and also bivariate geometric generalized exponential distribution and the exponential-discrete generalized exponential distribution. Several properties of the proposed univariate and bivariate distributions, and their physical interpretations, are investigated. The univariate distribution has four parameters, whereas the bivariate distribution has five parameters. We propose to use an EM algorithm to estimate the unknown parameters. According to extensive simulation studies, we see that the effectiveness of the proposed algorithm, and the performance is quite satisfactory. A bivariate data set is analyzed and it is observed that the proposed models and the EM algorithm work quite well in practice.

Implementation of EM Algorithm in Opinion Mining Movies Review Case Studies

Movies are very familiar to everyone, from children, adolescents to adults, whether just because they want to watch, a hobby, or fill their spare time. Movies that used to be watched only on television and had to wait months after release or directly to the cinema, with the development of technology, of course, it is increasingly easier for everyone to enjoy movies, now they can be watched through paid television services to smartphones. One of the websites that viewers often use to review movies they have watched is IMDb. The data review can be used to get an opinion or opinion mining from the audience, whether the title of the movie being reviewed is good or not. One of the algorithms that are often used is Naïve Bayes, apart from being easy to implement, Naïve Bayes is also known to be very fast and easy to use to predict classes on a test dataset. The purpose of this study is to see how much influence the Expectation-Maximization to increase accuracy on implementation of Expectation-Maximization algorithm in opinion mining movies review case studies. From the results of this study using the Expectation-Maximization method, it was found that the accuracy increased by 4% compared to using only Naïve Bayes.