Purpose: hidden caries is a term used to describe occlusal dentine caries that is missed on a visual examination, but can be detected by bitewing radiographs. The aim of this study is the review of new studies about this lesion and presentation the ways for diagnosis, prevention and treatmen of this lesion.Review of Literature: Investigations believe that the etiology of this lesion is the morphology of occlusal fissures and also topical fluoride use. Diagnosis of hidden caries is difficult and need to use the diagnostic tools such as bitewing radiographs. Investigators have shown the prevalence of hidden caries is between 1.4% to 15% of occlusal surfaces of permanent molars that have diagnosed as sound teeth. Prevention of this lesion is taken by fissure sealing soon after eruption and treatment is taken by amalgam or composite restoration. It is suggested to investigate about the prevalence of hidden caries in our country.

Background: Routinely collected data from tuberculosis surveillance system can be used to investigate and monitor the irregularities and abrupt changes of the disease incidence. We aimed at using a hidden Markov model in order to detect the abnormal states of pulmonary tuberculosis in Iran.Methods: Data for this study were the weekly number of newly diagnosed cases with sputum smear-positive pulmonary tuberculosis reported between April 2005 and March 2011 throughout Iran. In order to detect the unusual states of the disease, two hidden Markov models were applied to the data with and without seasonal trends as baselines.Consequently, the best model was selected and compared with the results of Serfling epidemic threshold which is typically used in the surveillance of infectious diseases.Results: Both adjusted R-squared and Bayesian Information Criterion (BIC) reflected better goodness-of-fit for the model with seasonal trends (0.72 and -1336.66, respectively) than the model without seasonality (0.56 and -1386.75).Moreover, according to the Serfling epidemic threshold, higher values of sensitivity and specificity suggest a higher validity for the seasonal model (0.87 and 0.94, respectively) than model without seasonality (0.73 and 0.68, respectively).Conclusion: A two-state hidden Markov model along with a seasonal trend as a function of the model parameters provides an effective warning system for the surveillance of tuberculosis.

Background: The liver is the largest internal organ and the most important organ after heart and brain in the human body without which life is impossible. Diagnosis of liver disease requires a long time and sufficient expertise of the doctor. Statistical methods can be classified as an automated forecasting system and help specialists for quickly and accurately diagnose liver disease. hidden Markov model is an intelligent and robust statistical method that has been used in present study.Methods: The data used in this cross sectional study collected from records of patients with five different types of liver diseases, including cirrhosis, liver cancer, acute hepatitis, chronic hepatitis, and fatty liver disease. The patients have been admitted to Afzalipour hospital in Kerman, Iran, from 2006 to 2013. hidden Markov model using EM algorithm for learning was fitted to the data and for evaluating the performance of the model, criteria as accuracy, sensitivity and specificity were used.Results: The decision, sensitivity, and specificity criteria of the model for diagnosis of each liver disease were separately calculated and the highest level criteria in diagnosis of cirrhosis of the liver were 77% decision, 82% sensitivity, and 96% specificity, and also the lowest level of diagnosis for fatty liver disease was 65% decision, 69% sensitivity and 94% specificity.Conclusion: The results of this study indicate the potential capabilities of the hidden Markov model. Therefore, using hidden Markov model for prediction of diagnosis of liver disease is recommended.

hidden Markov models are widely used in Bioinformatics. They are applied to protein sequence alignment, protein family annotation and gene-finding. The Baum-Welch training is an expectation-maximization algorithm for training the emission and transition probabilities of hidden Markov odels. For very long training sequence, even the most efficient algorithms are memory-consuming. In this paper we discuss different approaches to decrease the memory use and compare the performance of different algorithms. In addition, we propose a bidirection algorithm with linear memory. We apply this algorithm to simulated data of protein profile to analyze the strength and weakness of the algorithm.

Due to the effective role of Markov models in customer relationship management (CRM), there is a lack of comprehensive literature review which contains all related literatures. In this paper the focus is on academic databases to find all the articles that had been published in 2011 and earlier. One hundred articles were identified and reviewed to find direct relevance for applying Markov models in CRM. Forty four articles were selected and categorized on two major subclasses: articles which had used Markov chain models (MCM) in CRM and those which had applied hidden Markov models (HMM) in CRM. Findings of this paper indicate that applying HMM in CRM is approximately rare, since it contains 27.2% of the total number of published articles. To complete investigation a two-step framework has been suggested for using HMM in busy customer portfolio management. It is for the first time that two important concepts (busy customer and HMM) are used to achieve a common goal. Also the model parameters have been estimated in order to analyze a real firm’s data.

In this paper, we propose an improved version of ID-HMM for face verification. DCT coefficients of face images are used as observation vectors in HMM states. Three types of modifications have been proposed to improve the overall performance of the classical model: (I) Replacing Baum-Welch algorithm with K-means clustering algorithm, (2) Replacing K-means with adaptive K-means and (3) Adaptive selection of training images amongst the available images in data set. The results show identical computational complexity in verification phase and better verification performance compared with other ID-HMM methods. The proposed algorithm has been successfully tested on the ORL face image data set, exhibiting an accuracy of 96%. This is almost 10% higher than the identification rate of the classical lD-HMMs and is comparable with 2D-HMMs accuracy; which basically has much higher processing complexity than ID-HMM.