Accurately estimating the number of infections that actually occur in the earliest phases of an outbreak and predicting the number of new cases per day in various countries is crucial for real-time monitoring of COVID-19 transmission. Numerous studies have used mathematical models to predict the progression of infection rates in several countries following the appearance of epidemiological outbreaks. In this study, we analyze the data reported and then study several logistical-type phenomenological models and their application in practice for forecasting infection evolution. When several epidemic waves follow one another, it is important to stress that a traditional logistic model cannot necessarily be fully adapted to the data made available. New models are being introduced to simultaneously take account of human behavior, measures taken by the government, and epidemiological conditions. This research used a generalized logistic model based on parameters that vary over time to describe trends in COVID-19-infected cases in countries that have undergone several waves. In two-wave scenarios, the parameters of the model evolve dynamically over time following a logistic function, where the first and second waves are characterized by two extreme values for the early period and the late one, respectively.

Air-writing is a widely used technique for writing arbitrary characters or numbers in the air. In this study, a data collection technique was developed to collect hand motion data for Bengali air-writing, and a motion sensor-based data set was prepared. The feature set as then utilized to determine the most effective machine learning (ML) model among the existing well-known supervised machine learning models to classify Bengali characters from air-written data. Our results showed that medium Gaussian SVM had the highest accuracy (96.5%) in the classification of Bengali character from air writing data. In addition, the proposed system achieved over 81% accuracy in real-time classification. The comparison with other studies showed that the existing supervised ML models predicted the created data set more accurately than many other models that have been suggested for other languages.

Environmental transition can potentially influence cardiovascular health. Investigating the relationship between such transition and heart disease has important applications. This study uses federated learning (FL) in this context and investigates the link between climate change and heart disease. The dataset containing environmental, meteorological, and health-related factors like blood sugar, cholesterol, maximum heart rate, fasting ECG, etc., is used with machine learning models to identify hidden patterns and relationships. Algorithms such as federated learning, XGBoost, random forest, support vector classifier, extra tree classifier, k-nearest neighbor, and logistic regression are used. A framework for diagnosing heart disease is designed using FL along with other models. Experiments involve discriminating healthy subjects from those who are heart patients and obtain an accuracy of 94.03%. The proposed FL-based framework proves to be superior to existing techniques in terms of usability, dependability, and accuracy. This study paves the way for screening people for early heart disease detection and continuous monitoring in telemedicine and remote care. Personalized treatment can also be planned with customized therapies.

The pair-wise Markov chain (PMC) model serves as an extension to the hidden Markov chain (HMC) model and has been widely used in unsupervised restoration tasks associated with reconstructing the hidden data. In fact, the PMC model can treat fairly complicated situations for which application of Bayesian restoration estimators such as maximum A Posteriori (MAP), or maximal Posterior mode (MPM) remains possible. The major novelty in this work is to construct a PMC model with observational data in two dimensions, and subsequently adapt the estimation algorithms, as well as, image restoration methods for that context. Often, the transformation of an image from a two-dimensional format to a one-dimensional sequence occurs via Hilbert-Peano scan (HPS), whereas in the proposed model, the second component of the observed process takes over this role to exceed the situation of pixel missing information after transformation for a to be segmented image. To reconstruct the hidden process, we used the MPM decision criterion after estimating the model's parameters with two algorithms: Stochastic expectation maximization (SEM) and iterative conditional estimation (ICE). In this study, experimental, numerical, and visual results are shown to demonstrate the superiority of the proposed model over the classical PMC for unsupervised restorations.