The effectiveness analysis of selected IT tools for predictions of the Covid-19 pandemic

The article presents the problem of the complexity of prediction and the analysis of the effectiveness of selected IT tools in the example of the Covid-19 pandemic data in Poland. The study used a variety of tools and methods to obtain predictions of extinct infections and mortality for each wave of the Covid-19 pandemic. The results are presented for the 4th wave with a detailed description of selected models and methods implemented in the prognostic package of the statistical programming language R, as well as in the Statistica and Microsoft Excel programs. Naive methods, regression models, exponential smoothing methods (including ETS models), ARIMA models, and the method of artificial intelligence - autoregressive models built by neural networks (NNAR) were used. Detailed analysis was performed and the results for each of these methods were compared. © 2022 Polish Information Processing Society.

Performance Analysis of the Triple Exponential Smoothing Method during the Covid19 Pandemic on Tourist Visit Data

Data forecasting methods are essential in the business world to determine the company's future steps. However, the COVID-19 pandemic has hit the tourism economy hard, resulting in a slump in income. In this study, trials were conducted to analyze the reliability of forecasting methods on data affected by the COVID-19 pandemic. The method used is the Triple Exponential Smoothing method involving two models, namely Additive and Multiplicative. In this paper, the test is carried out using actual data derived from data from a service company engaged in tourist crossing transportation. Each method's alpha, beta, and gamma values are determined based on the parameters that produce the smallest error value. The experiment results show the predictability of the Triple Exponential Smoothing method by measuring the prediction error value based on the Mean Absolute Percentage Error (MAPE) value, which was 7.56% in the Additive model and 10.32% in the Multiplicative model before the pandemic happened. However, both methods' prediction measurements during a pandemic produce poor forecasts with an error percentage above 40%. Meanwhile, during the decline in pandemic cases, the value of the Triple Exponential Smoothing Multiplicative method was closer to the actual data with a prediction error value of 33.02%. Therefore, the Triple Exponential Smoothing Multiplicative method is more resistant and suitable for implementing into a forecasting system with actual data that influences pandemic events. © 2022 IEEE.

Analyzing and Predicting the Deaths and Cases of Covid-19 in Different Countries Using Fuzzy K Means Algorithm and Exponential Method

Covid-19 disease, since it first appearance in the Chinese city of Wuhan, has led to many infections and deaths, not only in China, but also in most countries of the world. The most prominent symptoms of this disease are headache, fever, strong cough, and perhaps the strongest of it is difficulty breathing in the event that the virus reaches the lung, which leads to death in many cases if the patient's condition is late, or he does not have strong immunity. The purpose of this study is to use Fuzzy k Means (FKM) and predictive algorithm representing in Simple Exponential Smoothing Method (SESM) to evaluate confirmed cases and deaths in different countries. This study's findings show that the FKM approach can evaluate data and produce reliable results, in addition to the SESM can give good prediction. According to this study, machine learning technologies and predicting methodologies achieved good results when used together. © 2021 IEEE.

COVID-19 Patient Mortality Risk Classification Using Linear Regression and Exponential Smoothing Methods

The dominant explanation for this phenomenon is there is no action to prevent a spike in coronavirus. Seeing this problem, we do some literature and research on artificial intelligence and machine learning to support the development of coronavirus forecasting in Indonesia. This research focuses on analyzing future coronavirus case possibilities using machine learning methodology. We use the official Indonesia Covid website data to collect data from the provinces with the largest cases in Indonesia from January until March. In this research, we used supervised machine learning methods of Linear Regression (LR) and Exponential Smoothing (ES) to make it easier for people to understand the data structure adapted to a particular model. The result of our research showed that each province in Indonesia is expected to decrease in new confirmed recovered cases and death cases from April to May while using the Exponential Smoothing method. In the other case, the Linear Regression method showed that cases would decrease in almost all cases in each province, and some cases will increase, such as Recovered Cases and Death Cases in West Java. © 2022 IEEE.