Loading...
4 results
Search Results
Now showing 1 - 4 of 4
- Forecasting omicron variant of Covid-19 with ANN model in european countries – number of cases, deaths, and ICU patientsPublication . Carvalho, Kathleen; Reis, Luis Paulo; Teixeira, João PauloAccurate predictions of time series are increasingly required to support judgments in a variety of decisions. Several predictive models are available to support these predictions, depending on how each field offers a data variety with varied behavior. The use of artificial neural networks (ANN) at the beginning of the COVID-19 pandemic was significant since the tool may offer forecasting data for various conditions and hence assist in governing critical choices. In this context, this paper describes a system for predicting the daily number of cases, fatalities, and Intensive Care Unit (ICU) patients for the next 28 days in five European countries: Portugal, the United Kingdom, France, Italy, and Germany. The database selection is based on comparable mitigation processes to analyze the impact of safety procedure flexibilization with the most recent numbers of COVID-19. Additionally, it is intended to check the algorithm’s adaptability to different variants throughout time. The network’s input data has been normalized to account for the size of the countries in the study and smoothed by seven days. The mean absolute error (MAE) was employed as a comparing criterion of two datasets, one with data from the beginning of the pandemic and another with data from the last year, since all variables (cases, deaths, and ICU patients) may be tendentious in percentage analysis. The best architecture produced a general MAE prediction for the 28 days ahead of 256,53 daily cases, 0,59 daily deaths, and 1,63 ICU patients, all numbers normalized by million people.
- COVID-19 time series forecasting – twenty days aheadPublication . Carvalho, Kathleen; Vicente, João Paulo; Teixeira, João PauloOccupational exposure to cytotoxic agents has been recognized as a potential danger to the health of handlers. However, collective and individual protection equipment has been developed for use by professionals. This article aims to identify and describe the protection equipment applicable to a centralized unit of cytostatics preparation, using a qualitative and quantitative descriptive analysis. A questionnaire survey yielded 83 responses, covering 18 centralized cytostatic preparation units. The results show some weaknesses detected in some institutions such as the absence of a shower and eyewash fountain, the lack of knowledge about the procedures manual, and the use of a surgical mask. However, the results point to awareness by the general manipulators regarding the use of some personal protective equipment. This study contributes to the investigation of the use of equipment for the protection of cytostatic manipulators at work in centralized cytostatic preparation units.
- Electromagnetic modeling approaches of static electric machinesPublication . Carvalho, Kathleen; Ferreira, Ângela P.; Miotto, Ednei LuizThe efficiency improvement of electric machines of major importance in the industrial field, considering that those devices represent a large portion of electricity consumption. Therefore, in the study of electromagnetic projects is mandatory to analyze the behavior of electric devices in rated and exceptional operation conditions. In this context, the application of the finite element method is relevant, since its high degree of discretization allows to analyze fields distribution with an accuracy not obtained by analytical approaches. When applied to complex domains, such as electric machines, that method makes it possible to verify saturation points and active losses in the device, with high accuracy. Thereby, this work proposes a computational model of a single-phase E-core transformer, assisted by the finite element method. The project is based on three approaches, in order to stablish a comparative analysis among the outputs. First of all, was analytically calculated through a reluctance mesh able to verify the magnetic flux distribution in the middle path of the transformer’s core. For this purpose, the project of the windings was necessary, based on the stablished physical characteristics and electric parameters. The second approach was the design the computational model, considered a 2D approach, to evaluate magnetic magnitudes, also calculated by the reluctance network. On the other hand, the 3D model was developed in order to evaluate the losses distribution around the whole volume of the domain. The proposed models were evaluated in a static, by reluctance mesh and the computational model, and time-varying domain, in order to analyze the losses. Finally, a physical prototype was also tested, at no-load and short-circuit tests, to provide data about the transformer losses under rating conditions. Those results were used to validate the efficiency of the computational model to predict the core and resistive losses.
- Analysis and forecasting incidence, intensive care unit admissions, and projected mortality attributable to COVID-19 in Portugal, the UK, Germany, Italy, and France: predictions for 4 weeks aheadPublication . Carvalho, Kathleen; Vicente, João Paulo; Jakovljevic, Mihajlo; Teixeira, João PauloThe use of artificial neural networks (ANNs) is a great contribution to medical studies since the application of forecasting concepts allows for the analysis of future diseases propagation. In this context, this paper presents a study of the new coronavirus SARS-COV-2 with a focus on verifying the virus propagation associated with mitigation procedures and massive vaccination campaigns. There were two proposed methodologies in making predictions 28 days ahead for the number of new cases, deaths, and ICU patients of five European countries: Portugal, France, Italy, the United Kingdom, and Germany. A case study of the results of massive immunization in Israel was also considered. The data input of cases, deaths, and daily ICU patients was normalized to reduce discrepant numbers due to the countries’ size and the cumulative vaccination values by the percentage of population immunized (with at least one dose of the vaccine). As a comparative criterion, the calculation of the mean absolute error (MAE) of all predictions presents the best methodology, targeting other possibilities of use for the method proposed. The best architecture achieved a general MAE for the 1-to-28-day ahead forecast, which is lower than 30 cases, 0.6 deaths, and 2.5 ICU patients per million people.