Objetivo: Descrever o perfil e a variação temporal das internações e mortalidade hospitalar por síndrome respiratória aguda grave (SRAG) por COVID-19 no Piauí, Brasil, segundo local de internação. Métodos: Estudo descritivo sobre dados do Sistema de Informação da Vigilância Epidemiológica da Gripe, da 12ª semana epidemiológica de 2020 à 12ª de 2021. Calculou-se a mortalidade hospitalar e respectivos intervalos de confiança de 95% (IC95%). Resultados: Os indivíduos observados eram majoritariamente do sexo masculino (57,1%), negros (61,2%), com uma ou duas comorbidades (30,5%). A mortalidade hospitalar no interior, entre internados (44,1% – IC95% 42,0%;46,3%), admitidos em unidades de terapia intensiva (82,3% – IC95% 79,7;84,8) e indivíduos submetidos a ventilação mecânica invasiva (96,6% – IC95% 94,9;97,8), foi maior do que na capital do estado. Conclusão: O estudo permitiu a caracterização do perfil das internações devidas a SRAG por COVID-19 no Piauí e demonstrou mortalidade hospitalar elevada, mantendo-se alta no período estudado, sobretudo no interior.
In this work, genetic algorithms (GA) and particle swarm optimization (PSO) are used to make an automated choice of hyperparameters of the MLP-NARX, ELM-NARX, and ESNNARX neural models applied to the identification of two photovoltaic systems: one installed in Teresina, in Brazil, and another in Hamburg, Germany. The automatic optimization process results showed that the PSO algorithm presents superior performance compared to the GA algorithm. Likewise, the identification carried out aimed to estimate the power generated by photovoltaic systems from two different approaches: linear mathematical models and neural identification models. Thus, the neural models implemented are more efficient and accurate than the linear mathematical models compared. From accuracy, the neural models ESNNARX and MLP-NARX were considered the best in identifying Hamburg and Teresina's photovoltaic systems, respectively.
In this paper we evaluate the performance of the ELM network based on NARX model in the task of prediction of Hénon, Mackey-Glass (MG) and chaotic laser series. An analysis of the results showed that the NARX-ELM network achieved the best results for the Hénon and MG series. The same was not true for the chaotic laser serie, whereas the ELM networks failed on making more accurate predictions for a horizon greater than the NARX network trained with the backpropagation algorithm.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.