25Objectives 26 The current form of severe acute respiratory syndrome called coronavirus disease 2019 27 (COVID-19) caused by a coronavirus (SARS-CoV-2) is a major global health problem. The 28 aim of our study was to use the official epidemiological data and predict the possible outcomes 29 of the COVID-19 pandemic using artificial intelligence (AI)-based RNNs (Recurrent Neural 30 Networks), then compare and validate the predicted and observed data. 31 Materials and Methods 32We used the publicly available datasets of World Health Organization and Johns Hopkins 33 University to create the training dataset, then have used recurrent neural networks (RNNs) with 34 gated recurring units (Long Short-Term Memory -LSTM units) to create 2 Prediction Models. 35Information collected in the first t time-steps were aggregated with a fully connected (dense) 36 neural network layer and a consequent regression output layer to determine the next predicted 37 value. We used root mean squared logarithmic errors (RMSLE) to compare the predicted and 38 observed data, then recalculated the predictions again. 39 Results 40The result of our study underscores that the COVID-19 pandemic is probably a propagated 41 source epidemic, therefore repeated peaks on the epidemic curve (rise of the daily number of 42 the newly diagnosed infections) are to be anticipated. The errors between the predicted and 43 validated data and trends seems to be low. 44 Conclusions 45 3The influence of this pandemic is great worldwide, impact our everyday lifes. Especially 46 decision makers must be aware, that even if strict public health measures are executed and 47 sustained, future peaks of infections are possible. The AI-based predictions might be useful 48 tools for predictions and the models can be recalculated according to the new observed data, 49 to get more precise forecast of the pandemic. 50 51 52 53 54 55 56 57 58 59 60 61 4 62
Objectives The COVID-19 pandemic is considered a major threat to global public health. The aim of our study was to use the official epidemiological data to forecast the epidemic curves (daily new cases) of the COVID-19 using Artificial Intelligence (AI)-based Recurrent Neural Networks (RNNs), then to compare and validate the predicted models with the observed data. Methods We used publicly available datasets from the World Health Organization and Johns Hopkins University to create a training dataset, then we employed RNNs with gated recurring units (Long Short-Term Memory - LSTM units) to create two prediction models. Our proposed approach considers an ensemble-based system, which is realized by interconnecting several neural networks. To achieve the appropriate diversity, we froze some network layers that control the way how the model parameters are updated. In addition, we could provide country-specific predictions by transfer learning, and with extra feature injections from governmental constraints, better predictions in the longer term are achieved. We have calculated the Root Mean Squared Logarithmic Error (RMSLE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE) to thoroughly compare our model predictions with the observed data. Results We reported the predicted curves for France, Germany, Hungary, Italy, Spain, the United Kingdom, and the United States of America. The result of our study underscores that the COVID-19 pandemic is a propagated source epidemic, therefore repeated peaks on the epidemic curve are to be anticipated. Besides, the errors between the predicted and validated data and trends seem to be low. Conclusion Our proposed model has shown satisfactory accuracy in predicting the new cases of COVID-19 in certain contexts. The influence of this pandemic is significant worldwide and has already impacted most life domains. Decision-makers must be aware, that even if strict public health measures are executed and sustained, future peaks of infections are possible. The AI-based models are useful tools for forecasting epidemics as these models can be recalculated according to the newly observed data to get a more precise forecasting.
This paper proposes a retrial queueing model with the finite number of sources to evaluate the performance of spectrum renting in mobile cellular networks. The model incorporates necessary ingredients such as the finite number of subscribers, their impatience and a queue for the outbound service. To consider the specific feature of spectrum renting and the current mobile cellular technology, a variable number of servers that are switched on and off in groups is introduced. We present a novel way to take into account the renting * Corresponding author. 1440004-1 2nd ReadingJanuary 21, 2014 9:50 WSPC/S0217-5959 APJOR 1440004.tex T. V. Do et al.fee, which can be used to fine-tune the operation of the spectrum renting procedure. Numerical results show that it is still profitable to initiate a spectrum renting request at high loads, even if no discount is offered by the frequency bands' owners.
Abstract. This paper deals with performance modeling of radio frequency licensing. Licensed users (Primary Users -PUs) and normal users (Secondary Users -SUs) are considered. The main idea, is that the SUs are able to access to the available non-licensed radio frequencies.A finite-source retrial queueing model with two non-independent frequency bands (considered as service units) is proposed for the performance evaluation of the system. A service unit with a priority queue and another service unit with an orbit are assigned to the PUs ans SUs, respectively. The users are classified into two classes: the PUs have got a licensed frequency, while the SUs have got a frequency band, too but it suffers from the overloading. We assume that during the service of the non-overloaded band the PUs have preemptive priority over SUs. The involved inter-event times are supposed to be independent, hypoexponentially, hyper-exponentially, lognormal distributed random variables, respectively, depending on the different cases during simulation.The novelty of this work is that we create a new model to analyze the effect of distribution of inter-event time on the mean and variance of the response time of the PUs and SUs.As the validation of the simulation program a model with exponentially distributed inter-event times is considered in which case a continuous time Markov chain is introduced and by the help of MOSEL (MOdeling Specification and Evaluation Language) tool the main performance measures of the system are derived. In several combinations of the distribution of the involved random variables we compare the effect of their distribution on the first and second moments of the response times illustrating in different figures.
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.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.