Applications of artificial intelligence in battling against covid-19: A literature review

Chaos Solitons & Fractals, Journal Year: 2020, Volume and Issue: 142, P. 110338 - 110338

Published: Oct. 3, 2020

Language: Английский

---

DenseNet Convolutional Neural Networks Application for Predicting COVID-19 Using CT Image

SN Computer Science, Journal Year: 2021, Volume and Issue: 2(5)

Published: July 23, 2021

Language: Английский

---

Artificial intelligence for forecasting and diagnosing COVID-19 pandemic: A focused review

Artificial Intelligence in Medicine, Journal Year: 2022, Volume and Issue: 128, P. 102286 - 102286

Published: March 28, 2022

Language: Английский

---

Comparison of ARIMA, ETS, NNAR, TBATS and hybrid models to forecast the second wave of COVID-19 hospitalizations in Italy

The European Journal of Health Economics, Journal Year: 2021, Volume and Issue: 23(6), P. 917 - 940

Published: Aug. 4, 2021

The coronavirus disease (COVID-19) is a severe, ongoing, novel pandemic that emerged in Wuhan, China, December 2019. As of January 21, 2021, the virus had infected approximately 100 million people, causing over 2 deaths. This article analyzed several time series forecasting methods to predict spread COVID-19 during pandemic's second wave Italy (the period after October 13, 2020). autoregressive moving average (ARIMA) model, innovations state space models for exponential smoothing (ETS), neural network autoregression (NNAR) trigonometric model with Box-Cox transformation, ARMA errors, and trend seasonal components (TBATS), all their feasible hybrid combinations were employed forecast number patients hospitalized mild symptoms intensive care units (ICU). data February 2020-October 2020 extracted from website Italian Ministry Health ( www.salute.gov.it ). results showed (i) better at capturing linear, nonlinear, patterns, significantly outperforming respective single both series, (ii) numbers COVID-19-related hospitalizations ICU projected increase rapidly mid-November 2020. According estimations, necessary ordinary beds expected double 10 days triple 20 days. These predictions consistent observed trend, demonstrating may facilitate public health authorities' decision-making, especially short-term.

Language: Английский

---

Impact of lockdowns on the spread of COVID-19 in Saudi Arabia

Informatics in Medicine Unlocked, Journal Year: 2020, Volume and Issue: 20, P. 100420 - 100420

Published: Jan. 1, 2020

Epidemiological models have been used extensively to predict disease spread in large populations. Among these models, Susceptible Infectious Exposed Recovered (SEIR) is considered be a suitable model for COVID-19 predictions. However, SEIR its classical form unable quantify the impact of lockdowns. In this work, we introduce variable system equations study various degrees social distancing on disease. As case study, apply our modified initial data available (till April 9, 2020) Kingdom Saudi Arabia (KSA). Our analysis shows that with no lockdown around 2.1 million people might get infected during peak 2 months from date was first enforced KSA (March 25th). On other hand, Kingdom's current strategy partial lockdowns, predicted number infections can lowered 0.4 by September 2020. We further demonstrate stricter level curve effectively flattened KSA.

Language: Английский

---

Prediction of the confirmed cases and deaths of global COVID-19 using artificial intelligence

Environmental Science and Pollution Research, Journal Year: 2021, Volume and Issue: 28(9), P. 11672 - 11682

Published: Jan. 7, 2021

The outbreak of coronavirus disease 2019 (COVID-19) has seriously affected the environment, ecology, economy, society, and human health. With global epidemic dynamics becoming more serious, prediction analysis confirmed cases deaths COVID-19 become an important task. We develop artificial neural network (ANN) for modeling COVID-19. data are collected from January 20 to November 11, 2020 by World Health Organization (WHO). By introducing root mean square error (RMSE), correlation coefficient (R), absolute (MAE), statistical indicators model verified evaluated. size training test death base employed in is optimized. best simulating performance with RMSE, R, MAE realized using 7 past days' as input variables dataset. And estimated R 0.9948 0.9683, respectively. Compared different algorithms, experimental simulation shows that trainbr algorithm better than other algorithms reproducing amount deaths. This study ANN suitable predicting future. Using model, we also predict June 5, 2020. During period, new infected 0.9848, 17,554, 12,229, respectively; 0.8593, 631.8, 463.7, predicted very close actual results show continuous strict control measures should be taken prevent further spread epidemic.

Language: Английский

---

Precise prediction of performance and emission of a waste derived Biogas–Biodiesel powered Dual–Fuel engine using modern ensemble Boosted regression Tree: A critique to Artificial neural network

Fuel, Journal Year: 2022, Volume and Issue: 321, P. 124131 - 124131

Published: April 9, 2022

Language: Английский

---

A novel approach based on combining deep learning models with statistical methods for COVID-19 time series forecasting

Neural Computing and Applications, Journal Year: 2021, Volume and Issue: 34(4), P. 3135 - 3149

Published: Oct. 10, 2021

The COVID-19 pandemic has disrupted the economy and businesses impacted all facets of people's lives. It is critical to forecast number infected cases make accurate decisions on necessary measures control outbreak. While deep learning models have proved be effective in this context, time series augmentation can improve their performance. In paper, we use techniques create new that take into account characteristics original series, which then generate enough samples fit properly. proposed method applied context forecasting using three techniques, (1) long short-term memory, (2) gated recurrent units, (3) convolutional neural network. terms symmetric mean absolute percentage error root square measures, significantly improves performance memory networks. Also, improvement average for units. Finally, present a summary top model as well visual representation actual forecasted data each country.

Language: Английский

---

A Review of the Machine Learning Algorithms for Covid-19 Case Analysis

IEEE Transactions on Artificial Intelligence, Journal Year: 2022, Volume and Issue: 4(1), P. 44 - 59

Published: Jan. 11, 2022

The purpose of this article is to see how machine learning (ML) algorithms and applications are used in the COVID-19 inquiry for other purposes. available traditional methods international epidemic prediction, researchers authorities have given more attention simple statistical epidemiological methodologies. inadequacy absence medical testing diagnosing identifying a solution one key challenges preventing spread COVID-19. A few statistical-based improvements being strengthened answer challenge, resulting partial resolution up certain level. ML advocated wide range intelligence-based approaches, frameworks, equipment cope with issues industry. application inventive structure, such as handling relevant outbreak difficulties, has been investigated article. major goal 1) Examining impact data type nature, well obstacles processing 2) Better grasp importance intelligent approaches like pandemic. 3) development improved types prognosis. 4) effectiveness influence various strategies 5) To target on potential diagnosis order motivate academics innovate expand their knowledge research into additional COVID-19-affected industries.

Language: Английский

---

GRU Neural Network Based on CEEMDAN–Wavelet for Stock Price Prediction

Applied Sciences, Journal Year: 2023, Volume and Issue: 13(12), P. 7104 - 7104

Published: June 14, 2023

Stock indices are considered to be an important indicator of financial market volatility in various countries. Therefore, the stock forecast is one challenging issues decrease uncertainty future direction markets. In recent years, many scholars attempted use different conventional statistical and deep learning methods predict indices. However, non-linear noise data will usually cause stochastic deterioration time lag results, resulting existing neural networks that do not demonstrate good prediction results. For this reason, we propose a novel framework combine gated recurrent unit (GRU) network with complete ensemble empirical mode decomposition adaptive (CEEMDAN) better accuracy, which wavelet threshold method especially used denoise high-frequency noises sub-signals exclude interference for predictions. Firstly, choose representative datasets collected from closing prices S&P500 CSI 300 evaluate proposed GRU-CEEMDAN–wavelet model. Additionally, compare improved model traditional ARIMA several modified models using gate structures. The result shows mean values MSE MAE GRU based on CEEMDAN–wavelet smallest by significance analysis. Overall, found our could improve accuracy alleviates problem.

Language: Английский

---