COVID-19 Spread Forecasting, Mathematical Methods vs. Machine Learning, Moscow Case

Pavlyutin, Matvey; Samoyavcheva, Marina; Kochkarov, R. A.; Плешакова, Екатерина; Korchagin, Sergey; Gataullin, Timur; Никитин, П. В.; Hidirova, Mohiniso

doi:10.3390/math10020195

Cited by 13 publications

(8 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The findings imply that the logistic growth model best describes the pandemic's behavior, that there is sufficient correlation between climatic and movement factors and illness numbers, and that the Long Short-Term Memory (LSTM) network may be successfully used to forecast daily cases. A similar comparison of forecasting methodologies for the same task was performed in [9]. The classical methods of mathematical modeling in this case showed some weaknesses.…”

Section: Introductionmentioning

confidence: 77%

Optimal Neural Network Model for Short-Term Prediction of Confirmed Cases in the COVID-19 Pandemic

2022

View full text Add to dashboard Cite

COVID-19 is one of the largest issues that humanity still has to cope with and has an impact on the daily lives of billions of people. Researchers from all around the world have made various attempts to establish accurate mathematical models of COVID-19 spread. In many branches of science, it is difficult to make accurate predictions about short time series with extremely irregular behavior. Artificial neural networks (ANNs) have lately been extensively used for such applications. Although ANNs may mimic the nonlinear behavior of short time series, they frequently struggle to handle all turbulences. Alternative methods must be used as a result. In order to reduce errors and boost forecasting confidence, a novel methodology that combines Time Delay Neural Networks is suggested in this work. Six separate datasets are used for its validation showing the number of confirmed daily COVID-19 infections in 2021 for six world countries. It is demonstrated that the method may greatly improve the individual networks’ forecasting accuracy independent of their topologies, which broadens the applicability of the approach. A series of additional predictive experiments involving state-of-the-art Extreme Learning Machine modeling were performed to quantitatively compare the accuracy of the proposed methodology with that of similar methodologies. It is shown that the forecasting accuracy of the system outperforms ELM modeling and is in the range of other state-of-the art solutions.

show abstract

Section: Introductionmentioning

confidence: 77%

Optimal Neural Network Model for Short-Term Prediction of Confirmed Cases in the COVID-19 Pandemic

2022

View full text Add to dashboard Cite

show abstract

“…The results show that in majority cases LSTM outperforms other models. In another recent comparative study LSTM-based forecasting model outperformed CNN and exponential regression models [67] .…”

Section: Deep Learning Models For Covid-19 Forecastingmentioning

confidence: 99%

“…LSTM was shown to outperform other models. Egypt; Feb - Aug, 2020 0.9998 Pavlyutin et al, 2022 [67] Compared long-term (48 days) forecasting accuracy of LSTM, CNN, and exponential regression models and found the LSTM to be the best. Moscow city; Oct - Dec, 2021 5.4 Rguibi et al, 2022 [73] Compared LSTM and ARIMA models and found similar performance.…”

Section: Deep Learning Models For Covid-19 Forecastingmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning for Covid-19 forecasting: State-of-the-art review.

Kamalov¹,

Rajab²,

Cherukuri³

et al. 2022

Neurocomputing

View full text Add to dashboard Cite

“…To understand the mechanism of the pandemic's spread, several models have been used, including statistical [ 9 ], mathematical [ 10 – 15 ], computational simulation [ 16 – 18 ], and numerical simulation [ 19 – 21 ]. The techniques of machine learning [ 22 – 25 ] and Big Data are also used [ 26 – 28 ]. The first and the most popular model is called the suspected, infected and recovered individuals model (SIR model) [ 29 – 32 ].…”

Section: Introductionmentioning

confidence: 99%

COVID-19 multiwaves as multiphase percolation: a general N-sigmoidal equation to model the spread

Aferni¹,

Guettari²,

Hamdouni

2023

Eur. Phys. J. Plus

View full text Add to dashboard Cite

The aim of the current study is to investigate the spread of the COVID-19 pandemic as a multiphase percolation process. Mathematical equations have been developed to describe the time dependence of the number of cumulative infected individuals, , and the velocity of the pandemic, , as well as to calculate epidemiological characteristics. The study focuses on the use of sigmoidal growth models to investigate multiwave COVID-19. Hill, logistic dose response and sigmoid Boltzmann models fitted successfully a pandemic wave. The sigmoid Boltzmann model and the dose response model were found to be effective in fitting the cumulative number of COVID-19 cases over time 2 waves spread ( N = 2). However, for multiwave spread ( N > 2), the dose response model was found to be more suitable due to its ability to overcome convergence issues. The spread of N successive waves has also been described as multiphase percolation with a period of pandemic relaxation between two successive waves. Graphical abstract

show abstract

COVID-19 Spread Forecasting, Mathematical Methods vs. Machine Learning, Moscow Case

Cited by 13 publications

References 30 publications

Optimal Neural Network Model for Short-Term Prediction of Confirmed Cases in the COVID-19 Pandemic

Optimal Neural Network Model for Short-Term Prediction of Confirmed Cases in the COVID-19 Pandemic

Deep learning for Covid-19 forecasting: State-of-the-art review.

COVID-19 multiwaves as multiphase percolation: a general N-sigmoidal equation to model the spread

Contact Info

Product

Resources

About