Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021;39(3-4):515-539.
doi: 10.1007/s00354-021-00129-z. Epub 2021 Jul 18.

A Deep Learning Method to Forecast COVID-19 Outbreak

Satyabrata Dash  1 , Sujata Chakravarty  2 , Sachi Nandan Mohanty  3 , Chinmaya Ranjan Pattanaik  4 , Sarika Jain  5
Affiliations

A Deep Learning Method to Forecast COVID-19 Outbreak

Satyabrata Dash et al. New Gener Comput. 2021.

Abstract

A new pandemic attack happened over the world in the last month of the year 2019 which disrupt the lifestyle of everyone around the globe. All the related research communities are trying to identify the behaviour of pandemic so that they can know when it ends but every time it makes them surprise by giving new values of different parameters. In this paper, support vector regression (SVR) and deep neural network method have been used to develop the prediction models. SVR employs the principle of a support vector machine that uses a function to estimate mapping from an input domain to real numbers on the basis of a training model and leads to a more accurate solution. The long short-term memory networks usually called LSTM, are a special kind of RNN, capable of learning long-term dependencies. And also is quite useful when the neural network needs to switch between remembering recent things, and things from a long time ago and it provides an accurate prediction to COVID-19. Therefore, in this study, SVR and LSTM techniques have been used to simulate the behaviour of this pandemic. Simulation results show that LSTM provides more realistic results in the Indian Scenario.

Keywords: COVID-19; Long short-term memory; Support vector regression.

PubMed Disclaimer

Figures

Fig. 1
Fig. 1
An example for long short term memory
Fig. 2
Fig. 2
Updating of long-term memory
Fig. 3
Fig. 3
LSTM chain structure
Fig. 4
Fig. 4
LSTM cell structure with forget gate
Fig. 5
Fig. 5
LSTM structure with input gate
Fig. 6
Fig. 6
LSTM structure output gate
Fig. 7
Fig. 7
Gates involved in LSTM
Fig. 8
Fig. 8
Analysis of the mapping from an input sphere to real numbers
Fig. 9
Fig. 9
Convex optimization problem by requiring minimization
Fig. 10
Fig. 10
The aim is to find the value of w and b by minimizing the risk
Fig. 11
Fig. 11
Growth of cumulative positive cases during 30th January 2020 to 11th June 2020
Fig. 12
Fig. 12
Growth of day-wise positive cases during 30th January 2020 to 11th June 2020
Fig. 13
Fig. 13
Growth of cumulative recover cases during 30th January 2020 to 11th June 2020
Fig. 14
Fig. 14
Growth of daily recover cases during 30th January 2020 to 11th June 2020
Fig. 15
Fig. 15
Growth of total death cases during 30th January 2020 to 11th June 2020
Fig. 16
Fig. 16
Growth of daily death cases during 30th January 2020 to 11th June 2020
Fig. 17
Fig. 17
Prediction using LSTM
Fig. 18
Fig. 18
Prediction using SVR
Fig. 19
Fig. 19
Comparison of RMSE, MSE, MAE, and TVS of SVR vs LSTM
See this image and copyright information in PMC

References

    1. WHO . Coronavirus disease 2019 (COVID19). Situation report 24. February 13, 2020. Geneva: World Health Organization; 2020.
    1. Li Y, Wang B, Peng R, Zhou C, Zhan Y, Liu Z, Jiang X, Zhao B. Mathematical modeling and epidemic prediction of COVID19 and its significance to epidemic prevention and control measures. Ann. Infect. Dis. Epidemiol. 2020;5(1):10521.
    1. nCoV-2019 Data Working Group.: Epidemiological data from the nCoV-2019 outbreak: early descriptions from publicly available data (2020). http://virological.org/t/epidemiological-data-from-the-ncov2019-outbreak.... Accessed 13 Feb 2020
    1. Camacho, A., Kucharski, A., Aki-Sawyerr, Y., White, M.A., Flasche, S., Baguelin, M., Tiffany, A.: Temporal changes in Ebola transmission in Sierra Leone and implications for control requirements: a real-time modelling study. PLoS Curr. 7 (2015). 10.1371/currents.outbreaks.406ae55e83ec0b5193e30856b9235ed2 - PMC - PubMed
    1. Funk S, Ciglenecki I, Tiffany A, Gignoux E, Camacho A, Eggo RM, Clement { The impact of control strategies and behavioural changes on the elimination of Ebola from Lofa County, Liberia. Philos. Trans. R. Soc. B Biol. Sci. 2017;372(1721):20160302. doi: 10.1098/rstb.2016.0302. - DOI - PMC - PubMed

LinkOut - more resources