Forecasting Daily Covid-19 Deaths in Germany Using Artificial Neural Networks
Abstract
In this research paper, the ANN approach was applied to analyze daily
COVID-19 deaths in Germany. The employed daily data covers the period to 1 January 2020 to 31 December 2020 and the out-of-sample
period ranges over the period to 1January 2021 to 31 May 2021. The residuals
and forecast evaluation criteria (Error, MSE and MAE) of the applied model
indicate that the model is stable in forecasting daily COVID-19 cases in
Germany. The applied ANN (12, 12, 1) model projections indicate thatCOVID-19
mortality in Germany will generally range between 29 and 1000 deaths per day
over the out-of-sample period. Therefore the authorities in Germany are
encouraged to continue applying WHO guidelines on prevention and control of
COVID-19 including vaccination of its population in order to achieve herd
immunity.
Country : Zimbabwe
1 Dr. Smartson. P. NYONI2 Thabani NYONI3 Tatenda. A. CHIHOHO
ZICHIRe Project, University of Zimbabwe, Harare, Zimbabwe
Bai, S., Kolter, J.Z & Koltun,
V. (2018). An Empirical Evaluation of Generic Convolutional and Recurrent
Networks for Sequence Modeling. Cornell University Library, arXiv.org, ISSN:
2331-8422, arXiv: 1409.0473.
Crescenzio Gallo (2015). Artificial
neural networks tutorial, Encyclopedia of information science and Technology,
3rd Edition, pp 2-13.
Dan W. Patterson (1995) Artificial
Neural networks Theory and Applications. Singapore; New York: Prentice
Hall.
Fojnica, A., Osmanoviae &
Badnjeviae A (2016). Dynamic model of tuberculosis-multiple strain prediction
based on artificial neural network. In proceedings of the 2016 5th
Mediterranean conference on embedded computing pp290-293.
Gomes, G. S. S., et al. (2011).
Comparison of New Activation Functions in Neural Network for Forecasting
Financial Time Series, Neural Computing & Applications, 20: 417 – 439.
Kaushik AC &Sahi. S (2018).
Artificial neural network-based model for orphan GPCRs.Neural.Comput.Appl. 29,985-992.
KishanMehrotra., Chilukuri K.,
Mohan, & Sanjay Ranka (1997) Elements of artificial neural networks.
Cambridge, Mass.: MIT Press.
Smartson P Nyoni., Thabani Nyoni
& Tatenda A Chihoho (2020) Prediction of new Covid-19 cases in Spain using
artificial neural networks. IJARIIE Vol-6 Issue-6 2395-4396.
Smartson P Nyoni., Thabani Nyoni
& Tatenda A Chihoho (2020) Prediction of new Covid-19 cases in Ghana using
artificial neural networks. IJARIIE Vol-6 Issue-6 2395-4396.
Smartson. P. Nyoni., Thabani Nyoni
& Tatenda A. Chihoho (2020). Forecasting COVID-19 cases in Zimbabwe using
artificial neural networks, IJARIIE, 6, 6, 2395-4396.
Smartson. P. Nyoni., Thabani Nyoni
& Tatenda A. Chihoho (2020). Forecasting COVID-19 cases in Ethiopia using
artificial neural networks, IJARIIE, 6, 6, 2395-4396.
Smartson. P. Nyoni., Thabani
Nyoni., Tatenda. A. Chihoho (2020) Prediction of daily new Covid-19 cases in
Egypt using artificial neural networks. IJARIIE- Vol-6 Issue-6 2395-4396.
Weng SF., Reps J., Kai J.,
Garibaldi JM & Qureshi N (2017) Can machine-learning improve cardiovascular
risk prediction using routine clinical data? PLOS ONE 12(4): e0174944. https://doi.org/10.1371/journal.pone.0174944
Yan, H., Jiang, J., Zheng, J.,
Peng, C & Li, Q. (2006) A multilayer perceptron based medical decision
support system for heart disease diagnosis. Expert Syst. Appl. 2006, 30,
272–281.
Zhang G P (2003). “Time series
forecasting using a hybrid ARIMA and neural network model”, Neurocomputing 50:
159–175.
