Predicting death and confirmed cases of coronavirus

Farqad Hamid Abdulraheem, Moatasem Yaseen Al-Ridha, Raid Rafi Omar Al-Nima

Abstract


At the end of 2019, a new virus called coronavirus has globally spread causing severe effections. In this paper, an artificial intelligence (AI) method is proposed to predict numbers of death and confirmed coronavirus cases. Efficient machine learning (ML) network named the byesian regularization backpropagation (BRB) is employed. It can estimates numbers of death and confirmed cases from applied population density and date. So, the BRB uses the population density, month and day as inputs, and predicts the new cases per million and new deaths per million as outputs. The network was trained and assessed by using a daily coronavirus recorded dataset known as the our world in data (OWID). The considered dates here are from the 31st of December 2019 to the 13th of October 2020. Furthermore, recorded information from countries over all world are employed. The obtained results provided a good promising performance with a testing mean absolute error (MAE) equal to 0.0218.

Keywords


Bayesian neural network Coronavirus; Machine learning; Pandemic; Predicting

Full Text:

PDF


DOI: https://doi.org/10.11591/eei.v11i1.3133

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Bulletin of EEI Stats