COVID-19 Pandemic Prediction for Hungary; a Hybrid Machine Learning Approach

EasyChair Preprint 3310, version 2

Abstract

For the prediction of the COVID-19 outbreak, several epidemiological models are being used around the world to project the number of infected individuals and mortality rates. Advancing accurate prediction models is of utmost importance to take proper actions. Due to a high level of uncertainty and lack of essential data, the standard epidemiological models have been challenged for delivering higher accuracy for long-term prediction. As an alternative to the susceptible-infected-resistant (SIR)-based models, this study proposes a hybrid machine learning approach to predict the COVID-19 outbreak in Hungary. The hybrid machine learning methods of adaptive network-based fuzzy inference system (ANFIS) and multi-layered perceptron-imperialist competitive algorithm (MLP-ICA) are used to predict the time series of the infected individuals and mortality rate. The models predict that by late May, the outbreak and the total morality will drop substantially. The validation is performed for nine days with promising results, which confirms the model accuracy. It is expected that the model maintains its accuracy as long as no significant interruption occurs. Based on the results reported here, and due to the complex nature of the COVID-19 outbreak and variation in its behavior from nation-to-nation, this study suggests machine learning as a useful tool to model the outbreak. This paper provides an initial benchmarking to demonstrate the potential of machine learning for future research.

Keyphrases: COVID-19, Coronavirus, SARS-CoV-2, machine learning, prediction model

@booklet{EasyChair:3310,
  author    = {Gergo Pinter and Imre Felde and Amir Mosavi and Pedram Ghamisi and Richard Gloaguen},
  title     = {COVID-19 Pandemic Prediction for Hungary; a Hybrid Machine Learning Approach},
  howpublished = {EasyChair Preprint 3310},
  year      = {EasyChair, 2020}}