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

Abstract

Several epidemiological models are being used around the world to project the number of infected individuals and the mortality rates of the COVID-19 outbreak. Advancing accurate prediction models is of utmost importance to take proper actions. Due to a high level of uncertainty or even lack of essential data, the standard epidemiological models have been challenged regarding the delivery of higher accuracy for long-term prediction. As an alternative to the susceptibleinfected-resistant (SIR)-based models, this study proposes a hybrid machine learning approach to predict the COVID-19 and we exemplify its potential using data from 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 time series of 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 an effective tool to model the outbreak. This paper provides an initial benchmarking to demonstrate the potential of machine learning for future research.

RETRACTED ARTICLE: Modeling the progression of COVID-19 deaths using Kalman Filter and AutoML

“…Pinter et al use hybrid machine learning methods of adaptive network-based fuzzy inference system (ANFIS) and multi-layered perceptron-imperialist competitive algorithm (MLP-ICA) to predict time series of COVID-19 infected individuals and mortality rate (Pinter et al. 2020 ). Erraissi et al present a Spark ML approach to predict COVID-19 cases (Erraissi et al.…”

A Hybrid Model based on mBA-ANFIS for COVID-19 Confirmed Cases Prediction and Forecast

“…Pinter et al [ 17 ] proposed a hybrid machine learning method to predict COVID-19 cases in Hungary. Adaptive neuro-fuzzy inference system (ANFIS) has been combined with multilayered perceptron-imperialist competitive algorithm (MLP-ICA) to anticipate the time series of infected persons and mortality rate.…”

COVID-19 cases prediction by using hybrid machine learning and beetle antennae search approach

“…Other applications of ANFIS for disease forecasts include: Hepatitis C virus epidemic ( Khodaei-mehr, Tangestanizadeh, Vatankhah, & Sharifi, 2018 ), tuberculosis ( Mohammed et al, 2018 , Uçar et al, 2013 ), and finally, COVID-19. The COVID-19 related applications include forecasting the confirmed cases of the COVID-19 in China ( Al-qaness, Ewees, Fan, & Aziz, 2020 ), outbreak prediction ( Ardabili et al, 2020 ) and prediction case-study on the state of Hungary ( Pinter et al, 2020 ). Since the COVID-19 is a relatively new challenge, only a few studies have been found from this domain.…”

“…The conclusion of this research suggests that machine learning can be used effectively to model the outbreak of the disease. This approach was later exemplified on the case of Hungary ( Pinter, Felde, Mosavi, Ghamisi, & Gloaguen, 2020 ), in order to demonstrate the potential of the machine learning approach and to set a path for future research. The research presented in Suzuki and Suzuki (2020) utilize machine learning approach to estimate the number of reported cases in each province of South Korea, by employing a combination of XGBoost and MultiOutputRegressor as a machine learning model.…”