Back

Machine Learning Algorithms to Fight the COVID-19 Pandemic

PATTNAIK, M.; PATTNAIK, A.; PATTNAIK, A.

2023-01-04 epidemiology
10.1101/2022.12.31.22284091 medRxiv
Show abstract

The ongoing novel COVID-19 global pandemic is one of the health emergencies in 21st century after hundred years of Spanish flu that affected almost all the countries in the world. The objective of this study is to generate STM and LTM real-time out of sample forecasts of the future COVID-19 confirmed and death cases respectively for the top five mostly affected countries in the world namely USA, India, Brazil, Russia and UK. As of January 17, 2021, it has caused a pandemic outbreak with more than 94.5 million confirmed cases and more than 2 million reported deaths worldwide. Due to extreme robust behaviour in the univariate time series data, forecasting of both COVID-19 confirmed and death cases has become the exigent task for the government officials, healthcare workers, economists, corporate leaders, government, decision makers, public-policy makers, and scientific experts to allocate health resources. To solve this problem different hybrid approaches are applied which eliminate both linear and non-linear errors of the time series datasets and the predictions of for these countries will be practical to act as forewarning for all.

Matching journals

The top 10 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.