AUTHOR=Kumar R. Lakshmana , Khan Firoz , Din Sadia , Band Shahab S. , Mosavi Amir , Ibeke Ebuka 

TITLE=Recurrent Neural Network and Reinforcement Learning Model for COVID-19 Prediction

JOURNAL=Frontiers in Public Health

VOLUME=Volume 9 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/public-health/articles/10.3389/fpubh.2021.744100

DOI=10.3389/fpubh.2021.744100

ISSN=2296-2565

ABSTRACT=Detection and prediction of the novel Coronavirus present new challenges for the medical research community due to this widespread infection across the globe. This poses a huge challenge for medical research societies around the globe. Methods driven by Artificial Intelligence can help predict specific parameters, hazards, and outcomes of such a pandemic. Recently, deep learning-based approaches have proven a novel opportunity to determine various difficulties in prediction. In this work, two learning algorithms, namely deep learning and reinforcement learning, were developed for the forecast of COVID-19. This article constructs a model using Recurrent Neural Networks (RNN), particularly Modified Long-Short Term Memory (MLSTM) model, towards forecasting the count of freshly affected individuals, losses, and cures in the following few days. This study also suggests deep learning of reinforcement to optimize COVID-19's predictive outcome based on the symptoms. Real-world data collection was applied to analyze the success of the suggested system. The findings show that the established approach promises future prognosticating outcomes concerning the current COVID-19 pandemic.