Futuristic evaluation of CoVID-19 spread using transfer learning: A post vaccination scenario

Abstract

Corona virus (CoVID) has spread like wild-fire across the globe, and measures to curb this disease are still under development. With vaccination of CoVID coming to market, it is necessary to observe the effects of this vaccination on the global scale. Along with this observation it is essential to understand the spreading trend of CoVID post vaccination, which will help Governments to deploy vaccination centres in the areas where CoVID might re-spread. In order to solve this issue, the underlying text proposes a novel transfer learning approach. This approach learns from the spreading patterns of CoVID which are being currently observed, and links it with the vaccination measures taken by the Government during the previous Spanish Influenza pandemic of 1918. This linkage is backed up by the analysis of re-spreading of Spanish Influenza post its vaccination. In order to develop an effective prediction system, the linkage information is given to a transfer learning system. This system enables effective prediction of post vaccination CoVID spread. Due to unavailability of any similar previously developed architecture, the comparison is made with the post-vaccination spread data for Spanish Influenza in 1918, and an accuracy of more than 80% is observed. © 2021 Author(s).