Analysis of Large SARS-CoV-2 Data using Scalable Genetic Algorithm with Enhanced Bi-LSTM Method
Year: 2023
Type: article
Abstract: Corona Virus Disease 2019 (COVID-19), caused by the Severe Acute Respiratory Syndrome Coronavirus-2 (SARS-CoV-2) virus, which emerged in late 2019, is now spreading rapidly throughout the world and has reached most countries. Knowledge has led to researching the outbreak’s spread and growth. The increase in cases can lead to an increase in the size of SARS-CoV-2 datasets. The scalable model needs to be developed to handle very large SARS-CoV-2 datasets. This paper proposes a scalable machine learning algorithm for huge SARS-CoV-2 prediction. A Scalable Susceptible–Infected (SSI) model consisting of a Scalable Genetic Algorithm with enhanced bi-LSTM is proposed to predict coronavirus disease using a big data framework. The experimental results of epidemic data from several cities indicate that people infected from SARS-CoV-2 show more infection in the latter part of the first week from getting infected; this has relevance to the epidemic’s transmission rate. In addition, relative to conventional models for the epidemic, the hybrid model will substantially reduce prediction results errors and achieve better average absolute percentage errors (MAPEs).
Authors: Singh, Upendra, Raundale, Ajay
Language: English
Subfield: Modeling and Simulation
Field: Mathematics
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W7217791455
