Author:
V R Manuraj V R, Dr. S. Shankar, Dr.S. Uma
Published in
Journal of Science Technology and Research
( Volume , Issue )
Abstract
COVID-19 began in China in December 2019. As of January 2021, over a hundred million instances had been reported worldwide, leaving a deep socio-economic impact globally. Current investigation studies determined that artificial intelligence (AI) can play a key role in reducing the effect of the virus spread. The prediction of COVID-19 incidence in different countries and territories is important because it serves as a guide for governments, healthcare providers, and the general public in developing management strategies to battle the disease. The prediction proved beneficial in the early months of 2020 to alert nations and territories in danger of an outbreak, allowing them to take preventative measures. Despite the fact that the COVID-19 outbreak has expanded to practically every location on the planet, the prediction has value in terms of monitoring the intensity of the spread and recovery, as well as determining the likelihood of a sequel or tertiary epidemic. COVID-19, like influenza, could become a seasonal or recurring epidemic in the future. COVID-19 activity must so be predicted and monitored now and in the future.
Keywords
Machine Learning, Cloud Computing
References
Data not available

ABSTRACT:

The Improved Mathematical Model for Continuous COVID-19 prediction provides valuable insight into monitoring and managing pandemic trends. Since its emergence in December 2019, COVID-19 has disrupted global health and economies. Accurate forecasting models have become crucial for government and healthcare planning. This study proposes an improved mathematical model based on the Generalized Inverse Weibull distribution, enhanced by iterative weighting for more accurate epidemic tracking. Combined with machine learning techniques and implemented via cloud computing, this model enables real-time, data-driven prediction of virus spread patterns. By analyzing global datasets, the model helps identify potential outbreaks and recovery phases. It also assists in anticipating second or third waves of infection, allowing timely interventions. The approach enhances prediction precision and supports proactive decision-making during health crises. The Improved Mathematical Model for Continuous forecasting presents a significant advancement in epidemic monitoring and can be adapted for future pandemics to reduce risks and improve preparedness.

INTRODUCTION:

The COVID-19 pandemic, caused by SARS-CoV-2, has significantly affected health systems and economies globally. As the virus continues to spread, accurate modeling and prediction remain vital for disease control. The Improved Mathematical Model for Continuous forecasting uses machine learning and cloud computing to analyze COVID-19 trends and predict future outbreaks. This study applies the Generalized Inverse Weibull distribution with iterative weighting to enhance prediction accuracy. Real-time analysis allows authorities to monitor infection rates, anticipate surges, and implement preventive measures accordingly. The World Health Organization declared COVID-19 a global pandemic in March 2020, and since then, countries have faced multiple infection waves. This model enables early detection of potential outbreaks, helping policymakers and healthcare professionals mitigate impacts efficiently. By offering a data-driven framework, it improves the precision of epidemic forecasting. The Improved Mathematical Model for Continuous forecasting represents a proactive strategy to address both current and future public health emergencies.

DOWNLOAD

INDEXED IN