Soft Computing Models for Accurate COVID-19 Prediction:A Comparative Study

Abstract

The purpose of this research is to explore the effectiveness of soft computing models for accurate COVID-19 prediction by conducting a complete comparison investigation. The implementation of soft computing approaches, such as neural networks, fuzzy logic, and genetic algorithms, is something that we are investigating as a response to the worldwide requirement for accurate forecasting in the continuing epidemic. The study of the relevant literature draws attention to the shortcomings of traditional modelling techniques, so laying the groundwork for the implications and possibilities of soft computing in the field of illness prediction. The selection of a wide variety of soft computing models, the diligent collecting of data, the use of preprocessing methods, and the establishment of a methodical framework for comparative analysis are all components of our approach. The findings and comparison analysis shed light on the unique advantages and disadvantages of each model, providing insights into the overall performance of the models as well as the variables that influence the accuracy of their predictions. According to the results of this research, significant insights have been contributed to the ever-changing environment of COVID-19 prediction, which has ramifications for the process of making informed decisions in the field of public health.