COVID-19 Prediction Using Traditional and Deep Learning Models

Abstract

In response to the pressing challenges posed by the COVID-19 pandemic, this research endeavors to revolutionize disease classification through an innovative fusion of data analytics and advanced machine learning methodologies. The proposed study meticulously employs a dataset enriched with key physiological parameters namely, oxygen levels, pulse rates, and temperatures leveraging a systematic approach to dataset analysis, exploratory data analysis, and preprocessing. The research addresses a critical problem: the accurate and timely classification of COVID-19 cases. The developed methodology encompasses a diverse array of models, from traditional machine learning techniques to sophisticated deep learning architectures, ensuring a comprehensive evaluation. Through rigorous model selection, hyperparameter tuning, and performance analysis, we unravel actionable insights. The achieved results of the proposed model are very competitive with state-of-the-art models. This research not only contributes to the scientific understanding of COVID-19 classification but also lays the foundation for deploying effective machine learning tools in real-world scenarios for infectious disease management.