A deep neural network analysis of fractional omicron mathematical model with vaccination and booster dose

Abstract

This model includes asymptomatic subjects and has seven compartments that correspond to distinct stages of infection. The model uses a fractional order Caputo operator and the dynamics of infection are captured by important measures like infection rate, booster-induced efficacy, and vaccination efficacy. Using fixed-point theory, a fractional perspective assesses the model’s existence and uniqueness. An analysis of mathematical models and numerical simulations explores the impact of different vaccination strategies and boosters on the spread of Omicron. An iterative numerical scheme based on Newton’s polynomial interpolation approximates the problem numerically. Using fractional Caputo operators, simulations for diverse fractional orders are performed to validate the efficiency and applicability of the proposed technique. As a result of this detailed investigation, a more nuanced understanding of the dynamics of Omicron has been obtained under different vaccination scenarios. Additionally, deep neural network approach is applied to with high accuracy of training testing and validation data to study the given disease problem.

Keywords

• Omicron
• COVID-19
• Caputo operator
• Vaccination
• Qualitative analysis
• Machine learning