A framework for the analysis of skin sores disease using evolutionary intelligent computing approach

Area of Science:

• Epidemiology
• Computational Biology
• Artificial Intelligence

Background:

• Impetigo, a contagious bacterial skin disease, commonly affects infants and young children, presenting as sores primarily on the face.
• Understanding the dynamics of impetigo is crucial for developing effective treatment and prevention strategies.

Purpose of the Study:

• To introduce a neuro-evolutionary global algorithm for solving the nonlinear skin sores disease model (SSDM).
• To develop an artificial neural network-based approach for modeling impetigo dynamics.

Main Methods:

• Integration of a global genetic algorithm with local sequential quadratic programming (GA-LSQP) to solve the SSDM.
• Utilizing an activation function-based neural network model trained via mean square error for impetigo dynamics.
• Validation through comparison with the Adam strategy and absolute error analysis.

Main Results:

• The proposed GA-LSQP algorithm achieved high accuracy, demonstrated by absolute error analysis.
• Statistical investigations confirmed the consistency, stability, and convergence of the integrated technique.
• The solver's accuracy was further evidenced by small statistical values (minimum, median, maximum, mean, etc.).

Conclusions:

• The neuro-evolutionary algorithm provides a robust and accurate method for solving nonlinear disease models like impetigo.
• The study highlights the efficacy of integrating artificial intelligence with mathematical modeling for epidemiological research.
• The developed approach offers a reliable tool for analyzing and potentially controlling the spread of skin sores disease.