Presentation Information
[MS14-01]Dynamic Modeling, Analysis of Tuberculosis Infection among Diabetic Patients and Parameters Estimation Using PINNs
*Danumjaya Palla1 (1. BITS-Pilani K.K. Birla Goa Campus (India))
Keywords:
Diabetes Mellitus (DM),Tuberculosis (TB),Stability Analysis,Parameter Estimation,Physics Informed Neural Networks (PINNs)
In this work, we discuss a compartmental dynamic model of tuberculosis infection among diabetic patients. We perform the mathematical analysis on the model and discuss the existence,
uniqueness and boundedness of the solution. We discuss the stability analysis of the endemic equilibrium point. Next we apply a modified physics informed neural networks (PINNs) based on a deep neural network architecture, to forecast the disease transmission pattern and estimate the key model parameters. The essence of this PINNs algorithm is that it can utilize the differential equation and efficiently estimate the parameters even with small dataset. We show that our modified PINNs can forecast the tuberculosis transmission pattern competently and estimate the key model parameters effectively.
uniqueness and boundedness of the solution. We discuss the stability analysis of the endemic equilibrium point. Next we apply a modified physics informed neural networks (PINNs) based on a deep neural network architecture, to forecast the disease transmission pattern and estimate the key model parameters. The essence of this PINNs algorithm is that it can utilize the differential equation and efficiently estimate the parameters even with small dataset. We show that our modified PINNs can forecast the tuberculosis transmission pattern competently and estimate the key model parameters effectively.