Hepatitis C Dynamics' Estimation Process by Differential Neural Networks.

Hepatitis C is one of the illness that have affected many people around the world. It seriously harms the patient health in many ways. This paper provides a description of an adaptive nonlinear observer based on differential neural networks (DNN), designed for hepatitis C mathematical model, where all state vector is considered not to be available. Only viral load is assumed to be measurable with any analytical method like reverse transcriptase -polymerase chain reaction (RT-PCR). The process is taken in two stages: a training scheme which generates the correct parameter set for the DNN-observer and the estimation process for three different inputs, which confirms (in numerical way) the robustness to input variations of the DNN scheme.