Imprinted Dopamine Sensor Optimised by an Artificial Neural Network (ANN)

Dopamine is an important and special neurotransmitter that plays many critical roles in human health related to the central nervous, renal, cardiovascular, and hormonal systems. The control of dopamine level permit to reduce stress and human health disturb. To help the optimization condition in the production of available senor for dopamine sensing, a neural network model was developed. This generated model aims to optimize molecularly imprinted polypyrrole-chitosan for dopamine quantification using DPV measurements. Experimentally, some parameters were optimized such as pH, template concentration, monomer concentration, Acid concentration, cycle number and time of pre-concentration. This theoretical method consists to finding the optimal sensor architecture. In this paper, we present the Artificial Neural Network ANN model to optimize the parameters for the molecularly imprinted polypyrrole-chitosan and dopamine interaction. As results, a strong correlation between predicted and experimental data was obtained with small error values.