Artificial neural network modeling of nanofluid temperature rise in a magnetic hyperthermia process

In this paper, the temperature rise of magnetic nanoparticles (MNPs) dispersed in a fluid in a magnetic hyperthermia process is modeled by artificial neural networks (ANN). The experimental data sets obtained from hyperthermia test on Poly- N-isopropyl acrylamide coated Fe3O4 nanoparticles dispersed in aqueous solution are used to investigate several ANN patterns with different number of neurons. The data obtained from experiments are used to train, validate and test the ANN patterns and based on the calculated mean of square error and the coefficient of determination, R2, the best network structure is determined. The results indicate that the ANN is able to predict the experimental data with an excellent precession.