Neural networks based generalized profile function model

In this paper neural networks are used for obtaining the generalized profile function model, GPFM. The generalized model enable getting the most important overall characteristics of the region without detailed measurements on all individual objects. Testing of the obtained GPFM by using the validation dataset is done. A very high correlation is obtained between the measured data and data estimated using the generalized model. It is shown that the application of neural networks provides the generalized model with good performances.