Artificial computational intelligence in generating generalized profile function model
Pero J. Radonja, Srdjan Stanković, D. Dražić · 2008
In this paper a derivation of a generalized profile function model, GPFM, based on artificial intelligence is described. This generalized model provides an approximation of the profile function of any object in region. The procedure based on artificial computational intelligence, that is, neural networks, is very efficient and gives very good results. The GPFM, is generated using the basic dataset and verification is performed by the validation data set. The summary statistical parameters of the original, measured data and estimated data, based on the GPFM, are presented and compared. The test of the obtained GPFM, is also performed by regression analysis. The obtained correlation coefficients between the real, measured data and estimated data are very high, 0.9946 for the basic and 0.9933 for the validation dataset.