THE ROLE OF ARTIFICIAL NEURAL NETWORKS IN DETECTION OF PULMONARY FUNCTIONAL ABNORMALITIES

Abstract

An artificial neural network is a system based on the operation of biological neural networks, in other words, it is an emulation of the biological neural system. The objective of this study is to compare the performance of two different versions of neural network ART algorithms such as Fuzzy ART vs. ARTFC methods used for classification of pulmonary function, detecting restrictive, obstructive and normal patterns of respiratory abnormalities by means of each of the neural networks, as well as the data gathered from spirometry. The spirometry data were obtained from 150 patients by standard acquisition protocol, 100 subjects used for training and 50 subjects for testing, respectively. The results showed that the standard Fuzzy ART grows faster than ARTFC, which successfully solves the category proliferation problem.