摘要：This paper shows practical implementation of the multilayer feedforward neural network,trained by supervised backpropagation algorithm, to the problem of automatic classification of countries into beforehand predefined categories of economic development,contained in the United Nations report entitled World Economic Situation and Prospects 2012.The goal of the paper is to automate the process of classification of countries,to define a set of key measurable economic development indicators,as well as to emphasize significance of neural networks for solving classification problems.The research includes classification of 168 countries in 4 groups of economic development,based on 7 selected measurable indicators.The data from the official reports of the international economic institutions served for training of the intelligent decision-making system based on neural network, and as a measure of quality of training,confusion matrix was used,showing the precision of the intelligent system by determining the percentage of overlap with empirically obtained data.Precision of automatic classification speaks of neural networks as powerful apparatus for solving classification problems,but also of justification of choice of classification parameters and their importance.The importance of selected indicators is reflected in the factthat knowledge of their value is sufficient condition for automatic classification with reliability level of 80%.
其他摘要：Ovaj rad prikazuje praktičnu primenu višeslojne feedforward neuronske mreže,obučavane nadgledano backpropagation algoritmom,na problem automatskog klasifikovanja zemalja u unapred predefinisane kategorije ekonomske razvijenosti,sadržane u izveštaju Ujedinjenih nacija pod nazivom World Economic Situation and Prospects 2012(WESP 2012). Cilj rada je automatizacija procesa kategorisanja zemalja,definisanje skupa ključnih merljivih indikatora ekonomske razvijenosti,kao i apostrofiranje značaja neuronskih mreža za rešavanje klasifikacionih problema.Istraživanje obuhvata klasifikaciju 168 zemalja u 4 grupe ekonomske razvijenosti upotrebom 7 odabranih merljivih indikatora.Podaci iz zvaničnih izveštaja međunarodnih ekonomskih institucija poslužili su za obučavanje inteligentnog sistema odlučivanja zasnovanog na neuronskoj mreži,a kao mera kvaliteta obuke upotrebljena je confusion matrica,koja prikazuje preciznost inteligentnog sistema utvrđivanjem procenta poklapanja sa iskustveno dobijenim podacima.Preciznost automatske klasifikacije govori o neuronskim mrežama kao moćnom aparatu za rešavanje klasifikacionih problema,ali i o opravdanosti izbora klasifikacionih parametara i njihovoj važnosti.Važnost izabranih indikatora ogleda se u tome što je poznavanje njihovih vrednosti dovoljan uslov za automatsku klasifikaciju nivoa pouzdanosti od 80%.
关键词：economic development of countries;economic development indicators;neural networks;backpropagation algorithm;Matlab neural network toolbox
