Metrika članka

  • citati u SCindeksu: 0
  • citati u CrossRef-u:0
  • citati u Google Scholaru:[=>]
  • posete u poslednjih 30 dana:8
  • preuzimanja u poslednjih 30 dana:2
članak: 6 od 34  
Back povratak na rezultate
Industrija
2014, vol. 42, br. 4, str. 25-42
jezik rada: engleski
vrsta rada: izvorni naučni članak
objavljeno: 09/01/2015
doi: 10.5937/industrija42-5686
Primena neuronske mreže na problem kategorizacije ekonomske razvijenosti zemalja
aUniverzitet u Kragujevcu, Ekonomski fakultet
bUniverzitet u Kragujevcu, Fakultet za hotelijerstvo i turizam, Vrnjačka Banja

e-adresa: sobradovic@kg.ac.rs

Projekat

Izazovi i perspektive strukturnih promena u Srbiji: strateški pravci ekonomskog razvoja i usklađivanja sa zahtevima EU (MPNTR - 179015)

Sažetak

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%.

Ključne reči

ekonomska razvijenost zemalja; indikatori ekonomske razvijenosti; automatska klasifikacija; neuronske mreže; backpropagation algorithm; Matlab neural network toolbox

Reference

*** (2011) United Nations Development Programme. Human Development Report 2011 (HDR 2011). http://www.undp.org/content/undp/en/home.html
*** (2013) United Nations Development Programme. Human Development Report 2013 (HDR 2013). http://www.undp.org/content/undp/en/home.html
*** (2012) United Nations. World Economic Situation and Prospects 2012 (WESP 2012). http://www.un.org/en/
Adewole, A.P., Akinwale, A.T., Akintomide, A.B. (2011) Artificial Neural Network Model for Forecasting Foreign Exchange Rate. World of Computer Science and Information Technology Journal (WCSIT), 1(3): 110-, http://v1.wcsit.org/
Al-Shawadfi, A.M.G., Al-Hindi, A.H. (2003) Automatic Classification Using Neural Networks. International Journal of The Computer, The Internet and Management, 11(3): 72-, http://www.ijcim.th.org/
Bishop, C.M. (2000) Neural Networks for Pattern Recognition. Oxford university press
Goh, W.L., Mital, D.P., Babri, H.A. (1997) An artificial neural network approach to handwriting recognition. u: Knowledge-Based Intelligent Electronic Systems, First International Conference Adelaide South Australia, http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=4869
Haider, A., Hanif, N.M. (2009) Inflation Forecasting in Pakistan Using Artificial Neural Networks. Pakistan Economic and Social Review, 47(1): 123, http://pu.edu.pk/home/journal/7
Hart, A. (1992) Using Neural Networks for Classification Tasks - Some Experiments on Datasets and Practical Advice. Journal of the Operational Research Society, 43(3): 215, http://www.palgrave-journals.com/jors/index.html
Helbicha, M., Hagenauera, J., Leitnerb, M., Edwardsc, R. (2013) Exploration of unstructured narrative crime reports: an unsupervised neural network and point pattern analysis approach. Journal of the Cartography and Geographic Information Society, 40(4): 326, http://www.cartogis.org/
Li, Y. (2013) Evaluation of Psychological Contract Based on Neural Network. International Journal of Applied Mathematics and Statistics, 45(15): 28, http://www.ceser.in/ceserp/index.php/ijamas
Maier, R.H., Dandy, C.G. (2000) Neural networks for the prediction and forecasting of water resources variables: a review of modelling issues and applications. Environmental Modelling & Software, 15(1): 101, http://www.journals.elsevier.com/environmental-modelling-and-software/
Mitchell, R.J., Keating, D.A. (1998) Neural Network Control of Simple Mobile Robot. u: Landau L.J., Taylor J.G. [ur.] Concepts for Neural Networks, London: Springer, : 95-107
Naeini, M.P., Taremian, H., Hashemi, H.B. (2010) Stock Market Value Prediction Using Neural Networks. u: International Conference on Computer Information Systems and Industrial Management Applications (CISIM), http://www.mirlabs.org/cisim10/
Nittis, D.F., Tecchiolli, G., Zorat, A. (1998) Consumer Loan Classification Using Artificial Neural Networks. u: International ICSC Symposium on Engineering of Intelligent Systems, http://www.emeraldinsight.com/journals.htm?articleid=1472160&show=html
Önder, E., Bayɪr, F., Hep, en A. (2013) Forecasting Macroeconomic Variables using Artificial Neural Network and Traditional Smoothing Techniques. Journal of Applied Finance & Banking, 3(4): 73-1, http://www.scienpress.com/journal_focus.asp?main_id=56&Sub_id=IV
Ostafe, D. (2008) Interpretation of ECG Signal with a Multi-Layer Neural Network. Journal of Applied Computer Science, (3): 24-27, http://it.p.lodz.pl/course/view.php?id=12
Prantik, R., Vina, V. (2004) Neural Network Models for Forecasting Mutual Fund Net Asset Value. u: 8th Capital Markets Conference, Indian Institute of Capital Markets Paper, http://papers.ssrn.com/sol3/JELJOUR_Results.cfm?form_name=journalbrowse&journal_id=818444
Ripley, B.D. (1994) Neural Networks and Related Methods for Classification. Journal of the Royal Statistical Society, Series B (Methodological), 56(3): 409, http://search.lib.cam.ac.uk/?itemid=%7Ceresources%7C54729
Russell, J.S., Norvig, P. (2003) Artifical Intelligence - A modern Approach. Pearson Education International
Tagliarini, G.A., Christ, J.F., Page, E.W. (1991) Optimization using neural networks. IEEE Transactions on Computers, 40(12): 1347-1358, http://www.computer.org/portal/web/tc
The World Bank (2013) World Development Indicators, (WDI). http://databank.worldbank.org/data/home.aspx
Tsenov, G.T., Mladenov, V.M. (2010) Speech recognition using neural networks. u: 10th Symposium on Neural Network Applications in Electrical Engineering, http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=5628343
Vesely, A. (2011) Economic classification and regression problems and neural networks. Agricultural Economics, 57(3): 150, http://www.agriculturejournals.cz/web/AGRICECON.htm
Yashpal, S., Alok, S.C. (2009) Neural networks in data mining. Journal of Theoretical and Applied Information Technology, 5(1): 37-4, http://www.jatit.org/
Yin, X.Y., Wu, G.C., Yang, F.L. (1996) Predicting oil and gas reservoir and calculating thickness of reservoir from seismic data using neural network. u: 3rd International Conference on Signal Processing Proceedings, http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=4274