Metrika

  • citati u SCIndeksu: 0
  • citati u CrossRef-u:0
  • citati u Google Scholaru:[]
  • posete u poslednjih 30 dana:6
  • preuzimanja u poslednjih 30 dana:5

Sadržaj

članak: 1 od 5  
Back povratak na rezultate
2017, vol. 45, br. 1, str. 45-60
Prediktivni hibridni sistem za berzansko tržište - slučaj tranzitornih tržišta
aUniverzitet u Novom Sadu, Fakultet tehničkih nauka
bDžavni univerzitet u Novom Pazaru, Departman za matematičke nauke
cUniverzitet Educons, Fakultet poslovne ekonomije, Sremska Kamenica

e-adresav_djakovic@uns.ac.rs
Projekat:
Razvoj novih informaciono-komunikacionih tehnologija, korišćenjem naprednih matematičkih metoda, sa primenama u medicini, telekomunikacijama, energetici, zaštititi nacionalne baštine i obrazovanju (MPNTR - 44006)
Unapređenje konkurentnosti Srbije u procesu pristupanja Evropskoj uniji (MPNTR - 47028)

Sažetak
Predmet istraživanja u radu jeste kreiranje i testiranje poboljšanog fuzzy neural network backpropagation modela za predikciju berzanskih indeksa, uz poređenje sa tradicionalnim neural network backpropagation modelom. Cilj istraživanja jeste dolaženje do konkretnih saznanja o mogućnostima primene poboljšanog fuzzy neural network backpropagation modela za predikciju berzanskih indeksa, sa posebnim fokusom na tranzitorna tržišta. Metodologija korišćena u radu obuhvata integraciju fuzzy-fikovanih tezina u neuro mreži. Rezultati istraživanja biće korisni kako široj investicionoj javnosti, tako i akademskoj struci, u smislu korišćenja poboljšanog modela u donošenju odluka o investiranju i unapređenju znanja u predmetnoj oblasti.
Reference
Barbounis, T.G., Theocharis, J.B. (2007) Locally recurrent neural networks for wind speed prediction using spatial correlation. Information Sciences, 177(24): 5775-5797
Beale, E.M.L. (1972) A derivation of conjugate gradients. u: Lootsma F.A. [ur.] Numerical Methods for Nonlinear Optimization, London: Academic Press, 39-43
Casasent, D., Natarajan, S. (1995) A classifier neural net with complex-valued weights and square-law nonlinearities. Neural Networks, 8(6): 989-998
Cazorla, M.A., Escolano, F. (2003) Two bayesian methods for junction classification. IEEE Transactions on Image Processing, 12(3): 317-327
Cheng, L., Liu, J. (2014) An Optimized Neural Network Classifier for Automatic Modulation Recognition. TELKOMNIKA Indonesian Journal of Electrical Engineering, 12(2):
Draghici, S. (2002) On the capabilities of neural networks using limited precision weights. Neural Networks, 15(3): 395-414
Feuring, T. (1996) Learning in fuzzy neural networks. u: Proceedings of International Conference on Neural Networks (ICNN'96), Institute of Electrical and Electronics Engineers (IEEE), str. 1061-1066
Fletcher, R. (1964) Function minimization by conjugate gradients. Computer Journal, 7(2): 149-154
Gedeon, T. (1999) Additive neural networks and periodic patterns. Neural Networks, 12(4-5): 617-626
Hagan, M.T., Demuth, H.B., Beale, M.H. (1996) Neural network design. Boston: PWS Publishing
Ishibuchi, H., Tanaka, H., Okada, H. (1993) Fuzzy neural networks with fuzzy weights and fuzzy biases. u: IEEE International Conference on Neural Networks, Institute of Electrical and Electronics Engineers (IEEE), str. 1650-1655
Ishibuchi, H., Morioka, K., Tanaka, H. (1994) A fuzzy neural network with trapezoid fuzzy weights. u: Proceedings of 1994 IEEE 3rd International Fuzzy Systems Conference, Institute of Electrical and Electronics Engineers (IEEE), str. 228-233
Islam, M., Murase, K. (2001) A new algorithm to design compact two-hidden-layer artificial neural networks. Neural Networks, 14(9): 1265-1278
Kamarthi, S.V., Pittner, S. (1999) Accelerating neural network training using weight extrapolations. Neural Networks, 12(9): 1285-1299
Lin, C.T., Lee, C.S.G. (1996) Neural fuzzy systems: A neuro-fuzzy synergism to intelligent systems. Upper Saddle River: Prentice-Hall
Melin, P., Gonzalez, C., Bravo, D., Gonzalez, F., Martinez, G. (2006) Modular Neural Networks and Fuzzy Sugeno Integral for Face and Fingerprint Recognition. u: Abraham, Ajith; de Baets, Bernard; Köppen, Mario; Nickolay, Bertram [ur.] Applied Soft Computing Technologies: The Challenge of Complexity, Berlin-Heidelberg: Springer Nature, str. 603-618
Meltser, M., Shoham, M., Manevitz, L.M. (1996) Approximating Functions by Neural Networks: A Constructive Solution in the Uniform Norm. Neural Networks, 9(6): 965-978
Moller, A.F. (1993) A scaled conjugate gradient algorithm for fast supervised learning. Neural Netw, 6: 525-533
Neville, R.S., Eldridge, S. (2002) Transformations of sigma-pi nets: obtaining reflected functions by reflecting weight matrices. Neural Networks, 15(3): 375-393
Phansalkar, V.V., Sastry, P.S. (1994) Analysis of the back-propagation algorithm with momentum. IEEE Transactions on Neural Networks, 5(3): 505-506
Powell, M. J. D. (1977) Restart procedures for the conjugate gradient method. Mathematical Programming, 12(1): 241-254
Riedmiller, M., Braun, H. (1993) A direct adaptive method for faster backpropagation learning: the RPROP algorithm. u: IEEE International Conference on Neural Networks, Institute of Electrical and Electronics Engineers (IEEE), str. 586-591
Salazar-Tejeda, P.A., Melin, P., Castillo, O. (2008) A New Biometric Recognition Technique Based on Hand Geometry and Voice Using Neural Networks and Fuzzy Logic. u: Castillo, Oscar; Melin, Patricia; Kacprzyk, Janusz; Pedrycz, Witold [ur.] Soft Computing for Hybrid Intelligent Systems, Berlin, Heidelberg: Springer Nature, str. 171-186
Wilde, P. (1997) The Magnitude of the Diagonal Elements in Neural Networks. Neural Networks, 10(3): 499-504
Yam, J.Y.F., Chow, T.W.S. (2000) A weight initialization method for improving training speed in feedforward neural network. Neurocomputing, 30(1-4): 219-232
Yeung, D.S., Chan, P.P.K., Ng, W.W.Y. (2009) Radial Basis Function network learning using localized generalization error bound. Information Sciences, 179(19): 3199-3217
 

O članku

jezik rada: engleski
vrsta rada: izvorni naučni članak
DOI: 10.5937/industrija45-11052
objavljen u SCIndeksu: 21.05.2017.
metod recenzije: dvostruko anoniman
Creative Commons License 4.0