Araştırma Makalesi
BibTex RIS Kaynak Göster

Time Series Prediction with Direct and Recurrent Neural Networks

Yıl 2017, Cilt: 01 Sayı: 1, 7 - 15, 23.08.2017

Öz

Presents a comparative study for prediction of time series of the Consumer Price Index-CPI using recurrent neural network (RNN).  For this, three models are designed for networks with recurrent and are given the changes in "backpropagation" to allow them to incorporate the models ARX (Auto-Regressive with external input) and NARX (Nonlinear Auto Regressive with external input). Furthermore, we present a third architecture, re-fed with the hidden layer, nicknamed ARXI, which is a special case of the Elman Network. Is carried out training for all networks and tests the ability to generalize them (identification stage), in order to select the best architectures of recurrent networks to prediction of the IPC. After this stage, it makes the models validation, by means of the test the extrapolation capacity of the networks, i.e., presented data were not used during the training phase and gets the responses that indicate the capacity to predict future CPI for various times (validation phase). We conclude that NARX networks are those with best performance and that the hybrid system proposed by [5] constitutes an excellent tool when you want to get minimal networks that make a series of perdition satisfactorily.

Kaynakça

  • Lam M., Neural network techniques for financial performance prediction: integrating fundamental and technical analysis. Decision Support Systems 37, 2004; 567-581.
  • Yao J.T., Towards a better forecasting model for economic indices. In: Proceedings of the 6th Joint Conference on Information Science, 2002; 299-303.
  • José M. Menezes Jr. & Guilherme A. Barreto A New Look at Nonlinear Time Series Prediction with NARX Recurrent Neural Network, IX Brazilian Neural Networks Symposium (SBRN'2006), (2006), Ribeirão Preto-SP.
  • S. Crone (2005) Stepwise Selection of Artificial Neural Network Models for Time Series Prediction, Journal of Intelligent Systems, Vol. 14, No. 2-3, 2005, pp. 99-122.
  • De Campos L.M.L, R. M., A Biologically inspired methodology for neural networks design In: IEEE Conference on Cybernetics and Intelligent Systems. IEEE, pp. 619-624, 2004.
  • Cant-Paz, E. and C. Kamath, An empirical comparison of combinations of evolutionary algorithms and neural networks for classification problems, IEEE Transactions on Systems, Man, and Cybernetics-Part B: Cybernetics, pages 915-927, 2007.
  • N. Feng, G. Ning, and X. Zheng, A Framework for simulating axon guidance, In: Proceedings of Neuro computing, 2005, pp.70-84.
  • De Campos, Lídio Mauro Lima ; Roisenberg, Mauro ; Oliveira, Roberto Célio Limão de . (Accept) Automatic Design of Neural Networks with L-Systems and Genetic Algorithms - A Biologically Inspired Methodology. IJCNN 2011 - IEEE International Joint Conference on Neural Networks – San Jose, California, USA, 2011.
  • M.Tomita. Dynamic construction of Finite automata from examples using hill-climbing. In: Proceedings of the Fourth Annual Conference of the Cognitive Science Society. Ann Arbor, MI, pp. 105-108, 1982.
  • Aguirre, L.A., Introdução à Identificação de Sistemas, Editora UFMG, terceira edição, 2007.
  • PARK, D. C. et. al. Electrical load forecasting using an artificial neural network. Artificial Neural Network: forecasting time series. E.U.A., IEEE Press, p. 43-49, 1994.
  • LIN, T. et al. Learning long-term dependencies in NARX recurrent neural networks. IEEE Transactions on Neural Networks, v. 7, n. 6, p. 1424_1438, 1996.
Yıl 2017, Cilt: 01 Sayı: 1, 7 - 15, 23.08.2017

Öz

Kaynakça

  • Lam M., Neural network techniques for financial performance prediction: integrating fundamental and technical analysis. Decision Support Systems 37, 2004; 567-581.
  • Yao J.T., Towards a better forecasting model for economic indices. In: Proceedings of the 6th Joint Conference on Information Science, 2002; 299-303.
  • José M. Menezes Jr. & Guilherme A. Barreto A New Look at Nonlinear Time Series Prediction with NARX Recurrent Neural Network, IX Brazilian Neural Networks Symposium (SBRN'2006), (2006), Ribeirão Preto-SP.
  • S. Crone (2005) Stepwise Selection of Artificial Neural Network Models for Time Series Prediction, Journal of Intelligent Systems, Vol. 14, No. 2-3, 2005, pp. 99-122.
  • De Campos L.M.L, R. M., A Biologically inspired methodology for neural networks design In: IEEE Conference on Cybernetics and Intelligent Systems. IEEE, pp. 619-624, 2004.
  • Cant-Paz, E. and C. Kamath, An empirical comparison of combinations of evolutionary algorithms and neural networks for classification problems, IEEE Transactions on Systems, Man, and Cybernetics-Part B: Cybernetics, pages 915-927, 2007.
  • N. Feng, G. Ning, and X. Zheng, A Framework for simulating axon guidance, In: Proceedings of Neuro computing, 2005, pp.70-84.
  • De Campos, Lídio Mauro Lima ; Roisenberg, Mauro ; Oliveira, Roberto Célio Limão de . (Accept) Automatic Design of Neural Networks with L-Systems and Genetic Algorithms - A Biologically Inspired Methodology. IJCNN 2011 - IEEE International Joint Conference on Neural Networks – San Jose, California, USA, 2011.
  • M.Tomita. Dynamic construction of Finite automata from examples using hill-climbing. In: Proceedings of the Fourth Annual Conference of the Cognitive Science Society. Ann Arbor, MI, pp. 105-108, 1982.
  • Aguirre, L.A., Introdução à Identificação de Sistemas, Editora UFMG, terceira edição, 2007.
  • PARK, D. C. et. al. Electrical load forecasting using an artificial neural network. Artificial Neural Network: forecasting time series. E.U.A., IEEE Press, p. 43-49, 1994.
  • LIN, T. et al. Learning long-term dependencies in NARX recurrent neural networks. IEEE Transactions on Neural Networks, v. 7, n. 6, p. 1424_1438, 1996.
Toplam 12 adet kaynakça vardır.

Ayrıntılar

Birincil Dil İngilizce
Konular Matematik
Bölüm Articles
Yazarlar

Lidio Mauro Lima De Campos

Yayımlanma Tarihi 23 Ağustos 2017
Gönderilme Tarihi 18 Nisan 2017
Kabul Tarihi 20 Temmuz 2017
Yayımlandığı Sayı Yıl 2017 Cilt: 01 Sayı: 1

Kaynak Göster

APA De Campos, L. M. L. (2017). Time Series Prediction with Direct and Recurrent Neural Networks. Turkish Journal of Forecasting, 01(1), 7-15.
AMA De Campos LML. Time Series Prediction with Direct and Recurrent Neural Networks. TJF. Ağustos 2017;01(1):7-15.
Chicago De Campos, Lidio Mauro Lima. “Time Series Prediction With Direct and Recurrent Neural Networks”. Turkish Journal of Forecasting 01, sy. 1 (Ağustos 2017): 7-15.
EndNote De Campos LML (01 Ağustos 2017) Time Series Prediction with Direct and Recurrent Neural Networks. Turkish Journal of Forecasting 01 1 7–15.
IEEE L. M. L. De Campos, “Time Series Prediction with Direct and Recurrent Neural Networks”, TJF, c. 01, sy. 1, ss. 7–15, 2017.
ISNAD De Campos, Lidio Mauro Lima. “Time Series Prediction With Direct and Recurrent Neural Networks”. Turkish Journal of Forecasting 01/1 (Ağustos 2017), 7-15.
JAMA De Campos LML. Time Series Prediction with Direct and Recurrent Neural Networks. TJF. 2017;01:7–15.
MLA De Campos, Lidio Mauro Lima. “Time Series Prediction With Direct and Recurrent Neural Networks”. Turkish Journal of Forecasting, c. 01, sy. 1, 2017, ss. 7-15.
Vancouver De Campos LML. Time Series Prediction with Direct and Recurrent Neural Networks. TJF. 2017;01(1):7-15.

INDEXING

   16153                        16126   

  16127                       16128                       16129