ZAMAN SERİLERİ TAHMİNİNDE ARIMA-MLP MELEZ MODELİ
Yıl 2009,
Cilt: 23 Sayı: 3, 141 - 149, 12.08.2010
Oğuz Kaynar
Serkan Taştan
Öz
Bu çalışmada zaman serilerinin tahmini için otoregresif hareketli
ortalamalar(autoregressive integrated moving average-ARIMA) modeli ve çok
katmanlı yapay sinir ağları (multi layer perceptron-MLP) modeli birleştirilerek
bir melez model oluşturulmuştur. Melez modelde, zaman serisinin doğrusal
bileşeni ARIMA modeli ile doğrusal olmayan bileşeni ise MLP modeli ile
tahmin edilmiştir. ARIMA ve MLP modellerinin tek başına kullanılması ile elde
edilen tahmin sonuçları Melez modelin tahmin sonuçları ile karşılaştırılarak
Melez modelin tahmin performansı ölçülmüştür.
Kaynakça
- Wedding D.K. ve Cios K.J. (1996), “Time series forecasting by combining RBF networks, certainty factors, and the Box–Jenkins model”, Neurocomputing, 10, ss.149–168.
- Donaldson, R.G. ve Kamstra, M. (1996), “Forecasting combining with neural networks”, Journal of Forecasting, 15, ss.49–61.
- Pelikan, E., Groot, C. ve Wurtz, D. (1992) “Power consumption in WestBohemia: improved forecasts with decorrelating connectionist Networks”, Neural Network World, 2, ss.701–712.
- Tseng,F.-M.,Yu, H.-C. ve Tzeng, G.-H. (2002),"Combining neural network model with seasonal time series ARIMA model", Technological Forecasting and Social Change, 69, ss.71-87.
- Fausett, L. (1994),”Fundamentals of Neural Networks: Architectures, Algorithms and Applications”, Prentice Hall.
- Hansen, J. ve Nelson, R. (2003), “Time-series analysis with neural Networks and ARIMA-neural network hybrids”, Journal of Experimental and Theoretical Artificial Intelligence, 15(3), ss.315–330.
- Hippert, H.S., Pedreira, C.E. ve Souza, R.C. (2001), “Neural networks for shortterm load forecasting: a review and evaluation”, IEEE Transactions on Power System, 16, ss.44–55.
- Ginzburg, I. ve Horn, D. (1994), “Combined neural networks for time series analysis”, Adv. Neural Inf. Process.Systems, 6, ss.224–231.
- Öztemel, Ercan (2003),”Yapay Sinir Ağları, Papatya Yayıncılık”, İstanbul.
- Zhang G. P. (2003) ,”Time series forecasting using a hybrid ARIMA and neural network model”, Neurocomputing, 50, ss.159-175.
- Zhang, G., Patuwo, B. E. ve Hu, M. Y. (1998) “Forecasting with artificial neural networks: the state of the art”, International Journal of Forecasting, 14, ss.35-62.
Yıl 2009,
Cilt: 23 Sayı: 3, 141 - 149, 12.08.2010
Oğuz Kaynar
Serkan Taştan
Kaynakça
- Wedding D.K. ve Cios K.J. (1996), “Time series forecasting by combining RBF networks, certainty factors, and the Box–Jenkins model”, Neurocomputing, 10, ss.149–168.
- Donaldson, R.G. ve Kamstra, M. (1996), “Forecasting combining with neural networks”, Journal of Forecasting, 15, ss.49–61.
- Pelikan, E., Groot, C. ve Wurtz, D. (1992) “Power consumption in WestBohemia: improved forecasts with decorrelating connectionist Networks”, Neural Network World, 2, ss.701–712.
- Tseng,F.-M.,Yu, H.-C. ve Tzeng, G.-H. (2002),"Combining neural network model with seasonal time series ARIMA model", Technological Forecasting and Social Change, 69, ss.71-87.
- Fausett, L. (1994),”Fundamentals of Neural Networks: Architectures, Algorithms and Applications”, Prentice Hall.
- Hansen, J. ve Nelson, R. (2003), “Time-series analysis with neural Networks and ARIMA-neural network hybrids”, Journal of Experimental and Theoretical Artificial Intelligence, 15(3), ss.315–330.
- Hippert, H.S., Pedreira, C.E. ve Souza, R.C. (2001), “Neural networks for shortterm load forecasting: a review and evaluation”, IEEE Transactions on Power System, 16, ss.44–55.
- Ginzburg, I. ve Horn, D. (1994), “Combined neural networks for time series analysis”, Adv. Neural Inf. Process.Systems, 6, ss.224–231.
- Öztemel, Ercan (2003),”Yapay Sinir Ağları, Papatya Yayıncılık”, İstanbul.
- Zhang G. P. (2003) ,”Time series forecasting using a hybrid ARIMA and neural network model”, Neurocomputing, 50, ss.159-175.
- Zhang, G., Patuwo, B. E. ve Hu, M. Y. (1998) “Forecasting with artificial neural networks: the state of the art”, International Journal of Forecasting, 14, ss.35-62.