Sains Malaysiana 30: 107-118 (2001) Sains Matematik/ Mathematical Sciences
Peramalan Siri Masa Bermusim Menggunakan Rangkaian Nueral Terhadap Nyahmusim Data (Prediction of Seasonal Time Series Using Neural Network Towards Deseasonalised Data)
Roselina bte Sallehuddin, Mohd Salihin Ngadiman & Siti Mariyam Hj Shamsuddin Fakulti Sains Komputer dan Sistem Maklumat Universiti Teknologi Malaysia 81310 Skudai Johor, Malaysia
ABSTRAK
Rencana ini membincangkan peramalan data siri masa bermusim menggunakan salah satu daripada teknik perhitungan lembut, iaitu rangkaian neural terhadap data yang sudah dinyahmusim bagi melihat prestasi rangkaian terhadap rangkaian. Hasil yang diperoleh menggunakan kedua jenis data ini dibandingkan, dan didapati bahawa keputusan peramalan menggunakan model rangkaian neural terhadap data nyahmusim adalah lebih baik dengan kadar peratusan peramalan adalah tinggi. Bagi tujuan perbandingan, hasil yang diperoleh menggunakan kaedah rangkaian neural dibandingkan dengan hasil peramalan menggunakan model Box-Jenkins.
ABSTRACT
This paper discusses seasonal time series data using one of the soft computing techniques i.e, neural network, towards deseasonalised data to investigate its performance on prediction. The results obtained using these data are compared, and it is found that neural network gives higher prediction rates towards deseasonalised data. For comparison purposes, the results using neural network are compared with the predictions is results using Box-Jenkins model.
RUJUKAN/REFERENCES
Box, G.E.P. & Jenkins, G.M. 1976. Time Series Analysis: Forecasting and control. San Francisco. CA: Holden-Day. Chu, C.H. & Widjaja, D. 1994. Neural network system for forecasting method selection. Decision Support Systems 12(13-24). Gent, C.R., Sheppard, C.P. 1992. Predicting time series by a fully connected neural network trained by back propagation. Computing and control Engineering Journal 3(3): 109-112. Hu, M.J.C. 1964. Application of the adaline system to weather forecasting. Technical Report 6775-1. Stanford Electronic Laboratories. Stanford, C.A. Jun. Klimasauaskas, C.C. 1991. Applying Neural Networks. Part 3, Training A Neural Network. PC-A1, May/Jun (pg 202-24). Kuan, C-M. & Liu,T. 1995. Forecasting exchange rates using feed forward and recurrent neural networks. Journal of Applied Econometrics 10:347-364. Lachtermacher, G., Fuller, J.D. 1995. Backpropagation in time series forecasting. Journal of forecasting 14: 381-393. Master,T. 1994. Practical Neural Network Recipies In C++. New York: Academic Press. Rumelhart. D.E., Hinton,G.E. & Williams. R.J. 1986. Learning representation by back-propagating errors. Nature 323(6188): 533-536 Refenes, A.N, M. Azema- Barac & S.A. Karoussos. 1992. Currency Exchange Rate Forecasting by Error BP. Proceeding of The Twenty fifth annual Hawaii International Conference on System Science, 4: 504-515. Roselina Sallehuddin. 1999. Penggunaan Model Rangkaian Neural Dalam Peramalan Siri Masa Bennusim. Tesis Sarjana, Universiti Teknologi Malaysia. Sharda, R. 1994. Neural Networks for the MS/OR analyst: An application bibliography. Interfaces 24(2): 116-130. Sharda, R. & Patil R.B. 1990. Neural Network as forecasting Experts: an empirical test. Proceedings of The International Joint Conference on Neural networks 2: 491-494. Tang, Z., C. de Almeida & P.A. Fishwick. 1991. Time Series Forecasting using Neural Networks Vs Box-Jenkins methodology. Simulation (November): 303310. Weigend,A.S., Huberman, B.A, & Rumelhart D.E. 1992. Predicting sunspots and exchange rates with connectionist networks. In Casdagli, M., Eubank, S. (eds.), Nonlinear Modelling and Forecasting, Redwood City, CA: Addison-Wesley, 395-432 Weigend, A.S., Huberman, B.A. 1991. Generalization by weight-elimination with application to forecasting. Advances in Neural Information Processing Systems 3: 875-882 Widrow, B., Rumelhart, D.E. & Lehr, M.A. 1994. Neural Networks: Applications in industry, business and sciences. Communications of the ACM 37(3): 93-102.
|
|||
|
