This Author published in this journals
All Journal Statistika
Claim Missing Document
Check
Articles

Found 2 Documents
Search

Forecasting Malaysia Load Using a Hybrid Model Norizan Mohamed; Maizah Hura Ahmad
STATISTIKA: Forum Teori dan Aplikasi Statistika Vol 10, No 1 (2010)
Publisher : Program Studi Statistika Unisba

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29313/jstat.v10i1.1003

Abstract

A hybrid model, which combines the seasonal time series ARIMA (SARIMA) and the multilayer feedforwardneural network to forecast time series with seasonality, is shown to outperform both twosingle models. Besides the selection of transfer functions, the determination of hidden nodes to usefor the non linear model is believed to improve the accuracy of the hybrid model. In this paper, wefocus on the selection of the appropriate number of hidden nodes on the non linear model to forecastMalaysia load. Results show that by using only one hidden node, the hybrid model of Malaysia loadperforms better than both single models with mean absolute percentage error (MAPE) of less than 1%.
An Artificial Neural Networks Forecasting for Malaysia’s Load Norizan Mohamed; Maizah Hura Ahmad; Zuhaimy Ismail; Khairil Anuar Arshad
STATISTIKA: Forum Teori dan Aplikasi Statistika Vol 8, No 2 (2008)
Publisher : Program Studi Statistika Unisba

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29313/jstat.v8i2.985

Abstract

In this paper, two artificial neural networks models, namely the multilayer feedforward neuralnetwork and the recurrent neural network are applied for Malaysia's load forecasting. A half hourlyload data is divided equally into three distinct sets for training, validation and testing.Backpropagation is selected as the learning algorithm whereas the transfer function for both hiddenlayer and output layer is sigmoid the function. The forecasting performances were compared betweenthese two models. The results show that, the sum squared error (SSE) of multilayer feedforwardneural network were the lowest hence the multilayer feedforward neural network is a better model fora half hourly Malaysia's load.