Universiti Teknologi Malaysia Institutional Repository

Forecasting of the rice yields time series forecasting using artificial neural network and statistical model

Shabri , Ani and Samsudin, Ruhaidah and Ismail, Zuhaimy (2009) Forecasting of the rice yields time series forecasting using artificial neural network and statistical model. Journal of Applied Sciences, 9 (23). pp. 4168-4173. ISSN 1812-5654

[img]
Preview
PDF (Abstract)
12Kb
[img] HTML - Published Version
1311Kb

Abstract

Accurate forecasting of the rice yields is very important for the organization to make a better planning and decision making. In this study, a hybrid methodology that combines the individual forecasts based on artificial neural network (CANN) approach for modeling rice yields was investigated. The CANN has several advantages compared with conventional Artificial Neural Network (ANN) model, the statistical the autoregressive integrated moving average (ARIMA) and exponential smoothing (EXPS) model in order to get more effective evaluation. To assess the effectiveness of these models, we used 38 years of time series records for rice yield data in Malaysia from 1971 to 2008. Results show that the CANN model appears to perform reasonably well and hence can be applied to real-life prediction and modeling problems.

Item Type:Article
Uncontrolled Keywords:ARIMA, exponent smoothing, artificial neural network, combining forecasting, rice yields
Subjects:Q Science > Q Science (General)
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:Computer Science and Information System (Formerly known)
ID Code:18982
Deposited By: Ramli Haron
Deposited On:29 Nov 2011 09:04
Last Modified:05 Dec 2013 03:26

Repository Staff Only: item control page