Universiti Teknologi Malaysia Institutional Repository

Univariate Artificial Neural Network In Forcasting Demand Of Low Cost House In Petaling Jaya

Bakhary, Norhisham and Yahya, Khairulzan and Ng Chin, Nam (2004) Univariate Artificial Neural Network In Forcasting Demand Of Low Cost House In Petaling Jaya. Jurnal Teknologi B (40B). pp. 67-75. ISSN 0127-9696

[img]
Preview
PDF
511Kb

Official URL: http://www.penerbit.utm.my/onlinejournal/40/B/JTJU...

Abstract

Recently researchers have found the potential applications of Artificial Neural Network (ANN) in various fields in civil engineering. Many attempts to apply ANN as a forecasting tool has been successful. This paper highlighted the application of Time Series Univariate Neural Network in forecasting the demand of low cost house in Petaling Jaya district, Selangor, using historical data ranging from February 1996 to April 2000. Several cases of training and testing were conducted to obtain the best neural network model. The lowest Root Mean Square Error (RMSE) obtained for validation step is 0.560 and Mean Absolute Percentage Error (MAPE) is 8.880 %. These results show that ANN is able to provide reliable result in term of forecasting the housing demand based on previous housing demand record.

Item Type:Article
Uncontrolled Keywords:Time Series Univariate Neural Network, low cost housing demand, RMSE, MAPE
Subjects:T Technology > TA Engineering (General). Civil engineering (General)
Divisions:Civil Engineering
ID Code:1538
Deposited By: En Mohd. Nazir Md. Basri
Deposited On:07 Mar 2007 07:03
Last Modified:03 Sep 2012 09:21

Repository Staff Only: item control page