Pemodelan Rangkaian Suap Balik Elman bagi Peramalan Harga Rumah

Authors

  • Siti Mariyam Hj. Shamsuddin Fakulti Sains Komputer dan Sistem Maklumat Universiti Teknologi Malaysia, Malaysia
  • Siti Zaiton Mohd Hashim Fakulti Sains Komputer dan Sistem Maklumat Universiti Teknologi Malaysia, Malaysia
  • Rozaida Ghazali Fakulti Sains Komputer dan Sistem Maklumat Universiti Teknologi Malaysia, Malaysia
  • Azuraliza Abu Bakar Fakulti Teknologi dan Sains Maklumat Universiti Kebangsaan Malaysia, Malaysia

DOI:

https://doi.org/10.32890/ijms2006.13.2.10

Keywords:

Rangkaian Suap Balik, rangkaian elman, rangkaian neural piawai, pemodelan, peramalan

Abstract

Artikel ini rnembincangkan satu pendekatan Rangkaian Suap Balik iaitu Rangkaian Elrnan bagi peramalan harga rumah teres di Kuala Lumpur. Rangkaian Elman dengan algoritma pembelajaran rambatan balik dikaji bagi mencerap kelakuan data perumahan untuk mendapatkan satu model peramalan yang baik. Lapan faktor yang mempengaruhi harga rumah dicadangkan dan diolah sebagai input parameter rangkaian suap balik Elman. Berdasarkan kutipan pembelajaran pada rangkaian Elman terhadap 80% data latihan perumahan, didapati bahawa rangkaian ini berjaya menghasilkan keputusan yang lebih baik dengan kadar pengelasan adalah 97.6% dan penghasilan ralat yang kecil iaitu 0.012744 terhadap 20% data ujian perurnahan tahun 1997.

 

Downloads

Download data is not yet available.

References

Fausett, L. (1994). Fundamentals of Neural Network Architecture, Algorithm, and Applications. New Jersey: Prentice Hall, Inc.

Grudnitski, G. (1997). Valuation of Residential Properties using a Neural Network. IOP Publishing Ltd. & Oxford University Press. Ku Ruhana Ku Mahamud, Azuraliza Abu Bakar, & Norita Norwawi. (1998). Neural network modeling to predict house price performance. Research Report, School of Information Technology, Universiti Utara Malaysia.

Rossini, P. (1997). Application of Artificial Neural Networks to the Valuation of Residential Property. 3“* Pacific RIM Real Estate Society Conference, New Zealand.

Rossini, P. (1998). Improving the result of ANN Models for residential valuation. Proceeding of the 4!" Annual Pacific — Rim Real Estate Society Conference, Perth, Australia.

Rodriguez, P., Wiles, J., & Elman, J. L. (1999). A recurrent neural network that learns to counts. Connection Science, 11(1), 5-40. IJMS 13 (2), 217-230 (2006) 229

Wang, H. & Ho, K. H. (1995). Artificial intelligent modeling of the private housing market in Singapore. Proceeding of the International Congress on Real Estate, Singapore, 1-10.

Wilson, I., Paris, S., Ware, A., & Jenkins, D. (2002). Residential price forecasting at Regional dan National Levels. FIG XXII International Congress, Washington, D. C, USA..um.edu.my www.ijms 230 IJMS 13 (2), 217-230 (2006)

Downloads

Published

06-12-2006

Issue

Vol. 13 No. 2 (2006): International Journal of Management Studies (IJMS) Vol. 13, No. 2 December 2006

Section

Articles

Research impact

Harvested 2026-09-08
0 citations recorded so far

Counts differ between services because each indexes a different body of literature. None of them is the whole picture.

Identifiers DOI 10.32890/ijms2006.13.2.10 OpenAlex W195156647

Most read articles by the same author(s)