Jordan Pi-sigma neural network for temperature prediction

Husaini, Noor Aida and Ghazali, Rozaida and Mohd Nawi, Nazri and Ismail, Lokman Hakim (2011) Jordan Pi-sigma neural network for temperature prediction. In: Ubiquitous Computing and Multimedia Applications: International Conference, UCMA 2011, Korea, April 11-13, Proceedings. Springer-Verlag Berlin Heidelberg, pp. 547-558. (Unpublished)

Full text not available from this repository.


This study examines and analyses the use of a new recurrent neural network model: Jordan Pi-Sigma Network (JPSN) as a forecasting tools. JPSN's ability to predict future trends of temperature was tested and compared to that of Multilayer Perception (MLP) and the standard Pi-Sigma Neural Network (PSNN); trained with the standard gradient descent algorithm. A set of historical temperature for five years from Malaysian Meteorological Department was used as input data train the networks for the next-day prediction. Simulation results show that JPSN forecast comparatively superior to MLP and PSNN models, with lower prediction error, thus revealing a great potential in predicting the temperature measurement.

Item Type:Book Section
Subjects:Q Science > QA Mathematics > QA76 Computer software
Divisions:Faculty of Science Computer and Information Technology > Department of Software Engineering
ID Code:3040
Deposited By:Normajihan Abd. Rahman
Deposited On:21 Feb 2013 15:10
Last Modified:21 Feb 2013 15:10

Repository Staff Only: item control page