Pi-Sigma neural network for temperature forecasting in Batu Pahat

Husaini, Noor Aida and Ghazali, Rozaida and Mohd Nawi, Nazri and Ismail, Lokman Hakim (2011) Pi-Sigma neural network for temperature forecasting in Batu Pahat. In: Software Engineering and Computer Systems, Second International Conference, ICSECS 2011, Kuantan Pahang, Malaysia, June 27-29, 2011, Proceedings, Part II. Springer-Verlag Berlin Heidelberg, pp. 530-541. (Unpublished)

Full text not available from this repository.


In this study, two artificial neural network (ANN) models, a Pi-Sigma Neural Network (PSNN) and a three-layer multilayer perceptron (MLP), are applied for temperature forecasting. PSNN is use to overcome the limitation of widely used MLP, which can easily get stuck into local minima and prone to overfitting. Therefore, good generalization may not be obtained. The models were trained with backpropagation algorithm on historical temperature data of Batu Pahat region. Through 810 experiments, we found that PSNN performs considerably better results compared to MLP for daily temperature forecasting and can be suitably adapted to forecasts a particular region using the historical data over larger geographical areas.

Item Type:Book Section
Uncontrolled Keywords:pi-sigma neural network; temperature forecasting; backpropagation
Subjects:Q Science > QA Mathematics > QA76 Computer software
Divisions:Faculty of Science Computer and Information Technology > Department of Software Engineering
ID Code:3042
Deposited By:Normajihan Abd. Rahman
Deposited On:21 Feb 2013 15:19
Last Modified:21 Feb 2013 15:19

Repository Staff Only: item control page