Forecasting sunspot numbers with Feedforward Neural Networks (FNN) using ‘Sunspot Neural Forecaster’ system

Author

Samin, Reza Ezuan ; Saealal, Muhammad Salihin ; Khamis, Azme ; Isa, Syahirbanun ; Kasmani, Ruhaila Md

Author_Institution

Fac. of Electr. & Electron. Eng., Univ. Malaysia Pahang, Pekan, Malaysia

fYear

2011

fDate

21-22 June 2011

Firstpage

1

Lastpage

5

Abstract

This paper presents the investigations of forecasting performance of different type of Feedforward Neural Networks (FNN) in forecasting the sunspot numbers. Feedforward Neural Network will be used in this investigation by using different learning algorithms, sunspot data models and FNN transfer functions. Simulations are done using Matlab 7 where customized Graphic User Interface (GUI) called `Sunspot Neural Forecaster´ have been developed for analysis. A complete analysis for different learning algorithms, sunspot data models and FNN transfer functions are examined in terms of Mean Square Error (MSE) and correlation analysis. Finally, the best optimized FNN parameters will be used to forecast the sunspot numbers.

Keywords

astronomy computing; feedforward neural nets; graphical user interfaces; learning (artificial intelligence); mathematics computing; sunspots; FNN transfer functions; Matlab 7 simulation; correlation analysis; feedforward neural networks; graphic user interface; learning algorithms; mean square error; sunspot data models; sunspot neural forecaster system; sunspot number forecasting; Algorithm design and analysis; Analytical models; Artificial neural networks; Correlation; Forecasting; Mathematical model; Transfer functions; Feedforward Neural Networks (FNN); Mean Square Error (MSE); Sunspot numbers;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical, Control and Computer Engineering (INECCE), 2011 International Conference on

Conference_Location

Pahang

Print_ISBN

978-1-61284-229-5

Type

conf

DOI

10.1109/INECCE.2011.5953839

Filename

5953839