A genetic-based neuro-fuzzy approach for prediction of solar activity

Abdel-Fattah A. Attia; Rabab H. Abdel-Hamid; Maha Quassim

doi:10.1117/12.553201

16 September 2004 A genetic-based neuro-fuzzy approach for prediction of solar activity

Abdel-Fattah A. Attia, Rabab H. Abdel-Hamid, Maha Quassim

Proceedings Volume 5497, Modeling and Systems Engineering for Astronomy; (2004) https://doi.org/10.1117/12.553201
Event: SPIE Astronomical Telescopes + Instrumentation, 2004, Glasgow, United Kingdom

Abstract

This paper presents an application of the neuro-fuzzy modeling to analyze the time series of solar activity, as measured through the relative Wolf number. The neuro-fuzzy structure will be optimized based on the linear adapted genetic algorithm with controlling population size (LAGA-POP). First, the dimension of the time series characteristic attractor is obtained based on the smallest Regularity Criterion (RC) and the neuro-fuzzy modeling. Second, after describing the neuro-fuzzy structure and optimizing its parameters based on LAGA-POP, the performance of the present approach in forecasting yearly sunspot numbers is favorably compared to that of other published methods. Finally, the comparison predictions for the remaining part of the 22nd and the whole 23rd cycle of solar activity are presented.

Citation Download Citation

Abdel-Fattah A. Attia, Rabab H. Abdel-Hamid, and Maha Quassim "A genetic-based neuro-fuzzy approach for prediction of solar activity", Proc. SPIE 5497, Modeling and Systems Engineering for Astronomy, (16 September 2004); https://doi.org/10.1117/12.553201

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available