16 September 2004 A genetic-based neuro-fuzzy approach for prediction of solar activity
Author Affiliations +
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.
© (2004) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Abdel-Fattah A. Attia, Abdel-Fattah A. Attia, Rabab H. Abdel-Hamid, Rabab H. Abdel-Hamid, Maha Quassim, 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); doi: 10.1117/12.553201; https://doi.org/10.1117/12.553201

Back to Top