An adaptive and robust method for predicting solar activity cycles based on historical data and data-dependent parameters.

MWITONDI, Kassim and SAID, Raed (2012). An adaptive and robust method for predicting solar activity cycles based on historical data and data-dependent parameters. In: The Third Palestinian Conference on Modern Trends in Mathematics and Physics, Hebron, 16-18 July 2012. (Submitted)

Full text not available from this repository.
Official URL: http://www.pcmtmp.org/

Abstract

Modelling of the natural phenomena encompassed within our universe has for long been a subject of research in many disciplines. Conventionally, modelling of such phenomena has relied on the deployment of mathematical models - typically built on specific underlying assumptions. But with the model densities and parameters typically having to be estimated from data, in most applications, the need to develop adaptive methods of data analysis has grown alongside enhancements in methods of data acquisition. In recent years, scientists have paid an increasingly closer attention to the overall behaviour of the solar magnetic activity cycles. We propose an adaptive and robust approach to modelling and providing real-time predictions of the solar activity cycles based on its 11-year frequency of sunspots. Key Words: Clustering, Data Mining, Predictive Modelling, Solar Magnetic Activity, Sunspots, Supervised Modelling, Support Vector Machines, Unsupervised Modelling.

Item Type: Conference or Workshop Item (Paper)
Research Institute, Centre or Group: Centre for Health and Social Care Research
Depositing User: Kassim Mwitondi
Date Deposited: 12 Jun 2012 12:12
Last Modified: 12 Jun 2012 12:12
URI: http://shura.shu.ac.uk/id/eprint/5302

Actions (login required)

View Item

Downloads

Downloads per month over past year

View more statistics