Solar Storm Type Classification Using Probabilistic Neural Network compared with the Self-Organizing Map

Satiabudhi, Gregorius and Adipranata, Rudy and Setiahadi, Bambang and N, ADRIAN HARTANTO (2012) Solar Storm Type Classification Using Probabilistic Neural Network compared with the Self-Organizing Map. Jurnal Ilmiah KURSOR, Vol. 6 (No. 4). 211 - 220. ISSN 0216-0544

PDF Download (409Kb)

Abstract

One of the task of the LAPAN is making observation and forecasting of solar storms disturbance. This disturbances can affect the earths electromagnetic field that disrupt the electronic and navigational equipment on earth. LAPAN wanted a computer application that can automatically classify the type of solar storms, which became part of early warning systems to be created. The classification of the digital images of solar storm / sunspot is based on Modified - Zurich Sunspot Classification System. Classification method that we use here is the Probabilistic Neural Networks. The result of testing is promising because it has an accuracy of 94 for testing data. The accuracy is better than the accuracy of similar applications weve built with a combination of methods Self-Organizing Map and K-Nearest Neighbor.

Actions (login required)