34th Solar Physics Division Meeting, June 2003
Session 2 Data Analysis Challenges I
Oral, Monday, June 16, 2003, 1:30-3:30pm, Auditorium

[Previous] | [Session 2] | [Next]

[2.06] Automatic Solar Flare Detection Using MLP, RBF and SVM

M. Qu, F. Shih (College of Computing Sciences,NJIT), J. Jing, H.M. Wang (CFSR, BBSO/NJIT)

The focus of the automatic solar flare detection is on the development of efficient feature-based classifiers. Three advanced techniques used in this work are Multi-Layer Perceptron (MLP), Radial Basis Function (RBF), and Support Vector Machine (SVM) classifiers. We have experimented and compared these three methods for solar flare detection on the solar Halpha images obtained from Big Bear Solar Observatory in California. The preprocessing step is to obtain the nine principal features of the solar flares for the classifiers. Experimental results show that by using SVM, we can obtain the best classification rate of the solar flares. Our work would lead to real-time solar flare detection using advanced pattern recognition techniques.

The work is supported by National Science Foundation (NSF) under grants ATM 0076602 and ATM 0233931.

[Previous] | [Session 2] | [Next]

Bulletin of the American Astronomical Society, 35 #3
© 2003. The American Astronomical Soceity.