Feature Extraction Techniques for the Analysis of Spectral Polarization Profiles
Open Access
- 10 February 2005
- journal article
- Published by American Astronomical Society in The Astrophysical Journal
- Vol. 620 (1) , 517-522
Abstract
This paper introduces a novel feature extraction technique for the analysis of spectral line Stokes profiles. The procedure is based on the use of an auto-associative artificial neural network containing non-linear hidden layers. The neural network extracts a small subset of parameters from the profiles (features), from which it is then able to reconstruct the original profile. This new approach is compared to two other procedures that have been proposed in previous works, namely principal component analysis and Hermitian function expansions. Depending on the target application, each one of these three techniques has some advantages and disadvantages, which are discussed here.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- An orthonormal set of Stokes profilesAstronomy & Astrophysics, 2003
- Magnetic Maps of Prominences from Full Stokes Analysis of the He i D3 LineThe Astrophysical Journal, 2003
- Measuring solar magnetic fields with artificial neural networksNeural Networks, 2003
- Interpretation of observations by inversionAstronomische Nachrichten, 2003
- The Physical Content of the Leading Orders of Principal Component Analysis of Spectral ProfilesThe Astrophysical Journal, 2002
- The inversion of Stokes profiles with artificial neural networksAstronomy & Astrophysics, 2001
- Fast Inversion of Spectral Lines Using Principal Components Analysis. II. Inversion of Real Stokes DataThe Astrophysical Journal, 2001
- Neural networks and principal component analysis: Learning from examples without local minimaNeural Networks, 1989
- Auto-association by multilayer perceptrons and singular value decompositionBiological Cybernetics, 1988
- Parallel Distributed Processing1986