2004/10/23 by H. Socas‐Navarro, H. Socas-Navarro · 2 citations
Computer Science · Engineering · Physics and Astronomy · #Image and Signal Denoising Methods #Optical Polarization and Ellipsometry #Structural Health Monitoring Techniques #astro-ph
paper · pdf · doi:10.1086/426811
published as Astrophys.J. 620 (2005) 517-522 · ApJ, in press
arxiv created 2004/10/23 · openalex publication_date 2005/02/09 · arxiv updated 2009/12/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.