Feature Extraction Techniques for the Analysis of Spectral Polarization Profiles

Details Feature Extraction Techniques for the Analysis of Spectral Polarization Profiles Feature Extraction Techniques for the Analysis of Spectral Polarization Profiles

2004-10-23

arxiv.org/abs/astro-ph/0410565v1

Astrophys.J. 620 (2005) 517-522

Astronomy and Astrophysics

Astrophysics

ApJ, in press

Scientific paper

10.1086/426811

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.

Affiliated with

Also associated with

No associations

Rating

Feature Extraction Techniques for the Analysis of Spectral Polarization Profiles does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Feature Extraction Techniques for the Analysis of Spectral Polarization Profiles, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Feature Extraction Techniques for the Analysis of Spectral Polarization Profiles will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-187983