Publication Details

Wavelet Based Feature Extraction for Clustering of Be Stars

VRÁBELOVÁ Pavla, ŠKODA Petr and ZENDULKA Jaroslav. Wavelet Based Feature Extraction for Clustering of Be Stars. In: Nostradamus 2013: Prediction, Modeling and Analysis of Complex Systems. Volume 210 of Advances in Intelligent Systems and Computing. New York: Springer US, 2013, pp. 467-474. ISBN 978-3-319-00541-6. Available from: http://link.springer.com/chapter/10.1007%2F978-3-319-00542-3_46
Czech title
Extrakce příznaků pro klasifikaci Be hvězd založená na vlnkové transformaci
Type
conference paper
Language
english
Authors
Vrábelová Pavla, Ing. (DIFS FIT BUT)
Škoda Petr (ASU)
Zendulka Jaroslav, doc. Ing., CSc. (DIFS FIT BUT)
URL
Keywords

Be star, feature extraction, wavelet transform, wavelet power spectrum

Abstract

The goal of our work is to create a feature extraction method for classification of Be stars. Be stars are characterized by prominent emission lines in their spectrum. We focus on the automated classification of Be stars based on typical shapes of their emission lines. We aim to design a reduced, specific set of features characterizing and discriminating the shapes of Be lines. In this paper, we present a feature extraction method based on the wavelet transform and its power spectrum. Both the discrete and continuous wavelet transform are used. Different feature vectors are created and compared on clustering of Be stars spectra from the archive of the Astronomical Institute of the Academy of Sciences of the Czech Republic. The clustering is performed using the k- means algorithm. The results of our method are promising and encouraging to more detailed analysis.

Published
2013
Pages
467-474
Proceedings
Nostradamus 2013: Prediction, Modeling and Analysis of Complex Systems
Series
Volume 210 of Advances in Intelligent Systems and Computing
Conference
NOSTRADAMUS 2013, VSB Technical University of Ostrava, CZ
ISBN
978-3-319-00541-6
Publisher
Springer US
Place
New York, US
DOI
10.1007/978-3-319-00542-3_46
BibTeX 
@INPROCEEDINGS{FITPUB10307,
   author = "Pavla Vr\'{a}belov\'{a} and Petr \v{S}koda and Jaroslav Zendulka",
   title = "Wavelet Based Feature Extraction for Clustering of Be Stars",
   pages = "467--474",
   booktitle = "Nostradamus 2013: Prediction, Modeling and Analysis of Complex Systems",
   series = "Volume 210 of Advances in Intelligent Systems and Computing",
   year = 2013,
   location = "New York, US",
   publisher = "Springer US",
   ISBN = "978-3-319-00541-6",
   doi = "10.1007/978-3-319-00542-3\_46",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/10307"
}
Back to top