Conference paper

VRÁBELOVÁ Pavla, BAŘINA David, ŠKODA Petr, ZENDULKA Jaroslav and VÁŽNÝ Jaroslav. Classification of Be Stars Using Feature Extraction Based on Discrete Wavelet Transform. In: Proceedings of conferences Datakon and Znalosti 2013. Ostrava: VŠB-Technical University of Ostrava, 2013, pp. 95-102. ISBN 978-80-248-3189-3.
Publication language:english
Original title:Classification of Be Stars Using Feature Extraction Based on Discrete Wavelet Transform
Title (cs):Klasifikace Be hvězd použitím extrakce příznaků založené na diskrétní vlnkové transformaci
Pages:95-102
Proceedings:Proceedings of conferences Datakon and Znalosti 2013
Conference:ZNALOSTI 2013
Place:Ostrava, CZ
Year:2013
ISBN:978-80-248-3189-3
Publisher:VŠB-Technical University of Ostrava
Files: 
+Type Name Title Size Last modified
iconllncs.pdf461 KB2013-10-24 19:33:54
^ Select all
With selected:
Keywords
Be star, stellar spectrum, feature extraction, discrete wavelet
transform, DWT, classification, support vector machines, SVM
Annotation
The paper deals with classification of Be star spectra using discrete wavelet transform (DWT) and support vector machines (SVM).
Abstract
There is no known method specialized for feature extraction and classification of Be stars. In this paper, we propose several feature extraction methods based on the discrete wavelet transform (DWT). The data set is composed of spectra from the archive of the Astronomical Institute of the Academy of Sciences of the Czech Republic. The data set contains both Be and normal stars. A small segment containing the H line characteristic for Be stars is selected for feature extraction. Five different feature extraction methods based on DWT are proposed and compared with a common method of wavelet-based feature extraction from time series. For classification, the support vector machines (SVM) is used. The results are given by the accuracy of classification.
BibTeX:
@INPROCEEDINGS{
   author = {Pavla Vr{\'{a}}belov{\'{a}} and David Ba{\v{r}}ina and Petr
	{\v{S}}koda and Jaroslav Zendulka and Jaroslav
	V{\'{a}}{\v{z}}n{\'{y}}},
   title = {Classification of Be Stars Using Feature Extraction Based on
	Discrete Wavelet Transform},
   pages = {95--102},
   booktitle = {Proceedings of conferences Datakon and Znalosti 2013},
   year = {2013},
   location = {Ostrava, CZ},
   publisher = {V{\v{S}}B-Technical University of Ostrava},
   ISBN = {978-80-248-3189-3},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php.en.iso-8859-2?id=10416}
}

Your IPv4 address: 54.92.194.75
Switch to IPv6 connection

DNSSEC [dnssec]