Temperature- and Color-Based SDSS Stellar Spectral Classification Using Automated Scheme
Automated techniques minimize the complexity, saving time and efforts in the object classification and their analysis. Sloan Digital Sky Survey (SDSS) is one of the spectroscopic surveys releasing large data sets. Astronomers are looking for some automated techniques so that they can analyze these massive data sets which are now publicly available. We use Feed Forward Back Propagation (FFBP) Neural Network for automatic classification. Classification of stars is performed on the basis of two parameters that are temperature and color. 1500 SDSS spectra are classified into 4 spectral types, and around 2359 SDSS spectra are classified into 7 spectral types ranging from A to K and O to M type stars by using color and temperature, respectively.
KeywordsStellar spectra Spectral type Sloan digital sky survey (SDSS) Neural network
- 1.Bazarghan, Mahdi and Gupta, Ranjan: Automated classification of sloan digital sky survey (SDSS) stellar spectra using artificial neural networks. In: Astrophysics and Space Science (2008)Google Scholar
- 2.J. Sánchez Almeida, C. Allende Prieto: Automated Unsupervised Classification of the Sloan Digital Sky Survey Stellar Spectra using k-means Clustering. In: The Astrophysical Journal (2013)Google Scholar
- 3.Kheirdastan, S. and Bazarghan, M.: SDSS-DR12 bulk stellar spectral classification: Artificial neural networks approach. In: Astrophysics and Space Science (2016)Google Scholar
- 4.Aihara, Hiroaki, et al.: The eighth data release of the Sloan Digital Sky Survey: first data from SDSS-III. In: The Astrophysical Journal Supplement (2011)Google Scholar