Automated classification of sloan digital sky survey (SDSS) stellar spectra using artificial neural networks

Bazarghan, Mahdi; Gupta, Ranjan

doi:10.1007/s10509-008-9816-5

Cited by 26 publications

(17 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is quite surprising that Bazarghan & Gupta (2008) found and classified a significant number of hot O and Btype objects which are normally well beyond the colour regime selected by the SDSS. We therefore took a closer look at especially the O-type stars in their sample.…”

Section: Results Of the Classification Processmentioning

confidence: 99%

“…At this point, the learning process was aborted. Bazarghan & Gupta (2008) analysed 5000 SDSS DR6 spectra with a Probabilistic Neural Network (PNN) to classify apparent stellar objects. They divided their sample into 158 spectral types covering O to M-type stars.…”

Section: Classmentioning

confidence: 99%

“…The spectra of stars are just a spin-off product of the survey (Smolčić et al 2004). To our knowledge, only Bazarghan & Gupta (2008) analysed 5000 SDSS spectra with a Probabilistic Neural Network (PNN) to classify apparent stellar objects. Their results will be discussed in more detail later on.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An Artificial Neural Network approach to classify SDSS stellar spectra

Schierscher

Paunzen

2011

Astron Nachr

View full text Add to dashboard Cite

We present a combined method to classify stellar spectra of the seventh data release (DR7) of the SDSS via an Artificial Neural Network (ANN), derive radial velocities and to estimate distances from an isochrone fitting technique. In total, we used 29 182 spectra of stars falling in the effective temperature range between 10 000 and 5500 K, including white dwarfs. The targets were selected on the basis of SDSS colours. We compare our results not only with the SEGUE Stellar Parameter Pipeline output, but also with already published values and find excellent agreement. With new and extensive data sets from all-sky ground based as well as satellite missions, our approach will become very important and efficient to analyse these information.

show abstract

Section: Results Of the Classification Processmentioning

confidence: 99%

Section: Classmentioning

confidence: 99%

See 1 more Smart Citation

An Artificial Neural Network approach to classify SDSS stellar spectra

Schierscher

Paunzen

2011

Astron Nachr

View full text Add to dashboard Cite

show abstract

“…We can mention the already classical works by von Hippel et al (1994), Singh et al (1998), Bailer-Jones et al (1997), Vieira & Ponz (1998), as well as the more recent works by Gupta et al (2004), Willemsen et al (2005), Giridhar et al (2006), and Bazarghan & Gupta (2008). For a revision of various approaches toward the automated analysis of stellar spectra, including ANNs, see the review by Allende (2004).…”

Section: Introductionmentioning

confidence: 99%

Starmind: A Fuzzy Logic Knowledge-Based System for the Automated Classification of Stars in the Mk System

Manteiga

Carricajo

Rodrı́guez

et al. 2009

The Astronomical Journal

View full text Add to dashboard Cite

Astrophysics is evolving toward a more rational use of costly observational data by intelligently exploiting the large terrestrial and spatial astronomical databases. In this paper, we present a study showing the suitability of an expert system to perform the classification of stellar spectra in the Morgan and Keenan (MK) system. Using the formalism of artificial intelligence for the development of such a system, we propose a rules' base that contains classification criteria and confidence grades, all integrated in an inference engine that emulates human reasoning by means of a hierarchical decision rules tree that also considers the uncertainty factors associated with rules. Our main objective is to illustrate the formulation and development of such a system for an astrophysical classification problem. An extensive spectral database of MK standard spectra has been collected and used as a reference to determine the spectral indexes that are suitable for classification in the MK system. It is shown that by considering 30 spectral indexes and associating them with uncertainty factors, we can find an accurate diagnose in MK types of a particular spectrum. The system was evaluated against the NOAO-INDO-US spectral catalog.

show abstract

“…The efficiency of artificial neural networks in spectral classification is addressed in previous works bazargan@znu.ac.ir such as; Gulati et al (1994aGulati et al ( ,b, 1995, Von Hipple et al (1994), Weaver and Torres-Dodgen (1995), Bailer-Jones et al (1998), Bazarghan and Gupta (2008), and Manteiga et al (2009). Also the K-Means classification of spectra is used for different astrophysical contexts in these papers ;Balazs et al (1996); Simpson et al (2012), Galluccio et al (2008), Sanchez Almeida et al (2009, 2010, and Morales-Luisi et al (2011).…”

Section: Introductionmentioning

confidence: 99%

SDSS-DR12 bulk stellar spectral classification: Artificial neural networks approach

Kheirdastan

Bazarghan

2016

Astrophys Space Sci

View full text Add to dashboard Cite

This paper explores the application of Probabilistic Neural Network (PNN), SupportVector Machine (SVM) and k-means clustering as tools for automated classification of massive stellar spectra. The data set consists of a set of stellar spectra associated with the Sloan Digital Sky Survey (SDSS) SEGUE-1 and SEGUE-2, which consists of 400,000 data from 3850 to 8900Å with 3646 data points each. We investigate the application of principal components analysis (PCA) to reducing the dimensionality of data set to 280, 400 and 700 components.We show that PNN can give fairly accurate spectral type classifications σ RM S = 1.752, σ RM S = 1.538 and σ RM S = 1.391 and K-means can classify these spectra with an accuracy of σ RM S = 1.812, σ RM S = 1.731 and σ RM S = 1.654 and SVM with the accuracy of σ RM S = 1.795, σ RM S = 1.674 and σ RM S = 1.529 across the 280, 400 and 700 components, respectively. By using K-means the classification of the spectra renders 38 major classes. Furthermore, by comparing the results we noticed that PNN is more successful than K-means and arXiv:1609.03147v1 [astro-ph.IM] 11 Sep 2016 2 SVM in automated classification.

show abstract

Automated classification of sloan digital sky survey (SDSS) stellar spectra using artificial neural networks

Cited by 26 publications

References 20 publications

An Artificial Neural Network approach to classify SDSS stellar spectra

An Artificial Neural Network approach to classify SDSS stellar spectra

Starmind: A Fuzzy Logic Knowledge-Based System for the Automated Classification of Stars in the Mk System

SDSS-DR12 bulk stellar spectral classification: Artificial neural networks approach

Contact Info

Product

Resources

About