Automated star-galaxy discrimination for large surveys

Filippo Cortiglioni, Petri Mähönen, P. Hakala, Tapio Frantti

Research output: Contribution to journalArticleScientificpeer-review

16 Citations (Scopus)

Abstract

The size of survey data is increasing rapidly, and the automatic classification of objects is becoming more important. The classification is traditionally based, e.g., on point-spread function (PSF) fitting. Recently, several different neural network approaches have been introduced for classification. In this paper we use both self-organized map and learning vector quantization based neural networks for star-galaxy separation. Finally, we test a hybrid algorithm using fuzzy classifier and back-propagation neural networks. We show that different methods give relatively similar results. The classification accuracy is good enough for real data analysis, and selection between different methods must be done based on algorithmic complexity and availability of preclassified training sets.
Original languageEnglish
Pages (from-to)62-70
Number of pages9
JournalThe Astrophysical journal
Volume556
Issue number2
DOIs
Publication statusPublished - 2001
MoE publication typeA1 Journal article-refereed

Fingerprint

discrimination
galaxies
stars
vector quantization
back propagation
point spread functions
classifiers
learning
availability
education
method

Cite this

Cortiglioni, F., Mähönen, P., Hakala, P., & Frantti, T. (2001). Automated star-galaxy discrimination for large surveys. The Astrophysical journal, 556(2), 62-70. https://doi.org/10.1086/321558
Cortiglioni, Filippo ; Mähönen, Petri ; Hakala, P. ; Frantti, Tapio. / Automated star-galaxy discrimination for large surveys. In: The Astrophysical journal. 2001 ; Vol. 556, No. 2. pp. 62-70.
@article{6566585dfb9a4c6587b94d2ee9fc6ec4,
title = "Automated star-galaxy discrimination for large surveys",
abstract = "The size of survey data is increasing rapidly, and the automatic classification of objects is becoming more important. The classification is traditionally based, e.g., on point-spread function (PSF) fitting. Recently, several different neural network approaches have been introduced for classification. In this paper we use both self-organized map and learning vector quantization based neural networks for star-galaxy separation. Finally, we test a hybrid algorithm using fuzzy classifier and back-propagation neural networks. We show that different methods give relatively similar results. The classification accuracy is good enough for real data analysis, and selection between different methods must be done based on algorithmic complexity and availability of preclassified training sets.",
author = "Filippo Cortiglioni and Petri M{\"a}h{\"o}nen and P. Hakala and Tapio Frantti",
year = "2001",
doi = "10.1086/321558",
language = "English",
volume = "556",
pages = "62--70",
journal = "The Astrophysical journal",
issn = "0004-637X",
publisher = "Institute of Physics IOP",
number = "2",

}

Cortiglioni, F, Mähönen, P, Hakala, P & Frantti, T 2001, 'Automated star-galaxy discrimination for large surveys', The Astrophysical journal, vol. 556, no. 2, pp. 62-70. https://doi.org/10.1086/321558

Automated star-galaxy discrimination for large surveys. / Cortiglioni, Filippo; Mähönen, Petri; Hakala, P.; Frantti, Tapio.

In: The Astrophysical journal, Vol. 556, No. 2, 2001, p. 62-70.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Automated star-galaxy discrimination for large surveys

AU - Cortiglioni, Filippo

AU - Mähönen, Petri

AU - Hakala, P.

AU - Frantti, Tapio

PY - 2001

Y1 - 2001

N2 - The size of survey data is increasing rapidly, and the automatic classification of objects is becoming more important. The classification is traditionally based, e.g., on point-spread function (PSF) fitting. Recently, several different neural network approaches have been introduced for classification. In this paper we use both self-organized map and learning vector quantization based neural networks for star-galaxy separation. Finally, we test a hybrid algorithm using fuzzy classifier and back-propagation neural networks. We show that different methods give relatively similar results. The classification accuracy is good enough for real data analysis, and selection between different methods must be done based on algorithmic complexity and availability of preclassified training sets.

AB - The size of survey data is increasing rapidly, and the automatic classification of objects is becoming more important. The classification is traditionally based, e.g., on point-spread function (PSF) fitting. Recently, several different neural network approaches have been introduced for classification. In this paper we use both self-organized map and learning vector quantization based neural networks for star-galaxy separation. Finally, we test a hybrid algorithm using fuzzy classifier and back-propagation neural networks. We show that different methods give relatively similar results. The classification accuracy is good enough for real data analysis, and selection between different methods must be done based on algorithmic complexity and availability of preclassified training sets.

U2 - 10.1086/321558

DO - 10.1086/321558

M3 - Article

VL - 556

SP - 62

EP - 70

JO - The Astrophysical journal

JF - The Astrophysical journal

SN - 0004-637X

IS - 2

ER -