Fuzzy classifier for star-galaxy separation

Petri Mähönen (Corresponding Author), Tapio Frantti

Research output: Contribution to journalArticleScientificpeer-review

19 Citations (Scopus)

Abstract

The sizes of astronomical surveys are increasing rapidly. Hence, the automatic classification of objects is growing more important. This classification is traditionally based, e.g., on point-spread function fitting. Recently several different neural network approaches have been introduced. In this paper we introduce a simple method that is based on fuzzy set reasoning. The analysis presented here concentrates on separating point sources (stars) from extended ones. The tests show that the neural network approach is superior if compared to direct fuzzy classification. The paper shows that the inherent ability of neural networks to process complex nonlinear data justifies the use of them in astronomical classification. However, a combined fuzzy and neural network approach can be useful at least in special cases.

Original languageEnglish
Pages (from-to)261 - 264
Number of pages4
JournalThe Astrophysical journal
Volume541
Issue number1
DOIs
Publication statusPublished - 2000
MoE publication typeA1 Journal article-refereed

Fingerprint

classifiers
galaxies
stars
fuzzy sets
point spread functions
point sources
point source

Cite this

Mähönen, Petri ; Frantti, Tapio. / Fuzzy classifier for star-galaxy separation. In: The Astrophysical journal. 2000 ; Vol. 541, No. 1. pp. 261 - 264.
@article{595c001d4ae84b04b7bcdd3f594e2bfd,
title = "Fuzzy classifier for star-galaxy separation",
abstract = "The sizes of astronomical surveys are increasing rapidly. Hence, the automatic classification of objects is growing more important. This classification is traditionally based, e.g., on point-spread function fitting. Recently several different neural network approaches have been introduced. In this paper we introduce a simple method that is based on fuzzy set reasoning. The analysis presented here concentrates on separating point sources (stars) from extended ones. The tests show that the neural network approach is superior if compared to direct fuzzy classification. The paper shows that the inherent ability of neural networks to process complex nonlinear data justifies the use of them in astronomical classification. However, a combined fuzzy and neural network approach can be useful at least in special cases.",
author = "Petri M{\"a}h{\"o}nen and Tapio Frantti",
year = "2000",
doi = "10.1086/309424",
language = "English",
volume = "541",
pages = "261 -- 264",
journal = "The Astrophysical journal",
issn = "0004-637X",
publisher = "Institute of Physics IOP",
number = "1",

}

Mähönen, P & Frantti, T 2000, 'Fuzzy classifier for star-galaxy separation', The Astrophysical journal, vol. 541, no. 1, pp. 261 - 264. https://doi.org/10.1086/309424

Fuzzy classifier for star-galaxy separation. / Mähönen, Petri (Corresponding Author); Frantti, Tapio.

In: The Astrophysical journal, Vol. 541, No. 1, 2000, p. 261 - 264.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Fuzzy classifier for star-galaxy separation

AU - Mähönen, Petri

AU - Frantti, Tapio

PY - 2000

Y1 - 2000

N2 - The sizes of astronomical surveys are increasing rapidly. Hence, the automatic classification of objects is growing more important. This classification is traditionally based, e.g., on point-spread function fitting. Recently several different neural network approaches have been introduced. In this paper we introduce a simple method that is based on fuzzy set reasoning. The analysis presented here concentrates on separating point sources (stars) from extended ones. The tests show that the neural network approach is superior if compared to direct fuzzy classification. The paper shows that the inherent ability of neural networks to process complex nonlinear data justifies the use of them in astronomical classification. However, a combined fuzzy and neural network approach can be useful at least in special cases.

AB - The sizes of astronomical surveys are increasing rapidly. Hence, the automatic classification of objects is growing more important. This classification is traditionally based, e.g., on point-spread function fitting. Recently several different neural network approaches have been introduced. In this paper we introduce a simple method that is based on fuzzy set reasoning. The analysis presented here concentrates on separating point sources (stars) from extended ones. The tests show that the neural network approach is superior if compared to direct fuzzy classification. The paper shows that the inherent ability of neural networks to process complex nonlinear data justifies the use of them in astronomical classification. However, a combined fuzzy and neural network approach can be useful at least in special cases.

U2 - 10.1086/309424

DO - 10.1086/309424

M3 - Article

VL - 541

SP - 261

EP - 264

JO - The Astrophysical journal

JF - The Astrophysical journal

SN - 0004-637X

IS - 1

ER -