Neural networks and the classification of active Galactic nucleus spectra

Daya M. Rawson; Jeremy Bailey; Paul J. Francis

Neural networks and the classification of active Galactic nucleus spectra

Daya M. Rawson^*, Jeremy Bailey, Paul J. Francis

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

3 Citations (Scopus)

Abstract

The use of artificial neural networks (ANNs) as a classifier of digital spectra is investigated. Using both simulated and real data, it is shown that neural networks can be trained to discriminate between the spectra of different classes of active galactic nucleus (AGN) with realistic sample sizes and signal-to-noise ratios. By working in the Fourier domain, neural nets can classify objects without knowledge of their redshifts.

Original language	English
Pages (from-to)	207-211
Number of pages	5
Journal	Publications of the Astronomical Society of Australia
Volume	13
Issue number	3
Publication status	Published - Oct 1996

Keywords

Data analysis
Galaxies
General - Galaxies
Nuclei - Galaxies
Quasars
Seyferts - Methods

Cite this

@article{540608674b7b40edae24251b194b0de4,

title = "Neural networks and the classification of active Galactic nucleus spectra",

abstract = "The use of artificial neural networks (ANNs) as a classifier of digital spectra is investigated. Using both simulated and real data, it is shown that neural networks can be trained to discriminate between the spectra of different classes of active galactic nucleus (AGN) with realistic sample sizes and signal-to-noise ratios. By working in the Fourier domain, neural nets can classify objects without knowledge of their redshifts.",

keywords = "Data analysis, Galaxies, General - Galaxies, Nuclei - Galaxies, Quasars, Seyferts - Methods",

author = "Rawson, {Daya M.} and Jeremy Bailey and Francis, {Paul J.}",

year = "1996",

month = oct,

language = "English",

volume = "13",

pages = "207--211",

journal = "Publications of the Astronomical Society of Australia",

issn = "1448-6083",

publisher = "CSIRO Publishing",

number = "3",

}

TY - JOUR

T1 - Neural networks and the classification of active Galactic nucleus spectra

AU - Rawson, Daya M.

AU - Bailey, Jeremy

AU - Francis, Paul J.

PY - 1996/10

Y1 - 1996/10

N2 - The use of artificial neural networks (ANNs) as a classifier of digital spectra is investigated. Using both simulated and real data, it is shown that neural networks can be trained to discriminate between the spectra of different classes of active galactic nucleus (AGN) with realistic sample sizes and signal-to-noise ratios. By working in the Fourier domain, neural nets can classify objects without knowledge of their redshifts.

AB - The use of artificial neural networks (ANNs) as a classifier of digital spectra is investigated. Using both simulated and real data, it is shown that neural networks can be trained to discriminate between the spectra of different classes of active galactic nucleus (AGN) with realistic sample sizes and signal-to-noise ratios. By working in the Fourier domain, neural nets can classify objects without knowledge of their redshifts.

KW - Data analysis

KW - Galaxies

KW - General - Galaxies

KW - Nuclei - Galaxies

KW - Quasars

KW - Seyferts - Methods

UR - http://www.scopus.com/inward/record.url?scp=0030268247&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0030268247

VL - 13

SP - 207

EP - 211

JO - Publications of the Astronomical Society of Australia

JF - Publications of the Astronomical Society of Australia

SN - 1448-6083

IS - 3

ER -

Neural networks and the classification of active Galactic nucleus spectra

Abstract

Keywords

Other files and links

Fingerprint

Cite this