Sign on

SAO/NASA ADS Astronomy Abstract Service

· Find Similar Abstracts (with default settings below)
· Electronic Refereed Journal Article (HTML)
· Full Refereed Journal Article (PDF/Postscript)
· Full Refereed Scanned Article (GIF)
· arXiv e-print (arXiv:astro-ph/9803050)
· References in the article
· Citations to the Article (43) (Citation History)
· Refereed Citations to the Article
· Also-Read Articles (Reads History)
·
· Translate This Page
Title:
Automated classification of stellar spectra - II. Two-dimensional classification with neural networks and principal components analysis
Authors:
Bailer-Jones, Coryn A. L.; Irwin, Mike; von Hippel, Ted
Affiliation:
AA(Institute of Astronomy, Madingley Road, Cambridge CB3 0HA), AB(Royal Greenwich Observatory, Madingley Road, Cambridge CB3 0EZ), AC(Department of Astronomy, University of Wisconsin, Madison, WI 53706, USA)
Publication:
Monthly Notices of the Royal Astronomical Society, Volume 298, Issue 2, pp. 361-377. (MNRAS Homepage)
Publication Date:
08/1998
Origin:
MNRAS
MNRAS Keywords:
METHODS: ANALYTICAL, METHODS: DATA ANALYSIS, METHODS: NUMERICAL, STARS: FUNDAMENTAL PARAMETERS
DOI:
10.1046/j.1365-8711.1998.01596.x
Bibliographic Code:
1998MNRAS.298..361B

Abstract

We investigate the application of neural networks to the automation of MK spectral classification. The data set for this project consists of a set of over 5000 optical (3800-5200Angstroms) spectra obtained from objective prism plates from the Michigan Spectral Survey. These spectra, along with their two-dimensional MK classifications listed in the Michigan Henry Draper Catalogue, were used to develop supervised neural network classifiers. We show that neural networks can give accurate spectral type classifications (sigma_68 = 0.82 subtypes, sigma_rms= 1.09 subtypes) across the full range of spectral types present in the data set (B2-M7). We show also that the networks yield correct luminosity classes for over 95 per cent of both dwarfs and giants with a high degree of confidence. Stellar spectra generally contain a large amount of redundant information. We investigate the application of principal components analysis (PCA) to the optimal compression of spectra. We show that PCA can compress the spectra by a factor of over 30 while retaining essentially all of the useful information in the data set. Furthermore, it is shown that this compression optimally removes noise and can be used to identify unusual spectra. This paper is a continuation of the work carried out by von Hippel et al. (Paper I).

Printing Options

Print whole paper
Print Page(s) through

Return 600 dpi PDF to Acrobat/Browser. Different resolutions (200 or 600 dpi), formats (Postscript, PDF, etc), page sizes (US Letter, European A4, etc), and compression (gzip,compress,none) can be set through the Printing Preferences


More Article Retrieval Options

HELP for Article Retrieval
Bibtex entry for this abstract   Preferred format for this abstract (see Preferences)
   

Find Similar Abstracts:

Use: Authors
Title
Keywords (in text query field)
Abstract Text
Return: Query Results Return    items starting with number
Query Form
Database: Astronomy
Physics
arXiv e-prints