STAR GALAXY CLASSIFICATION USING KOHONEN SELF-ORGANIZING MAPS

Authors
MILLER AS COE MJ
Citation
As. Miller et Mj. Coe, STAR GALAXY CLASSIFICATION USING KOHONEN SELF-ORGANIZING MAPS, Monthly Notices of the Royal Astronomical Society, 279(1), 1996, pp. 293-300
Citations number
27
Categorie Soggetti
Astronomy & Astrophysics
Journal title
Monthly Notices of the Royal Astronomical Society → ACNP
ISSN journal
00358711
Volume
279
Issue
1
Year of publication
1996
Pages
293 - 300
Database
ISI
SICI code
0035-8711(1996)279:1<293:SGCUKS>2.0.ZU;2-Z
Abstract
The automatic classification of star/galaxy data sets is of growing im portance as the size of survey data sets increases. Here we present a classifier based on the Kohonen self-organizing map (SOM). The SOM was trained to classify by type using only a small number of manually cla ssified objects. Galaxy classification accuracies of 98 per cent are a chieved for objects with a limiting magnitude of 20.