NASA/IPAC EXTRAGALACTIC DATABASE
Date and Time of the Query: 2019-08-18 T16:16:21 PDT
Help | Comment | NED Home

For refcode 1998ApJS..116...47B:
Retrieve 86 NED objects in this reference.
Please click here for ADS abstract

NED Abstract

Copyright by American Astronomical Society. Reproduced by permission
1998ApJS..116...47B A Comparison of Neural Network Algorithms and Preprocessing Methods for Star-Galaxy Discrimination DAVID BAZELL General Sciences Corporation, 6100 Chevy Chase Drive, Laurel, MD 20707; bazell@erols.com AND YUAN PENG Princeton Information , LTD, 10887 Hilltop Lane, Columbia, MD 21044; ypeng@astro.umd.edu Received 1997 August 11; accepted 1997 December 3 ABSTRACT We are interested in examining different artificial intelligence techniques for classifying astronomical objects. In this study we use two different neural networks that utilize supervised learning: learning vector quantization and back-propagation. The networks are trained to distinguish stars and galaxies using an example base of 17 x 17 pixel images consisting of 60 galaxies and 27 stars extracted from the first-generation Digitized Sky Survey. For each neural network we use four different preprocessing methods to create input vectors from the pixelized images. We also use as input the "raw" image data consisting of a 289 (17 x 17) point vector. Our results show that both networks are capable of distinguishing stars and galaxies, with back-propagation working somewhat better in most cases. We discuss the details of the preprocessing methods and which methods work better in which cases. Subject headings: galaxies: general-methods: data analysis-stars: general- techniques: image processing
Retrieve 86 NED objects in this reference.
Please click here for ADS abstract

Back to NED Home