Mathematics – Logic
Scientific paper
Dec 1992
adsabs.harvard.edu/cgi-bin/nph-data_query?bibcode=1992aas...181.6508s&link_type=abstract
American Astronomical Society, 181st AAS Meeting, #65.08; Bulletin of the American Astronomical Society, Vol. 24, p.1222
Mathematics
Logic
Scientific paper
We explore a method for automatic morphological classification of galaxies by Artificial Neural Network algorithm. The method is illustrated using 13 galaxy parameters measured by machine (ESO-LV), and classification into 5 types (E, S0, Sa+Sb, Sc+Sd, and Irr). A sample Backpropogation algorithm allowed us to train a Network on a subset of the catalogue according to the catalogue human classification, and then to predict, using the measured parameters, the classification for the rest of the catalogue. We show that the Neural Network behaves in our problem as a Bayesian classifier, i.e., it assigns the a posteriori probability for each of the 5 classes considered. The Network highest probability choice agrees with the catalogue classification for 64 % of the galaxies. If either the first or the second highest probability choice of the Network is considered, the success rate is 90 %. The technique allows production of uniform and more objective classification of very large extragalactic data sets.
Lahav Ofer
Sodre Laerte Jr.
Storrie-Lombardi Lisa
Storrie-Lombardi Michael C.
No associations
LandOfFree
Morphological classification of galaxies utilizing neural networks does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Morphological classification of galaxies utilizing neural networks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Morphological classification of galaxies utilizing neural networks will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-1111256