J/ApJS/152/201 Classification of 2000 bright IRAS sources (Gupta+, 2004)
Automated classification of 2000 bright IRAS sources.
Gupta R., Singh H.P., Volk K., Kwok S.
<Astrophys. J. Suppl. Ser., 152, 201-209 (2004)>
=2004ApJS..152..201G 2004ApJS..152..201G
ADC_Keywords: Infrared sources ; Spectra, infrared
Keywords: infrared: galaxies - methods: data analysis
Abstract:
An artificial neural network (ANN) scheme has been employed that uses
a supervised back-propagation algorithm to classify 2000 bright
sources from the Calgary database of Infrared Astronomical Satellite
(IRAS) spectra in the region 8-23µm. The database has been
classified into 17 predefined classes based on the spectral
morphology. We have been able to classify over 80% of the sources
correctly in the first instance. The speed and robustness of the
scheme will allow us to classify the whole of the Low Resolution
Spectrometer database, containing more than 50,000 sources, in the
near future.
File Summary:
--------------------------------------------------------------------------------
FileName Lrecl Records Explanations
--------------------------------------------------------------------------------
ReadMe 80 . This file
table3.dat 18 382 List of LRS sources misclassified by
Artificial Neural Network
classes.dat 80 30 Classes definition
--------------------------------------------------------------------------------
See also:
III/197 : IRAS Low Resolution Spectra (IRAS team, 1987)
http://www.iras.ucalgary.ca/database.html :
IRAS Low Resolution Spectra Database
Byte-by-byte Description of file: table3.dat
--------------------------------------------------------------------------------
Bytes Format Units Label Explanations
--------------------------------------------------------------------------------
1- 11 A11 --- IRAS IRAS designation
13- 14 I2 --- Class Catalog class, defined in class.dat file
16- 17 I2 --- AClass Artificial Neural Network class,
defined in class.dat file
--------------------------------------------------------------------------------
Byte-by-byte Description of file: classes.dat
--------------------------------------------------------------------------------
Bytes Format Units Label Explanations
--------------------------------------------------------------------------------
1- 2 I2 --- Class Class number
4- 80 A77 --- Def Definition of the class
--------------------------------------------------------------------------------
History:
From electronic version of the journal
(End) Greg Schwarz [AAS], Patricia Vannier [CDS] 02-Jul-2004