Äîêóìåíò âçÿò èç êýøà ïîèñêîâîé ìàøèíû. Àäðåñ îðèãèíàëüíîãî äîêóìåíòà : http://www.stecf.org/conferences/adass/adassVII/reprints/vieirae.ps.gz
Äàòà èçìåíåíèÿ: Mon Jun 12 18:51:50 2006
Äàòà èíäåêñèðîâàíèÿ: Tue Oct 2 03:31:13 2012
Êîäèðîâêà: IBM-866

Ïîèñêîâûå ñëîâà: arp 220
Astronomical Data Analysis Software and Systems VII
ASP Conference Series, Vol. 145, 1998
R. Albrecht, R. N. Hook and H. A. Bushouse, e
ó Copyright 1998 Astronomical Society of the Pacific. All rights reserved.
ds.
Automated Spectral Classification Using Neural Networks
E. F. Vieira
Laboratorio de AstrofÒÐsica Espacial y FÒÐsica Fundamental
P.O.Box 50727, 28080 Madrid, Spain, Email: efv@lae#.esa.es
J. D. Ponz
GSED/ESA, Villafranca
P.O.Box 50727, 28080 Madrid, Spain, Email: jdp@vilspa.esa.es
Abstract. We have explored two automated classification methods:
supervised classification using Artificial Neural Networks (ANN) and uní
supervised classification using Self Organized Maps (SOM). These methí
ods are used to classify IUE lowídispersion spectra of normal stars with
spectral types ranging from O3 to G5.
1. Introduction
This paper describes the application of automated methods to the problem of the
classification of stellar spectra. The availability of the IUE lowídispersion archive
(Wamsteker et al. 1989) allows the application of pattern recognition methods
to explore the ultraviolet domain. The analysis of this archive is especially
interesting, due to the homogeneity of the sample.
The present work has been done within the context of the IUE Final Archive
project, to provide an e#cient and objective classification procedure to analyze
the complete IUE database, based on methods that do not require prior knowlí
edge about the object to be classified. Two methods are compared: a supervised
ANN classifier and an unsupervised Self Organized Map (SOM) classifier.
2. The Data Set
The spectra were taken from the IUE LowíDispersion Reference Atlas of Normal
Stars (Heck et al. 1983), covering the wavelength range from 1150 to 3200 Ú A.
The Atlas contains 229 normal stars distributed from the spectral type O3 to
K0, that were classified manually, following a classical morphological approach
(Jaschek & Jaschek 1984), based on UV criteria alone.
The actual input set was obtained by merging together data from the two
IUE cameras, sampled at a uniform wavelength step of 2 Ú A, after processing
with the standard calibration pipeline. Although the spectra are good in qualí
ity, there are two aspects that seriously hinder the automated classification:
interstellar extinction and contamination with geoícoronal Lyí# emission. Some
preíprocessing was required to eliminate these e#ects and to normalize the data.
508

Automated Spectral Classification Using Neural Networks 509
All spectra were corrected for interstellar extinction by using Seaton's (1979)
extinction law. Figure 1 shows original and corrected spectra, corresponding to
a O4 star; the wavelength range used in the classification is indicated by the
solid line.
1200 1600 2000 2400 2800 3200
Wavelength
Original
Selected range
After deíreddening
Normalized
Flux
Figure 1. Original and deíreddened spectra.
3. Supervised Classification Using ANN
A supervised classification scheme based on artificial neural networks (ANN)
has been used. This technique was originally developed by McCullogh and Pitts
(1943) and has been generalized with an algorithm for training networks having
multiple layers, known as backípropagation (Rumelhart et al. 1986).
The complete sample in the Atlas was divided into two sets: 64 standard
stars, with spectral types from O3 to G5, was used as the training set. The
remaining spectra were used as a test to exercise the classification algorithm.
The network contains 744 ½ 120 ½ 120 ½ 51 neurons. The resulting classification
error on the test set was 1.1 spectral subclasses. Figure 2 shows the classification
diagrams, comparing automatic classification (ANN) with manual (Atlas) and
with a simple metric distance algorithm.
4. Unsupervised Classification Using SOM
In the Self Organized Map (SOM) the net organizes the spectra into clusters
based on similarities using a metric to define the distance between two specí
tra. The algorithm used to perform such clustering was developed by Kohonen
(1984).

510 Vieira and Ponz
O B A F G
Metric Distance
O
B
A
F
G
ANN
O B A F G
Atlas
O
B
A
F
G
ANN
O B A F G
Atlas
O
B
A
F
G
Metric
Distance a
b
c
Figure 2. Results of supervised classification.
A 8 ½ 8 map with 744 neurons in the input layer was exercised on the same
input sample. The training set was used to define the spectral types associated
to the elements in the map. This classifier gives an error of 1.62 subclasses
when compared with the Atlas, with a correlation of 0.9844. In addition, 27
stars could not be classified according to the classification criterion used in this
experiment. Figure 3 shows the classification diagrams, comparing the SOM
classifier with ANN and manual classification.
5. Conclusions
Two automated classification algorithms were applied to a well defined sample
of spectra with very good results. The error found for supervised algorithm is
1.10 subclasses and 1.62 subclasses for the unsupervised method.
These methods can be directly applied to the set of spectra, without previí
ous analysis of spectral features.

Automated Spectral Classification Using Neural Networks 511
O B A F G K
ANN
O
B
A
F
G
K
SOM
O B A F G K
Atlas
O
B
A
F
G
K
SOM
Figure 3. Results of unsupervised classification.
References
Heck, A., Egret, D., Jaschek, M., & Jaschek, C. 1983, (Feb), IUE Low Dispersion
Spectra Reference Atlas, SP 1052, ESA, Part1. Normal Stars
Jaschek, M., & Jaschek, C. 1984, in The MK process and Stellar Classification,
David Dunlap Observatory, 290
Kohonen, T. 1984, Selfíorganization and Associative Memory Volume 8 of
Springer Series in Information Sciences (Springer Verlag, Nueva York)
McCullogh, W.S., & Pitts, W.H. 1943, Bull. Math. Biophysics, 5, 115
Rumelhart, D.E., Hinton, G.E., & Williams, R.J. 1986, Nature, 323, 533
Seaton, M.J. 1979, MNRAS, 187, 73P
Vieira, E.F., Ponz, J.D. 1995, A&AS, 111, 393
Wamsteker, W., Driessen, C., & MuÔnoz, J.R. et al. 1989, A&AS, 79, 1