Advertisement

Automated Spectral Classification of QSOs and Galaxies by Radial Basis Function Network with Dynamic Decay Adjustment

  • Mei-fang Zhao
  • Jin-fu Yang
  • Yue Wu
  • Fu-chao Wu
  • Ali Luo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3972)

Abstract

This paper presents a fast neural network method of radial basis function with dynamic decay adjustment (RBFN-DDA) to classify Quasi-Stellar Objects (QSOs) and galaxies automatically. The classification process is mainly comprised of three parts: (1) the dimensions of the normalized input spectra is reduced by the Principal Component Analysis (PCA); (2) the network is built from scratch: the number of required hidden units is determined during training and the individual radii of the Gaussians are adjusted dynamically until corresponding criterions are satisfied; (3) The trained network is used for the classification of the real spectra of QSOs and galaxies. The method of RBFN-DDA having constructive and fast training process solves the difficulty of selecting appropriate number of neurons before training in many methods of neural networks and achieves lower error rates of spectral classification. Besides, due to its efficiency, the proposed method would be particularly useful for the fast and automatic processing of voluminous spectra to be produced from the large-scale sky survey project.

Keywords

Radial Basis Function Neural Network Active Galactic Nucleus Radial Basis Function Network Equivalent Width Correct Classification Rate 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Connolly, A.J., Szalay, A.S., Bershady, M.A., et al.: Spectral Classification of Galaxies: An Orthogonal Approach. Astronomical Journal 110(3), 1071–1082 (1995)CrossRefGoogle Scholar
  2. Gaspar, G., de Valerie, L.: The ESO-Sculptor Survey: Spectral Classification of Galaxies with Z < 0.5. Astronomy and Astrophysics 332(4), 459–478 (1998)Google Scholar
  3. Zaritsky, D., Zabludoff, A.I., Jeffrey, A.W.: Spectral Classification of Galaxies along the Hubble Sequence. Astronomical Journal 110(5), 1602–1613 (1995)CrossRefGoogle Scholar
  4. Zhu, G.H., et al.: Automated Measurement of Redshifts of Galaxy Spectra of LAMOST. Spectroscopy and Spectral Analysis 25(6), 1002–1005 (2005)Google Scholar
  5. Zhang, L., Zhang, B.: A Geometrical Representation of McCulloch-Pitts Neural Model and Its Applications. IEEE Transactions on Neural Networks 10(4), 925–929 (1999)CrossRefGoogle Scholar
  6. Liu, H., Chandrasekar, V., Xu, G.: An Adaptive Neural Network Scheme for Radar Rainfall Estimation from WSR-88D Observations. J. Appl. Meteor. 40(11), 2038–2050 (2001)CrossRefGoogle Scholar
  7. Moody, J., Darken, C.J.: Fast Learning in Networks of Locally-Tuned Processing Units. Neural Computation 1(2), 281–294 (1989)CrossRefGoogle Scholar
  8. Reilly, D.L., Cooper, L.N., Elbaum, C.: A Neural Model for Category Learning. Biol. Cybernet 45(1), 35–41 (1982)CrossRefGoogle Scholar
  9. Berthold, M.R., Diamond, J.: Boosting the Performance of RBF Networks with Dynamic Decay Adjustment. In: Proceedings of the Advances in Neural Information Processing Systems (NIPS), vol. 7, pp. 521–528. MIT Press, Cambridge (1995)Google Scholar
  10. Calzetti, D., Kinney, A.L., Storchi-Bergmann, T.: Dust Extinction of The Stellar Continua in Starburst Galaxies: The Ultraviolet and Optical Extinction Law. Astrophysical Journal 429(8), 582–601 (1994)CrossRefGoogle Scholar
  11. Rodriguez-Pascual, P.M.: IUE Monitoring of the Bright Seyfert 1 Galaxy Fairall 9. In: Peterson, B.M., Cheng, F.-Z., Wilson, A.S. (eds.) Emission Lines in Active Galaxies: New Methods and Techniques. ASP Conference Series, vol. 113, pp. 167–168 (1997)Google Scholar
  12. Francis, P.J., et al.: A High Signal-to-Noise Ratio Composite Quasar Spectrum. Astrophysical Journal 373(2), 465–470 (1991)CrossRefMathSciNetGoogle Scholar
  13. Qin, D.M., et al.: A Fast Classification of Stellar Spectra Based on Principal Component Analysis. Spectroscopy and Spectral Analysis 23(1), 182–186 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Mei-fang Zhao
    • 1
  • Jin-fu Yang
    • 1
  • Yue Wu
    • 2
  • Fu-chao Wu
    • 1
  • Ali Luo
    • 2
  1. 1.National Laboratory of Pattern Recognition, Institute of AutomationChinese Academy of SciencesBeijingChina
  2. 2.National Astronomical ObservatoriesChinese Academy of SciencesBeijingChina

Personalised recommendations