A COMBINATION OF CONNECTIONIST SYSTEMS AND EVOLUTIONARY COMPUTATION TECHNIQUES TO ACHIEVE THE OPTIMAL DOMAIN FOR STELLAR SPECTRA SIGNAL PROCESSING

Diego Ordóñez, Carlos Dafonte, Bernardino Arcay, Minia Manteiga

Abstract

This paper presents part of the work carried out by Coordination Unit 8 of the GAIA project. GAIA is ESA’s spacecraft which is planned to be operative at the start of 2012 and will carry out an a stereoscopic census of the Galaxy. During the present development cycle, synthetic spectra are used to determine the stellar atmospheric parameters, particularly effective temperatures, superficial gravities, metallicities, possible abundances of alpha elements, and individual abundancies of certain chemical elements. We present the results of the application of genetic algorithms to the selection of relevant information from a set of spectra. This information will subsequently feed an artificial neural network that is in charge of extracting the parameters.

References

  1. Bailer-Jones, C. (2000). Stellar parameters from very low resolution spectra and medium band filters. Astronomy and Astrophysics, 357:197-205.
  2. Bailer-Jones, C. (2008). A method for exploiting domain information in astrophysical parameter estimation. Astronomical Data Analysis Software and Systems XVII. ASP Conference Series, XXX.
  3. Fiorentin, P., Bailer-Jones, C., Lee, Y., Beers, T., Sivarani, T., Wilhelm, R., Allende, C., and Norris, J. (2007). Estimation of stellar atmospheric parameters from sdss/segue spectra. Astronomy and Astrophysics, 467:1373-1387.
  4. Gulati, R. K., Ramirez, F., and Fuentes, O. (2001). Prediction of stellar atmospheric parameters using instancebased machine learning and genetic algorithms. Experimental Astronomy, 12(3):163-178.
  5. Harinder, Gulati, and Gupta (1998). Stellar spectral classification using principal component analysis and artificial neural networks. MNRAS, 295:312-318.
  6. Hippel, T. V., Allende, C., and Sneden, C. (2002). Automated stellar spectral classification and parameterization for the masses. In The Garrison Festschrift conference proceedings.
  7. Hu, Y.-C. (2008). Nonadditive grey single-layer perceptron with choquet integral for pattern classification problems using genetic algorithms. Neurocomputing, 72:331-340.
  8. Kaempf, T., Willemsen, P., Bailer-Jones, C., and de Boer, K. (2005). Parameterisation of rvs spectra with artificial neural networks first steps. 10th RVS workshop. Cambridge.
  9. Kinnebrock, W. (1994). Accelerating the standard backpropagation method using a genetic approach. Neurocomputing, 91(3):731-735.
  10. Mallat, S. (1989). A theory for multiresolution signal decomposition: The wavelet representation. Proc. IEEE Trans on Pattern Anal. and Math. intel., 11(7):674- 693.
  11. Morgan W.W., Keenan P.C., K. E. (1943). An atlas of stellar sepctra with outline of spectral classification. Astrophys. monographs, University of Chicago Press.
  12. Ordonez, D., Dafonte, C., Arcay, B., and Manteiga, M. (2007). A canonical integrator environment for the development of connectionist systems. Dynamics of continuous, Discrete and Impulsive Systems, 14:580- 585.
  13. Ordonez, D., Dafonte, C., Arcay, B., and Manteiga, M. (2008). Parameter extraction from rvs stellar spectra by means of artificial neural networks and spectral density analysis. Lecture Notes in Artificial Intelligence, 5271:212 - 219.
  14. Recio-Blanco, A., de Laverny, P., and Plez, B. (2005). Rvsarb-001. European Space Agency technique note.
  15. Rooij, A., Jain, L., and Johnson, R. (1996). Neural Network Training Using Genetic Algorithms. World Scientific Pub Co Inc, Singapore.
Download


Paper Citation


in Harvard Style

Ordóñez D., Dafonte C., Arcay B. and Manteiga M. (2009). A COMBINATION OF CONNECTIONIST SYSTEMS AND EVOLUTIONARY COMPUTATION TECHNIQUES TO ACHIEVE THE OPTIMAL DOMAIN FOR STELLAR SPECTRA SIGNAL PROCESSING . In Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICNC, (IJCCI 2009) ISBN 978-989-674-014-6, pages 323-330. DOI: 10.5220/0002264403230330


in Bibtex Style

@conference{icnc09,
author={Diego Ordóñez and Carlos Dafonte and Bernardino Arcay and Minia Manteiga},
title={A COMBINATION OF CONNECTIONIST SYSTEMS AND EVOLUTIONARY COMPUTATION TECHNIQUES TO ACHIEVE THE OPTIMAL DOMAIN FOR STELLAR SPECTRA SIGNAL PROCESSING},
booktitle={Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICNC, (IJCCI 2009)},
year={2009},
pages={323-330},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002264403230330},
isbn={978-989-674-014-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICNC, (IJCCI 2009)
TI - A COMBINATION OF CONNECTIONIST SYSTEMS AND EVOLUTIONARY COMPUTATION TECHNIQUES TO ACHIEVE THE OPTIMAL DOMAIN FOR STELLAR SPECTRA SIGNAL PROCESSING
SN - 978-989-674-014-6
AU - Ordóñez D.
AU - Dafonte C.
AU - Arcay B.
AU - Manteiga M.
PY - 2009
SP - 323
EP - 330
DO - 10.5220/0002264403230330