Hybrid approach to MK classification of stars neural networks and knowledge-based systems

  • Authors:

  • Alejandra Rodriguez;Iciar Carricajo;Carlos Dafonte;Bernardino Arcay;Minia Manteiga

  • Affiliations:

  • Univ. of A Coruña, Dep. of Infor. and Comm. Tech, A Coruña, Spain;Univ. of A Coruña, Dep. of Nav. and Earth Sciences, A Coruña, Spain;Univ. of A Coruña, Dep. of Infor. and Comm. Tech, A Coruña, Spain;Univ. of A Coruña, Dep. of Infor. and Comm. Tech, A Coruña, Spain;Univ. of A Coruña, Dep. of Nav. and Earth Sciences, A Coruña, Spain

  • Venue:
  • AIKED'07 Proceedings of the 6th Conference on 6th WSEAS Int. Conf. on Artificial Intelligence, Knowledge Engineering and Data Bases - Volume 6
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents a comparative study of the sensibility of knowledge-based systems and artificial neural networks applied to optical spectroscopy, a specific field of Astrophysics. We propose a description of various neural networks models and the comparison of the results obtained by each technique individually and by a combination of both. Whereas in previous works we developed a knowledge-based system for the automatic analysis of spectra, we shall now use the analysis methods developed in that system to extract the most important spectral features, by training the proposed neural networks with this numeric characterization. We do not only intend to analyse the efficiency of artificial neural networks in classification of stellar spectra; our approach is also focused on the integration of several artificial techniques in a unique hybrid system. The proposed system is capable of applying the most appropriate classification method to each spectrum, which widely opens the research in the field of automatic spectral classification.