Outlier Analysis in BP/RP Spectral Bands

  • Authors:

  • Diego Ordóñez;Carlos Dafonte;Minia Manteiga;Bernardino Arcay

  • Affiliations:

  • Department of Information and Communications Technologies, University of A Coruña, A Coruña, Spain 15071;Department of Information and Communications Technologies, University of A Coruña, A Coruña, Spain 15071;Department of Navigation and Earth Sciences, University of A Coruña, A Coruña, Spain 15071;Department of Information and Communications Technologies, University of A Coruña, A Coruña, Spain 15071

  • Venue:
  • ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part II
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Most astronomic databases include a certain amount of exceptional values that are generally called outliers. Isolating and analysing these "outlying objects" is important to improve the quality of the original dataset, to reduce the impact of anomalous observations, and most importantly, to discover new types of objects that were hitherto unknown because of their low frequency or short lifespan. We propose an unsupervised technique, based on artificial neural networks and combined with a specific study of the trained network, to treat the problem of outliers management. This work is an integrating part of the GAIA mission of the European Space Agency.