Outlier Analysis in BP/RP Spectral Bands
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.
Unable to display preview. Download preview PDF.
- 2.Bailer-Jones, C.: Stellar parameters from very low resolution spectra and medium band filters. Astronomy and Astrophysics 357, 197–205 (2000)Google Scholar
- 3.Bailer-Jones, C.: A method for exploiting domain information in astrophysical parameter estimation. In: Astronomical Data Analysis Software and Systems XVII. ASP Conference Series, vol. XXX (2008)Google Scholar
- 6.Hippel, T.V., Allende, C., Sneden, C.: Automated stellar spectral classification and parameterization for the masses. In: The Garrison Festschrift conference proceedings (June 2002)Google Scholar
- 7.Kaempf, T., Willemsen, P., Bailer-Jones, C., de Boer, K.: Parameterisation of rvs spectra with artificial neural networks first steps. In: 10th RVS workshop, Cambridge (September 2005)Google Scholar
- 9.Ordonez, D., Dafonte, C., Arcay, B., Manteiga, M.: A canonical integrator environment for the development of connectionist systems. Dynamics of Continuous, Discrete and Impulsive Systems 14, 580–585 (2007)Google Scholar