Advertisement

Pattern Analysis & Applications

, Volume 5, Issue 1, pp 15–22 | Cite as

Finding Hidden Events in Astrophysical Data using PCA and Mixture of Gaussians Clustering

  • Maria Funaro
  • Maria Marinaro
  • Alfredo Petrosino
  • Silvia Scarpetta
Article

Abstract:

The Principal Component Analysis (PCA) is applied to a set of astronomic data to obtain a separation between variations of luminosity and noisy fluctuations. A clustering with the Mixture of Gaussians method, performed in the principal subspace, allows us to classify the data according to the features of interest. Our results are compared with those obtained by the AGAPE (Andromeda Galaxy and Amplified Pixels Experiment) collaboration.

Key words: Astrophysical data; Classification; Data analysis; Mixture of Gaussians; Pixel lensing; Principal Component Analysis 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag London Limited 2002

Authors and Affiliations

  • Maria Funaro
    • 1
  • Maria Marinaro
    • 1
  • Alfredo Petrosino
    • 2
  • Silvia Scarpetta
    • 1
  1. 1.Dipartimento di Fisica ‘E. R. Caianiello’, University of Salerno, Baronissi (SA), ItalyIT
  2. 2.INFM – University of Salerno, Baronissi (SA), ItalyIT

Personalised recommendations