NEURAL NETWORKS FOR GAMMA-HADRON SEPARATION IN MAGIC

  • P. BOINEE
  • F. BARBARINO
  • A. DE ANGELIS
  • A. SAGGION
  • M. ZACCHELLO
Conference paper

Abstract

Neural networks have proved to be versatile and robust for particle separation in many experiments related to particle astrophysics. We apply these techniques to separate gamma rays from hadrons for the MAGIC Čerenkov Telescope. Two types of neural network architectures have been used for the classification task: one is the MultiLayer Perceptron (MLP) based on supervised learning, and the other is the Self-Organising Tree Algorithm (SOTA), which is based on unsupervised learning. We propose a new architecture by combining these two neural networks types to yield better and faster classification results for our classification problem.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    A.M. Hillas, Proc. 19th ICRC, La Jolla 3 (1985) 445Google Scholar
  2. [2]
    D. Heck, et al., CORSIKA, A Monte Carlo code to simulate extensive air showers, Forschungszentrum Karlsruhe, Report FZKA 6019 (1998)Google Scholar
  3. [3]
    S. Lawrence et al., Neural Network Classification and Prior Class Probabilities, Lecture Notes in Computer Science State-of-the-Art Surveys, edited by G. Orr et al., Springer Verlag, pp. 299–314 (1998)Google Scholar
  4. [4]
    C. Delaere, Multilayer Perceptron Root Class, http://root.cern.chGoogle Scholar
  5. [5]
    R.K. Bock et al., Methods for multidimensional event classification: a case study using images from a Cherenkov gamma-ray telescope, Nuclear Instruments and Methods in Physics Research, A 516 (2003)Google Scholar
  6. [6]
    Rajaniemi et al., Classifying Gamma-ray bursts using self-organizing maps Google Scholar
  7. [7]
    T. Kohonen Self-Organizing Maps, 2nd Ed., Springer (1997)Google Scholar
  8. [8]
    J. Dopazo, J.M. Carazo Phylogenetic reconstruction using an unsupervised growing neural network that adopts the topology of a phylogenetic tree, J. Mol. Evol. (1997) 44: 226–233CrossRefGoogle Scholar
  9. [9]
    B. Fritzke, A growing neural gas network learns topologies, in Advances in Neural Information Processing Systems 7, G. Tesauro, D.S. Touretzky and T. K. Leen, editors, MIT Press (1995)Google Scholar

Copyright information

© Springer 2006

Authors and Affiliations

  • P. BOINEE
    • 1
    • 2
  • F. BARBARINO
    • 1
    • 2
  • A. DE ANGELIS
    • 1
    • 2
  • A. SAGGION
    • 3
  • M. ZACCHELLO
    • 3
  1. 1.Dipartimento di FisicaUniversità di UdineUdineItaly
  2. 2.INFN, Sezione di Trieste, Gruppo di UdineUdineItaly
  3. 3.Dipartimento di FisicaUniversità di PadovaPadovaItaly

Personalised recommendations