Neural Gas Based Classification of Globular Clusters

  • Giuseppe AngoraEmail author
  • Massimo Brescia
  • Stefano Cavuoti
  • Giuseppe Riccio
  • Maurizio Paolillo
  • Thomas H. Puzia
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 822)


Within scientific and real life problems, classification is a typical case of extremely complex tasks in data-driven scenarios, especially if approached with traditional techniques. Machine Learning supervised and unsupervised paradigms, providing self-adaptive and semi-automatic methods, are able to navigate into large volumes of data characterized by a multi-dimensional parameter space, thus representing an ideal method to disentangle classes of objects in a reliable and efficient way. In Astrophysics, the identification of candidate Globular Clusters through deep, wide-field, single band images, is one of such cases where self-adaptive methods demonstrated a high performance and reliability. Here we experimented some variants of the known Neural Gas model, exploring both supervised and unsupervised paradigms of Machine Learning for the classification of Globular Clusters. Main scope of this work was to verify the possibility to improve the computational efficiency of the methods to solve complex data-driven problems, by exploiting the parallel programming with GPU framework. By using the astrophysical playground, the goal was to scientifically validate such kind of models for further applications extended to other contexts.


Data analytics Astroinformatics Globular Clusters Machine learning Neural Gas 



MB acknowledges the INAF PRIN-SKA 2017 program and the funding from MIUR Premiale 2016: MITIC.


  1. 1.
    Al-Rfou, R., Alain, G., Almahairi, A., et al.: Theano: A Python framework for fast computation of mathematical expressions. ArXiv e-prints, May 2016Google Scholar
  2. 2.
    Angora, G., Brescia, M., Riccio, G., Cavuoti, S., Paolillo, M., Puzia, T.H.: Astrophysical data analytics based on neural gas models, using the classification of globular clusters as playground. In: CEUR Workshop Proceedings, vol. 2022, pp. 381–388 (2017)Google Scholar
  3. 3.
    Annunziatella, M., Mercurio, A., Brescia, M., Cavuoti, S., Longo, G.: Inside catalogs: a comparison of source extraction software. Publ. Astron. Soc. Pac. 125(923), 68–82 (2013). Scholar
  4. 4.
    Bertin, E., Arnouts, S.: SExtractor: software for source extraction. Astron. Astrophys. Suppl. 117, 393–404 (1996). Scholar
  5. 5.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001). Scholar
  6. 6.
    Brescia, M., Cavuoti, S., Longo, G., et al.: Dameware: a web cyberinfrastructure for astrophysical data mining. Publ. Astron. Soc. Pac. 126(942), 783–797 (2014)Google Scholar
  7. 7.
    Brescia, M., Cavuoti, S., Paolillo, M., Longo, G., Puzia, T.: The detection of globular clusters in galaxies as a data mining problem. Mon. Not. R. Astron. Soc. 421(2), 1155–1165 (2012). Scholar
  8. 8.
    Brescia, M., Longo, G.: Astroinformatics, data mining and the future of astronomical research. Nuclear Instrum. Methods Phys. Res. A 720, 92–94 (2013). Scholar
  9. 9.
    Broomhead, D., Lowe, D.: Radial basis functions, multi-variable functional interpolation and adaptive networks RSRE-MEMO-4148, March 1988Google Scholar
  10. 10.
    Carlson, M., Holtzman, J.: Measuring sizes of marginally resolved young globular clusters with the hubble space telescope. Publ. Astron. Soc. Pac. 113(790), 1522–1540 (2001). Scholar
  11. 11.
    Cavuoti, S., Garofalo, M., Brescia, M., Paolillo, M., Pescape’, A., Longo, G., Ventre, G.: Astrophysical data mining with gpu. a case study: genetic classification of globular clusters. New Astron. 26, 12–22 (2014). Scholar
  12. 12.
    Cavuoti, S., Garofalo, M., Brescia, M., Pescape, A., Longo, G., Ventre, G.: Genetic algorithm modeling with GPU parallel computing technology. Smart Innov. Syst. Technol. 19, 29–39 (2013). Scholar
  13. 13.
    D’Isanto, A., Cavuoti, S., Brescia, M., Donalek, C., Longo, G., Riccio, G., Djorgovski, S.: An analysis of feature relevance in the classification of astronomical transients with machine learning methods. Mon. Not. R. Astron. Soc. 457(3), 3119–3132 (2016). Scholar
  14. 14.
    Dunn, L., Jerjen, H.: First results from sapac: toward a three-dimensional picture of the fornax cluster core. Astron. J. 132(3), 1384–1395 (2006). Scholar
  15. 15.
    Fritzke, B.: Supervised learning with growing cell structures. In: Proceedings of the 6th International Conference on Neural Information Processing Systems, NIPS 1993, pp. 255–262. Morgan Kaufmann Publishers Inc., San Francisco (1993).
  16. 16.
    Fritzke, B.: A growing neural gas network learns topologies. In: Proceedings of the 7th International Conference on Neural Information Processing Systems, NIPS 1994, pp. 625–632. MIT Press, Cambridge (1994).
  17. 17.
    Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. J. Mach. Learn. Res. 3, 1157–1182 (2003).
  18. 18.
    Harrell Jr., F.E.: Regression Modeling Strategies. Springer-Verlag New York Inc., Secaucus (2006)Google Scholar
  19. 19.
    Hughes, G.: On the mean accuracy of statistical pattern recognizers. IEEE Trans. Inf. Theor. 14(1), 55–63 (2006). Scholar
  20. 20.
    Jirayusakul, A., Auwatanamongkol, S.: A supervised growing neural gas algorithm for cluster analysis. Int. J. Hybrid Intell. Syst. 4(2), 129–141 (2007). Scholar
  21. 21.
    Martinetz, T., Schulten, K.: A “neural-gas” network learns topologies. Artif. Neural Networks 1, 397–402 (1991)Google Scholar
  22. 22.
    Martinetz, T., Berkovich, S., Schulten, K.: “neural-gas” network for vector quantization and its application to time-series prediction. IEEE Trans. Neural Networks 4(4), 558–569 (1993). Scholar
  23. 23.
    McCulloch, W., Pitts, W.: A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophys. 5(4), 115–133 (1943). Scholar
  24. 24.
    Montoro, J.C.G., Abascal, J.L.F.: The voronoi polyhedra as tools for structure determination in simple disordered systems. J. Phys. Chem. 97(16), 4211–4215 (1993). Scholar
  25. 25.
    Paolillo, M., Puzia, T.H., Goudfrooij, P., et al.: Probing the GC-LMXB Connection in NGC 1399: a wide-field study with the hubble space telescope and Chandra. Astrophys. J. 736, 90 (2011). Scholar
  26. 26.
    Pedregosa, F., Varoquaux, G., Gramfort, et al.: Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825–2830 (2011)Google Scholar
  27. 27.
    Puzia, T.H., Paolillo, M., Goudfrooij, P., et al.: Wide-field hubble space telescope observations of the globular cluster system in NGC 1399, ApJ 786, 78 (2014). Scholar
  28. 28.
    Stehman, S.V.: Selecting and interpreting measures of thematic classification accuracy. Remote Sens. Environ. 62(1), 77–89 (1997). Scholar
  29. 29.
    van der Walt, S., Colbert, S.C., Varoquaux, G.: The numpy array: a structure for efficient numerical computation. Comput. Sci. Eng. 13(2), 22–30 (2011). Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.University of Naples Federico II - Dept. of Physics “E. Pancini”NapoliItaly
  2. 2.INAF - Astronomical Observatory of CapodimonteNapoliItaly
  3. 3.INFN - Napoli UnitNapoliItaly
  4. 4.Institute of AstrophysicsPontificia Universidad Catolica de ChileMaculChile

Personalised recommendations