A CNN adapted to time series for the classification of Supernovae

Abstract : Cosmologists are facing the problem of the analysis of a huge quantity of data when observing the sky. The methods used in cos-mology are, for the most of them, relying on astrophysical models, and thus, for the classification, they usually use a machine learning approach in two-steps, which consists in, first, extracting features , and second, using a classifier. In this paper, we are specifically studying the supernovae phenomenon and especially the binary classification "I.a supernovae versus not-I.a supernovae". We present two Convolutional Neural Networks (CNNs) defeating the current state-of-the-art. The first one is adapted to time series and thus to the treatment of supernovae light-curves. The second one is based on a Siamese CNN and is suited to the nature of data, i.e. their sparsity and their weak quantity (small learning database).
Type de document :
Communication dans un congrès
Electronic Imaging, Jan 2019, Burlingame, CA, United States. IS&T International Symposium on Electronic Imaging - Proceedings of Color Imaging XXIV: Displaying, Processing, Hardcopy, and Applications, 2019
Liste complète des métadonnées

https://hal-lirmm.ccsd.cnrs.fr/lirmm-01968489
Contributeur : Marc Chaumont <>
Soumis le : mercredi 2 janvier 2019 - 18:39:34
Dernière modification le : mercredi 9 janvier 2019 - 01:22:46

Fichier

IST_ELECTRONIC_IMAGING_Color_I...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : lirmm-01968489, version 1

Citation

Anthony Brunel, Johanna Pasquet, Jérôme Pasquet, Nancy Rodriguez, Frédéric Comby, et al.. A CNN adapted to time series for the classification of Supernovae. Electronic Imaging, Jan 2019, Burlingame, CA, United States. IS&T International Symposium on Electronic Imaging - Proceedings of Color Imaging XXIV: Displaying, Processing, Hardcopy, and Applications, 2019. 〈lirmm-01968489〉

Partager

Métriques

Consultations de la notice

44

Téléchargements de fichiers

34