EAST representation: fast discovery of discriminant temporal patterns from time series

Abstract : Mining discriminant temporal patterns is one problematic for the time series classification currently led by the shapelet. We expose this problematic under the angle of a standard feature-space classification task. This approach is enabled by the recent observation that most enumerable subsequences from a time series are redundant and can be discarded. In addition to be simple, the approach turns out to have state of-the-art classification performances with extremely fast computations. It also provides a flexible framework with interesting perspectives.
Type de document :
Communication dans un congrès
ECML/PKDD Workshop on Advanced Analytics and Learning on Temporal Data, Sep 2016, Riva Del Garda, Italy
Liste complète des métadonnées

https://hal.sorbonne-universite.fr/hal-01350734
Contributeur : Xavier Renard <>
Soumis le : lundi 1 août 2016 - 15:17:36
Dernière modification le : jeudi 22 novembre 2018 - 01:21:46

Identifiants

  • HAL Id : hal-01350734, version 1

Collections

Citation

Xavier Renard, Maria Rifqi, Gabriel Fricout, Marcin Detyniecki. EAST representation: fast discovery of discriminant temporal patterns from time series. ECML/PKDD Workshop on Advanced Analytics and Learning on Temporal Data, Sep 2016, Riva Del Garda, Italy. 〈hal-01350734〉

Partager

Métriques

Consultations de la notice

323