Multilevel Spectral Clustering for extreme event characterization

Kelly Grassi (1) , Émilie Poisson Caillault (2) , Alain Lefebvre (1)

1 IFREMER - Institut Français de Recherche pour l'Exploitation de la Mer
2 LISIC - Laboratoire d'Informatique Signal et Image de la Côte d'Opale

Direct spectral clustering framework was first proposed to extract general pattern events within multivariate time series. This study investigated the way to identify extreme events, i.e. short duration and/or particular events, with no assumption about their emission date, duration and/or shape. A Multilevel Spectral Clustering (M-SC) architecture is proposed and compared with state-of-the-art clustering methods from a simulated manually labeled time series. Due to these promising empirical results, this new deep architecture is applied on marine field data.

Domaines: Machine Learning [stat.ML]

Kelly Grassi, Émilie Poisson Caillault, Alain Lefebvre. Multilevel Spectral Clustering for extreme event characterization. OCEANS 2019 - Marseille, Jun 2019, Marseille, France. pp.1-7, ⟨10.1109/OCEANSE.2019.8867261⟩. ⟨hal-03081909⟩