Afficher la couverture 'Multilevel Spectral Clustering for extreme event characterization | Grassi, Kelly' en grand format
/5

0 avis

Multilevel Spectral Clustering for extreme event characterization

Archive ouverte

Grassi, Kelly | Poisson Caillault, Émilie | Lefebvre, Alain

Edité par CCSD ; IEEE -

International audience. 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.

Consulter en ligne

Suggestions

Du même auteur

Comparative Study of Clustering Approaches Applied to Spatial or Temporal Pattern Discovery

Archive ouverte | Grassi, Kelly | CCSD

International audience. In the framework of ecological or environmental assessments and management, detection, characterization and forecasting of the dynamics of environmental states are of paramount importance. Th...

Caractérisation de la dynamique du phytoplancton, des événements récurrents aux événements extrêmes, grâce au Machine Learning

Archive ouverte | Lefebvre, Alain | CCSD

International audience

Which DTW Method Applied to Marine Univariate Time Series Imputation

Archive ouverte | Phan, Thi-Thu-Hong | CCSD

International audience. Missing data are ubiquitous in any domains of applied sciences. Processing datasets containing missing values can lead to a loss of efficiency and unreliable results, especially for large mis...

Chargement des enrichissements...