Forecasting the CATS benchmark with the Double Vector Quantization method - Université Paris 1 Panthéon-Sorbonne Accéder directement au contenu
Article Dans Une Revue Neurocomputing Année : 2007

Forecasting the CATS benchmark with the Double Vector Quantization method

Résumé

The Double Vector Quantization method, a long-term forecasting method based on the SOM algorithm, has been used to predict the 100 missing values of the CATS competition data set. An analysis of the proposed time series is provided to estimate the dimension of the auto-regressive part of this nonlinear auto-regressive forecasting method. Based on this analysis experimental results using the Double Vector Quantization (DVQ) method are presented and discussed. As one of the features of the DVQ method is its ability to predict scalars as well as vectors of values, the number of iterative predictions needed to reach the prediction horizon is further observed. The method stability for the long term allows obtaining reliable values for a rather long-term forecasting horizon.
Fichier principal
Vignette du fichier
neurocomp_def.pdf (440.93 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00134938 , version 1 (05-03-2007)

Identifiants

Citer

Geoffroy Simon, John Lee, Marie Cottrell, Michel Verleysen. Forecasting the CATS benchmark with the Double Vector Quantization method. Neurocomputing, 2007, 70 (13-15), pp.2400-2409. ⟨10.1016/j.neucom.2005.12.137⟩. ⟨hal-00134938⟩
100 Consultations
220 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More