User menu

Accès à distance ? S'identifier sur le proxy UCLouvain

Forecasting Time-Series by Kohonen Classification

Primary tabs

Lendasse, Amaury [UCL] de Bodt, Eric [UCL] Cottrell, Marie [Université Paris 1] Verleysen, Michel [UCL] Grégoire, Philippe [FUNDP]

In this paper, we propose a generic non-linear approach for time series forecasting. The main feature of this approach is the use of a simple statistical forecasting in small regions of an input space adequately chosen and quantized. The partition of the space is achieved by the Kohonen algorithm. The method is then applied to a widely known time-series from the SantaFe competition, and the results are compared with the best ones published for this series.

Document type Communication à un colloque (Conference Paper) – Présentation orale avec comité de sélection
Access type Accès restreint
Publication date 1998
Language Anglais
Conference "European Symposium on Artificial Neural Networks (ESANN'98)", Bruges (Belgium) (du 22/04/1998 au 24/04/1998)
Peer reviewed yes
Host document "Proceedigns of ESANN'98, European Symposium on Artificial Neural Networks"- p. 221-226 (ISBN : 2-9600049-8-1)
Publisher D-Facto public.
Affiliations UCL - FSA/ELEC - Département d'électricité
UCL - ESPO/IAG - Département d'administration et de gestion
Université Paris 1 - SAMOS
FUNDP - ECO_CeReFIM (Centre de recherche en finance)
Links
Bibliographic reference Lendasse, Amaury ; de Bodt, Eric ; Cottrell, Marie ; Verleysen, Michel ; Grégoire, Philippe. Forecasting Time-Series by Kohonen Classification.European Symposium on Artificial Neural Networks (ESANN'98) (Bruges (Belgium), du 22/04/1998 au 24/04/1998). In: Proceedigns of ESANN'98, European Symposium on Artificial Neural Networks, D-Facto public.1998, p. 221-226
Permanent URL http://hdl.handle.net/2078.1/111381