User menu

Accès à distance ? S'identifier sur le proxy UCLouvain

Time series forecasting: Obtaining long term trends with self-organizing maps

Primary tabs

Simon, Geoffroy [UCL] Lendasse, Amauri [Helsinki University of Technology] Cottrell, Marie [Université Paris I] Fort, JC [Université Paul Sabatier Toulouse] Verleysen, Michel [UCL]

Kohonen self-organisation maps are a well know classification tool, commonly used in a wide variety of problems, but with limited applications in time series forecasting context. In this paper, we propose a forecasting method specifically designed for multi-dimensional long-term trends prediction, with a double application of the Kohonen algorithm. Practical applications of the method are also presented. (c) 2005 Elsevier B.V. All rights reserved.

Document type Communication à un colloque (Conference Paper) – Présentation orale avec comité de sélection
Access type Accès restreint
Publication date 2005
Language Anglais
Conference "1st IAPR TC3 Workshop on Artificial Neural Networks in Pattern Recognition", Florence(Italy) (Sep 12-13, 2003)
Journal information "Pattern Recognition Letters" - Vol. 25, no. 12, p. 1795-1808 (2005)
Peer reviewed yes
issn 0167-8655
e-issn 1872-7344
Host document
Publisher Elsevier Science Bv (Amsterdam)
Affiliation UCL - FSA/ELEC - Département d'électricité
Keywords Self-organizing Maps ; Long-term trends ; Time series forecasting
Links
Bibliographic reference Simon, Geoffroy ; Lendasse, Amauri ; Cottrell, Marie ; Fort, JC ; Verleysen, Michel. Time series forecasting: Obtaining long term trends with self-organizing maps.1st IAPR TC3 Workshop on Artificial Neural Networks in Pattern Recognition (Florence(Italy), Sep 12-13, 2003). In: Pattern Recognition Letters, Vol. 25, no. 12, p. 1795-1808 (2005)
Permanent URL http://hdl.handle.net/2078.1/60899