Open Access
Translator Disclaimer
2005 Clustering Time Series, Subspace Identification and Cepstral Distances
Jeroen Boets, Katrien De Cock, Marcelo Espinoza, Bart De Moor
Commun. Inf. Syst. 5(1): 69-96 (2005).


In this paper a methodology to cluster time series based on measurement data is described. In particular, we propose a distance for stochastic models based on the concept of subspace angles within a model and between two models. This distance is used to obtain a clustering over the set of time series. We show how it is related to the mutual information of the past and the future output processes, and to a previously defined cepstral distance. Finally, the methodology is applied to the clustering of time series of power consumption within the Belgian electricity grid.


Download Citation

Jeroen Boets. Katrien De Cock. Marcelo Espinoza. Bart De Moor. "Clustering Time Series, Subspace Identification and Cepstral Distances." Commun. Inf. Syst. 5 (1) 69 - 96, 2005.


Published: 2005
First available in Project Euclid: 7 June 2006

zbMATH: 1089.62103
MathSciNet: MR2199724

Rights: Copyright © 2005 International Press of Boston


Vol.5 • No. 1 • 2005
Back to Top