In this paper we intend to shed further light on time series clustering. Firstly, we aim at clarifying, via Monte Carlo simulations, to which extent the choice of the measure of dissimilarity can affect the results of time series cluster analysis. Then we move to a different point of view and tackle the issue of classifying time series using the Self Organizing Maps (Kohonen, 2001), typically employed in pattern recognition for cross-sectional data.
A different perspective on clustering time series
GEROLIMETTO, Margherita;PROCIDANO, Isabella
2011-01-01
Abstract
In this paper we intend to shed further light on time series clustering. Firstly, we aim at clarifying, via Monte Carlo simulations, to which extent the choice of the measure of dissimilarity can affect the results of time series cluster analysis. Then we move to a different point of view and tackle the issue of classifying time series using the Self Organizing Maps (Kohonen, 2001), typically employed in pattern recognition for cross-sectional data.
File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
GerolimettoProcidano-attiCLADAG2011.pdf
non disponibili
Tipologia:
Documento in Post-print
Licenza:
Accesso chiuso-personale
Dimensione
115.37 kB
Formato
Adobe PDF
|
115.37 kB | Adobe PDF | Visualizza/Apri |
I documenti in ARCA sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
