Abstract
Looking for curves similarity could be a complex issue characterized by subjective choices related to continuous transformations of observed discrete data (Chiodi, 1989).In this paper we combine the aim of finding clusters from a set of individual curves to the functionalnature of data, applying a variant of a k-means algorithm based on the principal componentrotation of data. We apply a classical clustering method to rotated data, according to the directionof maximum variance.A k-means clustering algorithm based on PCA rotation of data is proposed, as an alternativeto methods that require previous interpolation of data based on splines or linear fitting (Garc´ıa-Escudero and Gordaliza (2005), Tarpey (2007), Sangalli et al. (2008))
Lingua originale | English |
---|---|
Numero di pagine | 3 |
Stato di pubblicazione | Published - 2010 |