Functional Principal components direction to cluster earthquake waveforms

D'Alessandro, A.

Risultato della ricerca: Paper

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 functional nature of data, applying a variant of a k-means algorithm based on the principal component rotation of data. We apply a classical clustering method to rotated data, according to the direction of maximum variance. A k-means clustering algorithm based on PCA rotation of data is proposed, as an alternative to 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 originaleEnglish
Stato di pubblicazionePublished - 2010

Fingerprint

earthquake
interpolation
method

Cita questo

Functional Principal components direction to cluster earthquake waveforms. / D'Alessandro, A.

2010.

Risultato della ricerca: Paper

D'Alessandro, A. 2010, 'Functional Principal components direction to cluster earthquake waveforms'.
D'Alessandro, A.. Functional Principal components direction to cluster earthquake waveforms. 2010.
D'Alessandro, A. / Functional Principal components direction to cluster earthquake waveforms.
@conference{c57ac07da5684af2a71389e34b87d19f,
title = "Functional Principal components direction to cluster earthquake waveforms",
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 functional nature of data, applying a variant of a k-means algorithm based on the principal component rotation of data. We apply a classical clustering method to rotated data, according to the direction of maximum variance. A k-means clustering algorithm based on PCA rotation of data is proposed, as an alternative to 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))",
keywords = "FPCA, waveforms, clustering approach",
author = "{D'Alessandro, A.} and Dario Luzio and Marcello Chiodi and Giada Adelfio",
year = "2010",
language = "English",

}

TY - CONF

T1 - Functional Principal components direction to cluster earthquake waveforms

AU - D'Alessandro, A.

AU - Luzio, Dario

AU - Chiodi, Marcello

AU - Adelfio, Giada

PY - 2010

Y1 - 2010

N2 - 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 functional nature of data, applying a variant of a k-means algorithm based on the principal component rotation of data. We apply a classical clustering method to rotated data, according to the direction of maximum variance. A k-means clustering algorithm based on PCA rotation of data is proposed, as an alternative to 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))

AB - 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 functional nature of data, applying a variant of a k-means algorithm based on the principal component rotation of data. We apply a classical clustering method to rotated data, according to the direction of maximum variance. A k-means clustering algorithm based on PCA rotation of data is proposed, as an alternative to 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))

KW - FPCA, waveforms, clustering approach

UR - http://hdl.handle.net/10447/52911

UR - http://meetingorganizer.copernicus.org/EGU2010/EGU2010-10344-1.pdf

M3 - Paper

ER -

Accesso al documento