Space-Time FPCA Clustering of Multidimensional Curves.

Giada Adelfio, Marcello Chiodi, Francesca Di Salvo, Francesca Di Salvo, Marcello Chiodi, Giada Adelfio

Risultato della ricerca: Chapter

Abstract

In this paper we focus on finding clusters of multidimensional curves with spatio-temporal structure, applying a variant of a k-means algorithm based on the principal component rotation of data. The main advantage of this approach is to combine the clustering functional analysis of the multidimensional data, with smoothing methods based on generalized additive models, that cope with both the spatial and the temporal variability, and with functional principal components that takes into account the dependency between the curves.
Lingua originaleEnglish
Titolo della pubblicazione ospiteStudies in Theoretical and Applied Statistics. SIS 2016.
Numero di pagine10
Stato di pubblicazionePublished - 2018

Serie di pubblicazioni

NomeSPRINGER PROCEEDINGS IN MATHEMATICS & STATISTICS

Fingerprint

Principal Components
Space-time
Clustering
Generalized Additive Models
Clustering Analysis
Curve
Smoothing Methods
Multidimensional Data
K-means Algorithm
Functional Analysis

All Science Journal Classification (ASJC) codes

  • Mathematics(all)

Cita questo

Adelfio, G., Chiodi, M., Di Salvo, F., Di Salvo, F., Chiodi, M., & Adelfio, G. (2018). Space-Time FPCA Clustering of Multidimensional Curves. In Studies in Theoretical and Applied Statistics. SIS 2016. (SPRINGER PROCEEDINGS IN MATHEMATICS & STATISTICS).

Space-Time FPCA Clustering of Multidimensional Curves. / Adelfio, Giada; Chiodi, Marcello; Di Salvo, Francesca; Di Salvo, Francesca; Chiodi, Marcello; Adelfio, Giada.

Studies in Theoretical and Applied Statistics. SIS 2016.. 2018. (SPRINGER PROCEEDINGS IN MATHEMATICS & STATISTICS).

Risultato della ricerca: Chapter

Adelfio, G, Chiodi, M, Di Salvo, F, Di Salvo, F, Chiodi, M & Adelfio, G 2018, Space-Time FPCA Clustering of Multidimensional Curves. in Studies in Theoretical and Applied Statistics. SIS 2016.. SPRINGER PROCEEDINGS IN MATHEMATICS & STATISTICS.
Adelfio G, Chiodi M, Di Salvo F, Di Salvo F, Chiodi M, Adelfio G. Space-Time FPCA Clustering of Multidimensional Curves. In Studies in Theoretical and Applied Statistics. SIS 2016.. 2018. (SPRINGER PROCEEDINGS IN MATHEMATICS & STATISTICS).
Adelfio, Giada ; Chiodi, Marcello ; Di Salvo, Francesca ; Di Salvo, Francesca ; Chiodi, Marcello ; Adelfio, Giada. / Space-Time FPCA Clustering of Multidimensional Curves. Studies in Theoretical and Applied Statistics. SIS 2016.. 2018. (SPRINGER PROCEEDINGS IN MATHEMATICS & STATISTICS).
@inbook{21acb9bfd65f4d7393ea515d83fb2993,
title = "Space-Time FPCA Clustering of Multidimensional Curves.",
abstract = "In this paper we focus on finding clusters of multidimensional curves with spatio-temporal structure, applying a variant of a k-means algorithm based on the principal component rotation of data. The main advantage of this approach is to combine the clustering functional analysis of the multidimensional data, with smoothing methods based on generalized additive models, that cope with both the spatial and the temporal variability, and with functional principal components that takes into account the dependency between the curves.",
author = "Giada Adelfio and Marcello Chiodi and {Di Salvo}, Francesca and {Di Salvo}, Francesca and Marcello Chiodi and Giada Adelfio",
year = "2018",
language = "English",
isbn = "978-3-319-73905-2",
series = "SPRINGER PROCEEDINGS IN MATHEMATICS & STATISTICS",
booktitle = "Studies in Theoretical and Applied Statistics. SIS 2016.",

}

TY - CHAP

T1 - Space-Time FPCA Clustering of Multidimensional Curves.

AU - Adelfio, Giada

AU - Chiodi, Marcello

AU - Di Salvo, Francesca

AU - Di Salvo, Francesca

AU - Chiodi, Marcello

AU - Adelfio, Giada

PY - 2018

Y1 - 2018

N2 - In this paper we focus on finding clusters of multidimensional curves with spatio-temporal structure, applying a variant of a k-means algorithm based on the principal component rotation of data. The main advantage of this approach is to combine the clustering functional analysis of the multidimensional data, with smoothing methods based on generalized additive models, that cope with both the spatial and the temporal variability, and with functional principal components that takes into account the dependency between the curves.

AB - In this paper we focus on finding clusters of multidimensional curves with spatio-temporal structure, applying a variant of a k-means algorithm based on the principal component rotation of data. The main advantage of this approach is to combine the clustering functional analysis of the multidimensional data, with smoothing methods based on generalized additive models, that cope with both the spatial and the temporal variability, and with functional principal components that takes into account the dependency between the curves.

UR - http://hdl.handle.net/10447/288534

M3 - Chapter

SN - 978-3-319-73905-2

T3 - SPRINGER PROCEEDINGS IN MATHEMATICS & STATISTICS

BT - Studies in Theoretical and Applied Statistics. SIS 2016.

ER -