Abstract
This paper proposes a clustering procedure for samples of multivariate functions in \((L^2(I))^{J}\), with \(J\ge 1\). This method is based on a k-means algorithm in which the distance between the curves is measured with a metric that generalizes the Mahalanobis distance in Hilbert spaces, considering the correlation and the variability along all the components of the functional data. The proposed procedure has been studied in simulation and compared with the k-means based on other distances typically adopted for clustering multivariate functional data. In these simulations, it is shown that the k-means algorithm with the generalized Mahalanobis distance provides the best clustering performances, both in terms of mean and standard deviation of the number of misclassified curves. Finally, the proposed method has been applied to two case studies, concerning ECG signals and growth curves, where the results obtained in simulation are confirmed and strengthened.
Similar content being viewed by others
References
Boudaoud S, Rix H, Meste O (2010) Core shape modelling of a set of curves. Comput Stat Data Anal 54:308–325
Bouveyron C (2015) funFEM: clustering in the discriminative functional subspace. R package version 1.1. https://CRAN.R-project.org/package=funFEM. Accessed 26 Nov 2018
Cerioli A (2005) K-means cluster analysis and Mahalanobis metrics: a problematic match or an overlooked opportunity? Stat Appl 17:1
Ferraty F, Vieu P (2006) Nonparametric functional data analysis: theory and practice. Springer series in statistics. Springer, New York
Galeano P, Joseph E, Lillo Rosa E (2014) The Mahalanobis distance for functional data with applications to classification. Technometrics 57(2):281–291
Gattone SA, Rocci R (2012) Clustering curves on a reduced subspace. J Comput Graph Stat 21(2):361–379
Ghiglietti A, Paganoni AM (2017) Exact tests for the means of gaussian stochastic processes. Stat Prob Lett 131:102–107
Ghiglietti A, Ieva F, Paganoni AM (2017) Statistical inference for stochastic processes: two-sample hypothesis tests. J Stat Plann Inference 180:49–68
Horváth L, Kokoszka P (2012) Inference for functional data with applications. Springer series in statistics. Springer, New York
Ieva F, Paganoni AM, Pigoli D, Vitelli V (2013) Multivariate functional clustering for the morphological analysis of electrocardiograph curves. J R Stat Soc Ser C Appl Stat 62:401–418
Jacques J, Preda C (2014) Model-based clustering for multivariate functional data. Comput Stat Data Anal 71:92–106
Kaufman L, Rousseeuw PJ (2009) Finding groups in data: an introduction to cluster analysis, vol 344. Wiley, New York
Liu X, Müller HG (2003) Modes and clustering for time-warped gene expression profile data. Bioinformatics 19:1937–1944
Liu X, Yang M (2009) Simultaneous curve registration and clustering for functional data. Comput Stat Data Anal 53:1361–1376
Martino A, Ghiglietti A, Ieva F, Paganoni AM (2018) gmfd: inference and clustering of functional data. R package version 1.0.1. https://CRAN.R-project.org/package=gmfd. Accessed 26 Nov 2018
Melnykov I, Melnykov V (2014) On K-means algorithm with the use of Mahalanobis distances. Stat Prob Lett 84:88–95
R Core Team (2016) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna
Ramsay J, Silverman BW (2002) Applied functional data analysis–methods and case studies. Springer series in statistics. Springer, New York
Ramsay J, Silverman BW (2005) Functional data analysis, 2nd edn. Springer series in statistics. Springer, New York
Ramsay JO, Wickham H, Graves S, Hooker G (2014) fda: functional data analysis. R package version 2.4.4
Sangalli LM, Secchi P, Vantini S, Vitelli V (2010) k-mean alignment for curve clustering. Comput Stat Data Anal 54:1219–1233
Soueidatt M (2014) Funclustering: a package for functional data clustering. R package version 1.0.1. https://CRAN.R-project.org/package=Funclustering. Accessed 26 Nov 2018
Tarpey T, Kinateder KKK (2003) Clustering functional data. J Classif 20:93–114
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Martino, A., Ghiglietti, A., Ieva, F. et al. A k-means procedure based on a Mahalanobis type distance for clustering multivariate functional data. Stat Methods Appl 28, 301–322 (2019). https://doi.org/10.1007/s10260-018-00446-6
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10260-018-00446-6