Exploratory Analysis of Functional Data via Clustering and Optimal Segmentation
Machine Learning
2010-04-06 v1 Machine Learning
Abstract
We propose in this paper an exploratory analysis algorithm for functional data. The method partitions a set of functions into clusters and represents each cluster by a simple prototype (e.g., piecewise constant). The total number of segments in the prototypes, , is chosen by the user and optimally distributed among the clusters via two dynamic programming algorithms. The practical relevance of the method is shown on two real world datasets.
Cite
@article{arxiv.1004.0456,
title = {Exploratory Analysis of Functional Data via Clustering and Optimal Segmentation},
author = {Georges Hébrail and Bernard Hugueney and Yves Lechevallier and Fabrice Rossi},
journal= {arXiv preprint arXiv:1004.0456},
year = {2010}
}