Exploratory analysis of functional data via clustering and optimal segmentation

NEUROCOMPUTING

卷:73

Article

Hebrail, Georges¹  Hugueney, Bernard²  Lechevallier, Yves³  Rossi, Fabrice¹ 

[1] Telecom ParisTech, BILab, CNRS, UMR 5141,LTCI, F-75013 Paris, France

[2] Univ Paris 09, LAMSADE, F-75016 Paris, France

[3] INRIA, Projet AxIS, F-78153 Le Chesnay, France

关键词: Functional data;    Multiple time series;    Exploratory analysis;    Clustering;    Segmentation;    Dynamic programming;   

DOI  :  10.1016/j.neucom.2009.11.022

来源: Elsevier

【 摘 要 】

We propose in this paper an exploratory analysis algorithm for functional data. The method partitions a set of functions into K clusters and represents each cluster by a simple prototype (e.g., piecewise constant). The total number of segments in the prototypes, P, 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. (C) 2010 Elsevier B.V. All rights reserved.

【 授权许可】

Free