Classification automatique de donn\'ees temporelles en classes ordonn\'ees
Machine Learning
2013-12-30 v1 Methodology
Abstract
This paper proposes a method of segmenting temporal data into ordered classes. It is based on mixture models and a discrete latent process, which enables to successively activates the classes. The classification can be performed by maximizing the likelihood via the EM algorithm or by simultaneously optimizing the model parameters and the partition by the CEM algorithm. These two algorithms can be seen as alternatives to Fisher's algorithm, which improve its computing time.
Cite
@article{arxiv.1312.7011,
title = {Classification automatique de donn\'ees temporelles en classes ordonn\'ees},
author = {Faicel Chamroukhi and Allou Samé and Gérard Govaert and Patrice Aknin},
journal= {arXiv preprint arXiv:1312.7011},
year = {2013}
}
Comments
in French, 44\`emes Journ\'ees de Statistique, SFdS