%0 Journal Article
%9 ACL : Articles dans des revues avec comité de lecture répertoriées par l'AERES
%A Chahdi, Hatim
%A Grozavu, N.
%A Mougenot, I.
%A Bennani, Y.
%A Berti-Equille, Laure
%T Génération de contraintes pour le clustering à partir d'une ontologie : application à la classification d'images satellites
%B Neural information processing : 23rd international conference, ICONIP 2016, Kyoto, Japan, October 16-21, 2016 : proceedings, part III
%C Cham
%D 2016
%E Hirose, A.
%E Ozawa, S.
%E Doya, K.
%E Ikeda, K.
%E Lee, M.
%E Liu, D.
%L fdi:010072201
%G ENG
%I Springer
%@ 978-3-319-46674-3
%K INTELLIGENCE ARTIFICIELLE ; TRAITEMENT D'IMAGE ; IMAGE SATELLITE ; CLASSIFICATION
%K ONTOLOGIE ; CLUSTERING
%M ISI:000389805200018
%N 9949
%P 156-164
%R 10.1007/978-3-319-46675-0_18
%U https://www.documentation.ird.fr/hor/fdi:010072201
%> https://www.documentation.ird.fr/intranet/publi/depot/2018-02-09/010072201.pdf
%W Horizon (IRD)
%X In this paper, we present a new approach combining topological unsupervised learning with ontology based reasoning to achieve both: (i) automatic interpretation of clustering, and (ii) scaling ontology reasoning over large datasets. The interest of such approach holds on the use of expert knowledge to automate cluster labeling and gives them high level semantics that meets the user interest. The proposed approach is based on two steps. The first step performs a topographic unsupervised learning based on the SOM (Self-Organizing Maps) algorithm. The second step integrates expert knowledge in the map using ontology reasoning over the prototypes and provides an automatic interpretation of the clusters. We apply our approach to the real problem of satellite image classification. The experiments highlight the capacity of our approach to obtain a semantically labeled topographic map and the obtained results show very promising performances.
%S Lecture Notes in Computer Science
%B ICONIP : International Conference on Neural Information Processing
%8 2016/10/16-21
%$ 122INTAR ; 126TELTRN