Data Mining consists in extracting previously unknown, potentially useful and reliable patterns from a given
set of data. The use of classification techniques, as well as the use of clustering techniques, can
provide important information for applications arising in various disciplines. The aim of our
Classification Days is to bring together researchers either working on the development
of specific data mining techniques, or interested in using such techniques for extracting useful
information from databases obtained when studying particular real-life problems.
CD3 "Time-series classification", June 21st, 2017.
During each CD, speakers are invited to give presentations of their scientific results and of their
scientific projects; these presentations will then be used as a starting point for a deeper
discussion involving all partecipants. At each CD, previous discussions are reminded and, when
this is the case, new collaborations issued from previous CDs are presented.
This page is for collecting all CD's programs, discussions and slides provided by the speakers.
It also collects the main references at the basis of the discussions, with a direct link to
the original publication.
PhD students of the Matisse Doctoral School, with the agreement of their supervisors, can have
their attendance to the CDs validated as "heures de formation".
CD2 "Enhancing k-means", February 7th, 2017.
Simon Malinowski, IRISA and University of Rennes 1
Recent Advances in Time Series Classification
Christophe Lino, IRISA (Rennes)
Towards Data-Driven Virtual Cinematography
Ferran Argelaguet, INRIA Rennes
Spatial and Rotation Invariant 3D Gesture Recognition Based on Sparse Representation
CD1 "Supervised biclustering", November 10th, 2016.
- Supervised biclustering
S. Busygin, O.A. Prokopyev, P.M. Pardalos,
Feature Selection for Consistent Biclustering via Fractional 0-1 Programming,
Journal of Combinatorial Optimization 10, 7-21, 2005.
A. Mucherino, L. Liberti,
A VNS-based Heuristic for Feature Selection in Data Mining.
In: "Hybrid Meta-Heuristics", Studies in Computational Intelligence 434,
E-G. Talbi (Ed.), 353-368, 2013.
- Big data approaches
N. Keriven, A. Bourrier, R. Gribonval, P. Pérez,
Sketching for Large-Scale Learning of Mixture Models,
IEEE Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP2016),
Shanghai, China, 6 pages, 2016.
N. Keriven, N. Tremblay, Y. Traonmilin, R. Gribonval,
to appear in IEEE Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP2017),
New Orleans, USA, 5 pages, 2017.
M. Morel, R. Kulpa, A. Sorel, C. Achard, S. Dubuisson,
Automatic and Generic Evaluation of Spatial and Temporal Errors in Sport Motions,
Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications,
Rome, Italy, 542-551, 2016.
A.L. Cruz Ruiz, C. Pontonnier, A. Sorel, G. Dumont,
Identifying Representative Muscle Synergies in Overhead Football Throws,
Computer Methods in Biomechanics and Biomedical Engineering 18(sup1), 1918-1919, 2015.
The CDs are organized by Antonio Mucherino and the main participants are the members of the MimeTIC team at IRISA/INRIA.
However, the speakers from other teams are regurarly invited to give presentations and take part to the discussions.
To INRIA for providing the coffee breaks!