Team AxIS
Members
Overall Objectives
Application Domains
Software
New Results
Contracts and Grants with Industry
Other Grants and Activities
Bibliography
previous up next PDF XML

Section: Other Grants and Activities

International Initiatives

Introduction

The following international initiatives are briefly described in this section:

Brazil: FACEPE-INRIA

Participants : Marc Csernel, Yves Lechevallier.

We continue our collaboration on clustering and web usage mining and we start a collaboration on social network data analysis with F.A.T. De Carvalho from Federal University of Pernambuco (Recife) and his team.

A scientific project Clustering of Relational Data and Social Network Data Analysis submitted by F. De Carvalho and Y. Lechevallier has been accepted by FACEPE and INRIA. The project starts on january 2010 and ends on december 2011. Researchers and students are concerned by this project from AxIS and CIn-UFPE side. It aims at developing methods of clustering of relational data and social network data analysis tools.

F. de A. T. de Carvalho was a visiting professor at AxIS project during three months (October to December). He collaborated actively with Y. Lechevallier [41] , [40] , [24] on partitional clustering algorithms based on multiple dissimilarity matrices in order to submit a paper to the COMPSTAT conference (Paris, August 22-27 2010) which was accepted [32] and an extended version to a international journal.

Morocco : the WRUM Project

Participants : Bernard Senach, Brigitte Trousse.

We kept contact with the WRUM project (Web Redesign based on Usage Mining). This project received fundings from the Research and Education Ministery and is managed by the CSPT commission. In this project close to the three topics of AxIS, the chosen application domain is e-Learning. Hicham Behja, Prof at ENSAM Meknès is in charge of the WRUM project with the support of Prof. A. Marzark (Univ. of Casablanca). AxIS is involved in the thesis committees of three PhD students (cf. 8.5.5 ).

Tunisia: STIC program

Participant : Yves Lechevallier.

During the STIC program, Y. Lechevallier in collaboration with M-A. Aufaure (Ecole centrale) supervised 4 masters and 2 thesis (Riadi Lab, ENSI Tunis) in this project. These masters and thesis subjects are about web mining (usage, content and structure, using different methods) and ontology construction from heterogeneous sources.

Y. Lechevallier is involved in the new STIC program Exploration des réseaux sociaux pour les systèmes de recommandation between France-Tunisia [56] . In this STIC project, we welcomed from ENSI (Tunisia) at Rocquencourt: A. Louati (April-August) who participated actively to the themes of our STIC under the co-supervision of H. Baazaoui Zghal, M.-A. Aufaure (Supelec), H. Ben Ghezala and Y. Lechevallier. The report [57] describes the need to design and implement a tool for analysing social networks based on the aggregation graphs. After a state of the art of social networks and their analysis, a tool graph based aggregation k-SNAP approach was tested.

USA: Explorer Program

Participant : Chongsheng Zhang.

Chongsheng Zhang, Ph D student, is visiting the WIS team of Prof. Carlo Zaniolo at UCLA from October to November 2010 in the context of the explorer program. This visit is dedicated to the study of bi-streaming data. In such a data stream, each transaction is made by a user with a unique identifier. And it is frequent for one user to make a few transactions within a short time interval. As such, if we observe the transactions by their users, the feature set for each user is unfinished and only partly available at one time point, but new features may be added afterwards. The characteristic that distinguishes it from other data streams lies in the co-evolving of the data points (the feature sets for the users) with the datastreams. That is to say, in a bi-streaming data streams, it is not uncommon that the data points are updating themselves. The dimension of the data can be very large, but one data point only has several features, whereas the features for different data points are not identical. There are many such data streams in real applications. Chongsheng has studied techniques for bistreaming data mining and more particularly itemset mining from such streams.

This work is done in collaboration with Mirjana Mazuran (Polimi, Italy), Hamid Mousavi(UCLA), Carlo Zaniolo (host professor at UCLA).

Participation to Standards in Ergonomics

Participant : Dominique Scapin.

Standardization in ergonomics is increasingly important due to the application of the European directives about the introduction of measures to encourage improvements in the safety and health of workers (e.g., 2006/42CE on security of machinery); as well as taking into consideration national and international legislation, including accessibility. Standardization in ergonomics covers many issues. The contributions from INRIA (D. L. Scapin) concern mainly software ergonomics, in the context of AFNOR X35A, X35E, as well as ISO and CEN mirror groups:


previous
next

Logo Inria