Geozoning

An Open-Source R Package on Zoning Methods for Spatial Data.

• Period: 2015-ongoing
• Partners: INRA, UMR MISTEA, UMR ITAP
• Team: Brigitte Charnomordic, Hazaël Jones, Patrice Loisel, Isabelle Sanchez, Bruno Tisseyre
• Description:A zoning method and a numerical criterion for zoning quality are available in this package. The zoning method is based on a numerical criterion that evaluates the zoning quality. This criterion quantifies simultaneously how zones are heterogeneous on the whole map and how neighbouring zones are similar. This approach allows comparison between maps either with different zones or different labels, which is of importance for zone delineation algorithms aiming at maximizing inter-zone variability. An optimisation procedure provides the user with the best zonings thanks to contour delineation for a given map.




• CRAN package website : geozoning on CRAN

TARDIS

• TARDIS: European Project
• Financial support: European Commission (7th PCRD)
• Period: 3 years (starts in november 2011)
• Partners: UPMC is the project coordinator.
• UPMC Team: Nicolas Sabouret, Hazaël Jones, Ahlem Abbaci, Matthieu Golsenne, Vincent Corruble
• Description: The number of young people not in employment, education or training (NEET) is increasing across Europe. Current research reveals that NEETs often lack self-confidence and the essential social skills needed to seek and secure employment. Youth inclusion associations across Europe provide social coaching programmes, in order to help young people acquire and improve their social competencies. However, it is an expensive and time-consuming approach that relies on the availability of trained practitioners as well as the willingness of the young people to engage in exploring their social strengths and weakness in front of their peers and practitioners. Digital technologies such as serious-games offer the advantage of repeatable experience that can be modulated to suit the individual needs of the young people. Additionally, such technologies are intrinsically motivating to the young and carry the potential of removing the many barriers that real-life situations may pose, in particular the stress associated with engaging in unfamiliar interactions with others.

  TARDIS aims to build a scenario-based serious-game simulation platform for young people at risk of exclusion, aged 16-25, to explore, practice and improve their social skills. TARDIS will facilitate the interaction through virtual agents (VAs) acting as recruiters in job interviews scenarios. The VAs are designed to deliver realistic socio-emotional interactions and are credible, yet tireless interlocutors. TARDIS exploits the unique affordances of digital technology, by creating an environment in which the quality and the quantity of emotional display by the agents can be modulated to scaffold the young trainees through a diverse range of possible interview situations. The scenarios are co-designed with experienced practitioners in several European countries in order to ensure their relevance to the different individuals across a number of cultural contexts.

  TARDIS offers three major innovations. First, it will be able to detect in real-time user's emotions and social attitudes through voice and facial expression recognition, and to adapt the progress of the game and the behaviour virtual interlocutor’s behaviour to the individual users. Second, it will provide field practitioners with an intuitive authoring tool for designing appropriate interview scenarios and for setting agents’ behaviours without the help of computer scientists. Third, it will give practitioners a unique access to a systematic record of the specific difficulties that the users experience. This will offer new instruments for practitioners to measure individual's progress in emotion regulation and social skill acquisition, thus facilitating reflection on their own practice and enabling a more flexible and personalised coaching for young people at risk of social exclusion.

• Website : http://www.tardis-project.eu

SAGECE

• SAGECE: Simulation for Crisis Gestion and Formation
• Financial support: ANR/CSOSG project
• Period: 2 years (starts in march 2008)
• Partners: SOGITEC is the project coordinator. Other partners are UTC/Heudiasyc/UMR 6599, CEA-LIST, ECI univ. Paris Descartes, EADS, ENSOSP, EMI, IRSN, AREVA.
• UTC Team: Domitile Lourdeaux, Dominique Lenne, Indira Thouvenin, Jean-Paul-Barthès, Julien Saunier, Hazaël Jones, Margaux Lhommet
• Goal: The goal is to develop and to evaluate an interactive simulation tool in an NRBC (Nuclear, Radiological, Bacteriological AND Chemical) crisis in order to form security actors. Security actors will benefit of a realistic crisis exercice tool of an accidental situation. In the scene, virtual agents with autonomous behaviors and avatars will interact.

FisPro

FisPro (Fuzzy Inference System Professional) allows to create fuzzy inference systems and to use them for reasoning purposes, especially for simulating a physical or biological system. Fuzzy inference systems are briefly described in the fuzzy logic glossary given in the user documentation. They are based on fuzzy rules, which have a good capability for managing progressive phenomenons.
More about FisPro...

My work on FisPro

• Implicative fuzzy rules implementation: possibility distribution representation, computing functions for fuzzy implicative rules (intersection, sup-min composition, union, ...)
• Inference from fuzzy inputs with implicative rules: new methodology for inference and algorithm. More details can be found about this method in A practical inference method with several implicative gradual rules and a fuzzy input: one and two dimensions publié dans FuzzIEEE 2007
• Toolbox for results analyse (based on tag utilisation and semantic interpretation)