Section: Contracts and Grants with Industry
Grants with Industry
EPIA: a RNTL Project (2003-2007)
Inria Contract Reference: S04 AO485 00 SOPML00 1
The EPIA project “Evolution of an Adaptive Information Portal” got labeled by RNTL 2002, was started on September 2003 and completed in june 2007. Partners are Dalkia, Ever(Mediapps) and Inria.
The objectives of this pre-competitive project is to use clustering methods for usage analysis [Oops!] and to use collaborative filtering to help intranet users to access information inside a large portal. After understanding the user needs for Net.Portal (construction tool for intranet portals), we finalized this year the specification of the NetPortal trace engine (cf. the deliverable D3 [Oops!] , [Oops!] ). The solution for the user interface lay-out and dynamics of a recommender system called Net.CanalRecommender was defined from the study of several alternatives (pull-down, menu bar, tabs) and the trade-off was chosen according to ergonomics criterias. In order set up an experiment, few usage scenarios were set up [Oops!] and a simple one was used for a demonstration of the recommender which suggests documents selected by people in previous sessions. The system [Oops!] combines in an original way users profiles and navigations similarities to improve documents. An evaluation plan with evaluation criterias and a query about user satisfaction have been defined but no real users were available to conduct an evaluation.
MobiVIP: a PREDIT Project (2004-2007)
Inria Contract Reference: 2 03 A2005 00 00MP5 01 1
MobiVIP, Individual Public Vehicles for Mobility in town centers, is a research project of Predit 3 (Integration of the Communication and Information systems Group). It involved five research laboratories and seven small business companies (SME), in order to experiment, show and evaluate the impact of the NTIC on a new service for mobility in town centers. This service is made up of small urban vehicles completing existing public transportation. The MobiVIP project has developped key technological bricks for the integrated deployment of mobility services in urban environment. The strengths of the project are:
the integration between assisted and automatic control, telecommunications, transportation modeling, evaluation of service;
the demonstrations on five complementary experimental sites;
the evaluation of possible technology transfer.
The MobiVIP Project has ended in June 2006 for most of the partners but has been extended up to June 2007 for AxIS and some others partners [Oops!] . In this project, our team has been in charge of the evaluation module and this continuation has allowed us to process real usage data of electrical vehicules in Antibes. Our data mining and classification tools have been used to set up a structured methodology of mobility logs analysis linking usage data in a complete processing chain from vehicule reservation up to trip destination.
This year we had two main tasks: the work related to the task 5.4 and the VU Log experimentation. In task 5.4 we proposed methodological tools to analyse profiles in a mobility context and to classify trip dataset coming from surveys and from simulated vehicule usage [Oops!] . Our classifications tools were used in relation with cartographic visualization to provide a better understanding of urban mobility. In this task we also realized a review of spatial cognition studies in order to apply their results in the design and evaluation of travellers information systems [Oops!] In task 5.5. [Oops!] the experimentation was conducted in collaboration with the company VU Log who provides services for urban mobility in Antibes: subscribers can use electrical vehicules for short trips around the town center. We first provided a technical assistance to the company in several pre-tests with users (potential customers) in order to understand their perception of the services and the way they would use them. Two analysis of real usage dataset were then conducted : the first one concerned the usage of a vocal server and showed very good technical performances of the system and a variety of usage patterns; the second focused on vehicules usage. The detailed analysis described in D5.1 (decomposition trip structure from vehicule reservation to arrival at destination) and D5.2. (evaluation criterias) were used to specified the dataset to record. Then, vizualisation tools were used in relation with classification tools to provide insight of pattern usages. The results revealed special usage patterns corresponding to specific situations knowned by VU Log team. The company has a strong demand for further analysis as it is convinced that usage mining is the key for quality in future mobility services. A complex process including several free software (QGis, Grass) in different environments (Windows, Linux) has been used to map trip data and visualization tools and a user'manual has been written [Oops!] .
Eiffel “E-tourism and Semantic Web”: a RNTL Project (2006-2009)
Inria Contract Reference: 105D1499 00 21173 01 0
The EIFFEL project related to semantic web and e-Tourism was labelled in 2006 by the RNTL program and started this year. Industrial partners are Mondeca and Antidot (leadership) and academic partners are LIRMM and University of Paris X (Nanterre).
The main goal of the Eiffel project is to provide users with an intelligent and multilingual semantic search engine dedicated to the tourism domain. This solution should allow tourism operators and local territories to highlight their resources; the end users will then use a specialised research tool allowing them to organize their trip on the basis of contextualised, specialised, organised and filtered information. Queries and results will be guided by user profiles extracted from usage analysis. These profiles will facilitate the access to distributed and highly heterogeneous data. In this project, AxIS is in charge of the sub-package SP8 and will define new paradigms dedicated to knowledge searching and visualizing, and will extract and exploit users' models and profiles from web logs. A first deliverable (june 2007) concerns the user interface specification for knowledge searching [Oops!] , [Oops!] . We are working on the user model definition to represent and store the most relevant characteristics of the user [Oops!] . We investigate the use of ontologies in modelling not only the user's preferences but also his global context (time, place, material, history, etc). Our objective is to automatically adapt the content and structure, based on information contained in the user profile. This information is obtained either explicitly or implicitly. AxIs strongly collaborated with Bénédicte Le Grand and Michel Soto from LIP6.
Others actions with Industry
Two new grants with industry were accepted and will start in 2008:
the “MIDAS” project in response to the ANR's call for proposals on “Masses de Données / Connaissances Ambiantes” has been accepted. MIDAS ( MIning DAta Streams ) will gather together 5 academic partners: AxIS, ENST (Paris), LIRMM (Montpellier), LGI2P (Nimes), GRIMAAG (Martinique); and two industrial partners: EDF R&D and France Télécom R&D.
The “Intermed” project in resposne to the ANR's TechLOg call for proposals has been accepted. The Intermed kick-off meeting previously planned in december 2007 has been delayed to 2008. Academic partners are Cemagref (G-EAU et TETIS) LIRMM, CEPEL and industrial partners are SCRIPTAL, SIRENA, Normind, PIKKO. The aim of the InterMed project is to design and implement a substructure of tools fitting the requirements of users in charge of territory planning. The goal is to use appropriate technologies to establish a functionnal link between citizen and local authorities. The technologies we are looking for will be progressively adapted to deal with human factors and constraints of the "field". The proposed experimental approach will rely on several iterations and active participation of people involved in the discussions.
We had different industrial contacts during this year:
VU Log, startup offering software and services dedicated to urban mobility (located in Antibes). Support for an experimentation with a small electric urban vehicule (speed limited to 45 km/h).
Agglomeration Community of Antibes Sophia Antipolis (CASA). A previous successfull collaboration during the MobiVIP project (See Delivrable 5.3. [Oops!] gave opportunity for further work. We had several metting with the CASA transportation team to plan a cooperation and a usage analysis of a Web site dedicated to car-sharing will probably be engaged.
Zetoo: AxIS participated to a meeting organised by valorization board of Inria to discuss an Alcatel' project about e-commerce and social networks.
Morocco Telecom: The exchanges with Morocco Telecom, Casablanca University and ENSAM (Meknes) about the WRUM proposal (redesign methology based on site usage mining) were extended this year and have are not yet resulted in effective cooperation.
SAP, Sophia Antipolis related to data mining and data streams (security and environnement problems) in relation with Marascu's PhD thesis. Contact: B. Trousse and F. Masseglia
DENSO Research: Mr Sazaki asked for a presentation of AxIS'expertise while visiting INRIA.