Data Mining, Machine Learning
a data science research group

Stay in touch

Follow @LirisDM2L

International fundings and projects FP7

GRAISearch EU FP7 - Call FP7-PEOPLE-2013-IAPP - Marie Curie
Use of Graphics Rendering and Artificial Intelligence for Improved Mobile Search Capabilities (2014-2018)

GRAISearch is an Industry-Academia Partnerships and Pathways project (IAPP) aiming at transferring knowledge from Academia to Industries. It is also a support for training and career development of researchers (Marie Curie). A Web startup, Tapastreet Ltd, as well as two academic institutions, INSA de Lyon (LIRIS UMR CNRS 5205) and Trinity College Dublin (TCD) for their knwoledge resp. in Data science & Vizualization, are involved. The goal is to transfer recent technologies from research on video summarization, 3D scene reconstruction, data mining and event detection from social media, into the products of Tapastreet LTD. Transfert is made also via 20 months mobilities between any pairs of the three partners.

View Project
Integrate EU FP7
Integrated Solutions for Agile Manufacturing in High-mix Semiconductor Fabs (2013-2015)

This projects involves 28 european partners and leaded by STMicroelectronics. Our DM2L team is involved in WP5 "Data Analysis and Yield". Maintaining cost decrease per function, reducing cycle times, improving reproducibility and equipment effectiveness while reducing the environmental impact of the factories are key challenges to be addressed to keep the competitiveness of European SC manufacturers. The INTEGRATE project aims to enhance European semiconductor fabs efficiency by providing methods and tools to better control the process variability, reduce the cycle time and enhance the effectiveness of the production equipment.

View Project
Mold4prodE EU FP7 - NMP - SME
Intelligent Molds for Productivity Enhancement (2011 - 2013)

Our DM2L team is involved in WP2 "Data driven-modelling of polymer injection molding process". Mold4prodE aims to develop and assess a method which will give tool makers the opportunity to design and deliver more quickly "turn key intelligent" tools to end users. The project comprises 24 partners, including SMEs, RTDs and other enterprises from the European union.

View Project

National fundings and projects ANR, FUI, ...

Comment reconstituer l’HIstoire des Réseaux d’assainissement et d’EAU potable – application sur le territoire de la Métropole de Lyon
Drinking and wastewater networks have been constructed more than a century ago. They have been built for and by the city. Today or tomorrow, such assets will have to be manage in order to maintain the performance on the sort, medium or long term. Installation date of pipes is one of the major information that needed to be known in order to shift from run-to-failure to proactive management, by predicting the condition of pipes that haven’t been investigated. However, such information is often missing and its reliability is questioned. The HIREAU research project aims to: demonstrate that it is feasible to reconstitute the missing installation date of pipes, provide utilities with operational methods to reconstitute such data, improve the knowledge of the history of cities and their networks. HIREAU started in November 2016 for three years and will investigated three different approaches: learning methods in order to predict installation date based on characteristics of the pipes and its environment, consultation of city archives in order to gather data on the existing pipes, in-situ investigations to determine the installation date of a pipe.

View Project
Nano2017Gouvernement français
Détection préventive des défauts et identification des causes (2014-2017)

A new R&D program in the sector of semi-conductors of 3,5 billions euros, financed by the French Government. The DM2L team works in a sub-project called Détection préventive des défauts et identification des causes with STMicroelectronics, LIG and ProbaYES.

View Project
Automated Self-service Bike Share Schemes. A Socio-Technical Innovation and its Social Appropriations (2013-2016)

The study of the Bicycle Sharing System of Lyon called Vélo'v and its social appropriation. Its objectives are to characterize Vélo'v as an evolving socio-technical system and to model it. In collaboration with ENS de Lyon, LET, JD Decaux cyclocity.

View Project
Tracaverre FUI APP 2014

More info soon.


This an energy-oriented research and development (R&D) project for the benefit of French plants. The goal is to deploy existing knowledge and new technological tools to assist industry in implementing more energy efficient technologies. We examine industrial energy consumption and identify energy recovery opportunities by analysing the data collected by multiple sensors. Partners : Automatique et Industrie, Probayes, LIRIS, NTN-SNR Roulements..

Fouille de données Spatio-Temporelles: application à la compréhension et à la surveillance de l'ERosion (2011-2014)

These last years, the increasing amount of geosciences data have lead to new promising applications. For example, the use of very high resolution satellite images now enables the observation of small objects. However, actual data analysis techniques suffer from the huge amount of complex data to process. Indeed, this environmental data is often heterogeneous, multi-scale, incomplete, and composed of complex objects. In this context, this computer science project aims at providing to geologists a semi-automatic and complete process for monitoring soil erosion.

View Project

Regional fundings and projects

Smart & Open-source Pattern Recognition Algorithm for Neural Oscillations (2015/2016)

Le rôle des états de vigilance dans la physiopathologie de la mémoire est une thématique majeure des neurosciences. Pour y répondre, il est indispensable de combiner des enregistrements intracérébraux multiples, avec d'autres paramètres comportementaux ou physiologiques durant les différents états de vigilance. L'analyse de ces données hétérogènes pose toutefois certains problèmes méthodologiques. Des approches de traitement des données et de classification ont été développées, en particulier au CRNL. Celles-ci reposent cependant sur l’analyse d’un nombre très limité de signaux, et étaient jusque là inadaptées à la problématique des 'Big Data', récente en neurosciences. Le LIRIS a développé récemment de nouvelles méthodes qui s’inspirent de la théorie spectrale des graphes et de modèles ensemblistes. Ces techniques ont été validées sur des données réelles de très grandes dimensions et pourraient être adaptées aux gros volumes de données cérébrales multidimensionnelles. Ces nouvelles approches de traitement des données sont non seulement essentielles pour comprendre le rôle cognitif des états de vigilance, mais aussi pour aider au diagnostic de nombreuses maladies neuropsychiatriques.Partenaires : DM2L (LIRIS) et l'Equipe Sleep (CRNL)

Olfamining LIRIS Transdiciplinary fundings (5000€) - MI CNRS DEFISENS (3000€)
Linking molecules to their odors with supervised descriptive rules discovery (2013-2015)

While it is generally agreed that the physicochemical characteristics of odorants affect the olfactory percept, no precise rules governing this 'chemical structure / odor' relation have yet been determined. One obstacle to this is the large number of dimensions – several thousand – needed to describe the molecules and, above all, a lack of data-processing methods suitable for this level of complexity. Our first objective will therefore make use of the 3 data-bases established as part of the Prevalolf project, correlating the multiple molecular characteristics (olfactory chemical space) to olfactory qualities (fruity, floral, woody, etc.: odor perception space). Methods taken from data mining producing descriptive rules are used to test the hypothesis that certain olfactory qualities, on which there is strong inter-subject agreement, can be predicted from the physicochemical properties of the odorant molecule. This project is executed with two groups of the LIRIS lab (DM2L and database group) as well as a CNRS laboratory in neursciences (CNRL).

View Project
Modélisation dynamique des flux de Velo’v ARC6
Rhône Alpes region PhD scholarship (2012-2015)

Ronan Hamon is funded by the Region for preparing his PhD, studying the usage of the bike renting system Vélo'v in Lyon (Grand Lyon, JC-Decaux Cyclocity). Modeling the bike usage streams as dynamic attributed graphs, the goal is to understand the dynamics of the 7 millions bike rides that occurred in Lyon in 2011..

Past Projects



Regional and local