| Home page | Publications | Projects | Software | Dissemination | Collaborations |
- Bayes Duality project (2021-2026) I am involved in this project launched with a funding of $2.76 millions by Japan JST - French ANR for a total of 5 years starting in October 2021. The goal is to develop a new learning paradigm for Artificial Intelligence that learns like humans in an adaptive, robust, and continuous fashion. On the Japan side the project is led by Mohammad Emtiyaz Khan as the research director, and Kenichi Bannai and Rio Yokota as the two Co-PIs. On the French side the project is led by Julyan Arbel. Project website.
- QFunc project (2020-2023) I am involved in this ANR/NSF France/USA project founded for 4 years. It is coordinated by Sophie Achard and involves Statify, Grenoble Institute of Neurosciences and University of California Santa-Barbara. The goal is to study spatiotemporal statistical models for quantification and estimation of functional connectivity. A workshop on brain connectivity has been organized in this context. More details on the workshop website.
- Radio-Aid project (2022-2026) I am involved in this ANR project entitled Radio-Aid for "Radiation induced neurotoxicity assessed by ST modeling and AI after brain radiotherapy" coordinated by S.Ancelet from IRSN has been granted for 4 years starting in April 2022. It involves Statify, Grenoble Insitute of Neurosciences, Pixyl, ICANS (Strasbourg), APHP, ICM and ENS P.Saclay.
- Road-AI project (2021-2025) I am involved in this national Inria project with Cerema and granted for 4 years starting in October 2021. The goal is to develop advanced data analysis tools for diagnosing and monitoring road and road-related infrastructures. The Inria teams involved are FUN, Modal, Statify, Titane, Acentauri and Coati. On the Cerema side, Statify will mainly work with the ENDSUM team. More information on this website.
- European H2020 RESSTORE (2015-2018) I am involved in this multi-center Stroke European H2020 project including 20 partners. led by Dr. Olivier Detante (Grenoble CHU). I will contribute through the Pixyl startup. RESSTORE stands for REgenerative Stem cell therapy for STroke in Europe. It is part of Clinical research on regenerative medicine program. It will involve a phase 2 trial with 300 patients imaged at 4 time points over a 3 year timeframe. Pixyl will provide automatic stroke lesion segmentations.
- VHIA ERC project (2015-19) I am involved in R. Horaud's ERC advanced Grant entitled Vision and Hearing In Action. VHIA studies the fundamentals of audio-visual perception for human-robot interaction.
- FUI VISION 4.0 (in short VI4.2): Industry 4.0, AI and the PCB industry (2016-2019). Vision 4.0 (in short Vi4.2) is one of the 8 projects labeled by Minalogic, the digital technology competitiveness cluster in Auvergne-Rhone-Alpes, that has been selected for the Industry 4.0 topic in 2016, as part of the 22nd call for projects of the FUI-Regions. This 3 year project is coordinated by VI Technology, a world leader in Automated Optical Inspection (AOI) of a broad range of electronic components. The other partners are the G-Scop Laboratory in Grenoble, ACTIA company based in Toulouse and Mistis, for a total budget of 3,4 Meuros. Today, in the printed circuits boards (PCB) assembly industry, the assembly of electronic cards is a succession of ultra automated steps. Manufacturers, in constant quest for productivity, face sensitive and complex adjustments to reach ever higher levels of quality. Project VI4.2 proposes to build an innovative software solution to facilitate these adjustments, from images and measures obtained in automatic optical inspection (AOI). The idea is - from a centralized station for all the assembly line devices - to analyze and model the defects finely, to adjust each automatic machine, and to configure the interconnection logic between them to improve the quality. Transmitted information is essentially of statistical nature and the role of the Mistis team is to identify which statistical methods might be useful to exploit at best the large amount of data registered by AOI machines. Preliminary experiments and results on the Solder Paste Inspection (SPI) step, at the beginning of the assembly line, helped determining candidate variables and measurements to identify future defects and to discriminate between them. More generally, the idea is to analyze two databases at both ends (SPI and Component Inspection) of the assembly process so as to improve our understanding of interactions in the assembly process, find out correlations between defects and physical measures and generate accordingly proactive alarms so as to detect as early as possible departures from normality.
- NeuroCoG, 2017- 2020 The NeuroCog project aims at understanding the biological, neurophysiological and functional bases of behavioral and cognitive processes in normal and pathological conditions, from cells to networks and from individual to social cognition. No decisive progress can be achieved in this area without an aspiring interdisciplinary approach. The interdisciplinary ambition of NeuroCoG is particularly strong, bringing together the best scientists, engineers and clinicians at the crossroads of experimental and life sciences, human and social sciences and information and communication sciences, to answer major questions on the workings of the brain and of cognition. One of the work package entitled InnobioPark is dedicated to Parkinson's Disease. The PhD thesis of Veronica Munoz Ramirez that I coadvised is one of the three PhDs in this work package.
- Data@UGA, 2017-2020 The Grenoble Alpes Data Institute aims at undertaking groundbreaking interdisciplinary research focusing on how data change science and society. It combines three fields of data-related research in a unique way: data science applied to spatial and environmental sciences, biology, and health sciences; data-driven research as a major tool in Social Sciences and Humanities; and studies about data governance, security and the protection of data and privacy. I am co-head of one of the 5 workpackage, WP2 Data Science for life sciences. In addition, a 2-years multi-disciplinary projects was granted in November 2017 in collaboration with IPAG and Univ. Paris Sud Orsay (Regression techniques for Massive Mars hyperspectral image analysis from physical model inversion).
- WIFUZ: Wireless multi sensor Fusion (2015-2017). I am the principal investigator for MISTIS of WIFUZ on WIreless multi sensors FUSion. This 2 year project is supported by DGA and led by the ACOEM company and involves another company, the HIKOB startup. The objective is to develop a prototype for surveillance and monitoring that is able to combine multi sensor data coming from acoustic sensors (microphones or antennas) and optical sensors (infrared cameras) and to distribute the processing to multiple algorithmic blocs.
- Persyvact and Persyvact2 (2015-2019) These Actions are supported by the Persyval Labex for 3.5 years. Persyvact2 is a follow-up of the Persyvact Exploratory labex project. Persyvact and Persyvact2 consist of about 20 researchers from different laboratories, GIPSA-lab, LJK and TIMC-IMAG and different fields related to data science.
- MultiPlanNet (2015-2017) This is a 2-year project to build a network for the analysis and fusion of multimodal data from planetology. There are 8 partners: IRCCYN Nantes, GIPSA-lab Grenoble, IPAG, Grenoble, CEA Saclay, UPS Toulouse, LGL Lyon1, GEOPS University Orsay. A two day workshop was organized in November 2017 in Grenoble, on the analysis of multimodal data for planets observation and exploration.
- CIFRE PhD with SCHNEIDER (2015-2018)I am the main advisor of a starting CIFRE PhD (T. Rahier) with Schneider Electric. The others advisors are S. Marie (Schneider) and S. Girard (MISTIS). The goal is to develop specific data mining techniques able to merge and to take advantage of both structured and unstructured (meta)data collected by a wide variety of Schneider Electric sensors to improve the quality of insights that can be produced.
- PIXYL (2017) I am involved in a collaboration with the Pixyl strat-up for the valorization of techniques for brain MRI segmentation.
- UAC XEROX INDIA (2015-2016) I am co-principal investigator with R. Horaud (PERCEPTION) of a Xerox Foundation University Affairs Committee (UAC) collaborative grant to work on Advanced and Scalable Graph Signal Processing Techniques, in collaboration with Arijit Biswas and Anirban Mondal, research scientists at Xerox Research Center India (XRCI) Bangalore. We plan to investigate robust mixture models and techniques to deal with graphical data.
- HUMAVIPS: Humanoids with auditory and visual abilities in populated spaces (2010-13). I was the principal investigator for Mistis of a three-year European project (STREP) started in February 2010. The project was named HUMAVIPS (Humanoids ables with auditory and visual abilities in populated spaces) and was in 2009/10 the only INRIA coordinated project granted in the highly competitive FP7-ICT program of the European Union. The partners involved were team Perception and Mistis from INRIA Rhone-alpes (coord.), the Czech Technical University CTU Czech Republic, Aldebaran Robotics ALD France, Idiap Research Institute Switzerland and Bielefeld University BIU Germany. The goal was to develop humanoid robots with integrated audio-visual perception systems and social skills, capable of handling multi-party conversations and interactions with people in realtime. My contribution consisted in developing statistical machine learning techniques for interactive robotic applications. More details on the project [web site].
- POP (Perception On Purpose, 2006-09), European STREP FP6. I was the principal investigator for Mistis of the POP European STREP (Perception On Purpose) coordinated by INRIA and involving teams Mistis and Perception. The other partners involved were the University of Sheffield, UK, University of Osnabr?ck, University Hospital Hamburg-Eppendorf in Germany and University of Coimbra in Portugal. The objective was to put forward the modelling of perception (visual and auditory) as a complex attentional mechanism that embodies a decision taking process. The part I had in charge included the PhD work of Vasil Kalidhov and Ramya Narasimha. Our contribution was to the development of theoretical and algorithmic models based on probabilistic and statistical modelling of both the input and the processed data. The final review of the project was held on December 11 and 12, 2008 with in particular a live demo running on the POP audio-visual head regarding multispeaker localisation using the algorithm we developed (Khalidov, Forbes and Horaud 2011). Further details on the project web site [Link].
- I-VP: Intuitive Vision Programming (MINALOGIC), 2009-2012. Since October 2009, I was the principal investigator for Mistis of the three-year Pole de competitivite Minalogic project I-VP (for Intuitive Vision Programming) supported by the French government. On the industrial part, the project was led by VI Technology, a world leader in Automated Optical Inspection (AOI) of a broad range of electronic components. The other partners involved were the CMM (Centre de Morphologie Mathematiques) in Fontainebleau, and Pige Electronique in Bourg-Les-Valence. The NOESIS company, which was a leader in the field of image processing and analysis software, in Crolles, was also involved to provide help with software development. The overall goal was to exploit more intensively statistical and image processing techniques to improve defect detection capability and programming time based on existing AOI principles so as to reach eventually a reliable defect detection with virtually zero programming skills and efforts.
- Optimyst II (2009-12). I was the principal investigator for Mistis of this three-year Pole de competitivite Minalogic project through a collaboration with CEA - LETI addressing variability issues when designing electronic devices. The partners involved were University Joseph Fourier (LJK), CEA-LETI, and Raise Partner, ASYGN and Dolphin Integration companies.
- Vahiné (2008-10), ANR MDCO (Masse de Données et Connaissances). I was the principal investigator for Mistis of this three-year project called "Visualisation et analyse d'images hyperspectrales multidimensionnelles en Astrophysique" (VAHINE), in the MDCO (Masse de Données et Connaissances) program. It aims at developing physical as well as mathematical models, algorithms, and software able to deal efficiently with hyperspectral multi-angle data but also with any other kind of large hyperspectral dataset (astronomical or experimental). It involves the Laboratoire de Planétologie (LPG) de Grenoble, the Gipsa-lab, Observatoire de la Cote d'Azur (Nice), and University Strasbourg I. I initiated this collaboration and I was in charge of coordinating the Mistis activities which involves an 18 months post-doctoral fellowship. [Link].
- ACI Movistar (2003-06), "masse de données" program, I was the principal investigator for Mistis of this three-year project (Action Concertee Incitative Masses de donnees) involving other partners, Lear team from INRIA, SMS from University Joseph Fourier and Heudiasyc from UTC, Compiegne. I initiated this project which aimed at investigating visual and statistical models for image recognition and description and learning techniques for the management of large image databases. The PhD work of Juliette Blanchet and Charles Bouveyron were related to this project.[link].
- The HEROES project (2013-14). I was the scientific coordinator of this project entitled HEROES for ''HEmodynamics-infoRmed atlas of brain functiOnal and vascular territoriES from multimodal MR images". Based on the information obtained from the combination of different MR modalities for a group of healthy subjects, the goal was to build an atlas of functional and vascular territories with homogeneous hemodynamic properties to address clinical questions (Stroke and Alzheimer). This project gathered three INRIA teams (MISTIS, PARIETAL and VISAGES), CEA NeuroSpin and GIN (Grenoble Institute of Neuroscience).
- The AINSI project (2011-12), [Link]. I was the scientific coordinator of the 2-year ARC project AINSI supported by INRIA. AINSI stands for "Modeles statistiques pour l'Assimilation d'Informations de Neuroimagerie fonctionnelle et de perfuSIon cerebrale". The goal was to propose an innovative statistically well-based solution to the joint determination of neural activity and brain vascularization by combining BOLD constrast images obtained in functional MRI and quantitative parametric images (Arterial Spin Labelling: ASL). The partners involved were Visages team from INRIA in Rennes, the INSERM Unit U594 (Grenoble Institute of Neuroscience) and the LNAO laboratory from CEA NeuroSpin.
- SeLMIC, ARC INRIA (2007-08). I was the scientific coordinator of the 2-year ARC project SeLMIC supported by INRIA, [Link]. SeLMIC stands for "Segmentation Longitudinale et multimodale par IRM d'anormalites cerebrales". It aimed at developing new statistical methods for the segmentation of multidimensional MR sequences corresponding to different types of MRI modalities and longitudinal data. The applications included the detection of brain abnormalities and more specifically strokes and Multiple Sclerosis lesions. The partners involved were team Visages from INRIA in Rennes, the INSERM Unit U594 (Grenoble Institute of Neuroscience) and Laboratoire d'Informatique de Grenoble (LIG).
- ChromoNet, ARC INRIA (2007-08), [Link], for Computational Analysis of Inter-Chromosomal Interaction Networks. I was the principal investigator for Mistis of this project that was coordinated by Marie-France Sagot from former team Helix. It aimed at the computational inference and analysis of inter-chromosomal interaction networks. The additional partners were the SSB (Statistiques des Séquences Biologiques) group at INRA and the Nuclear Organisation team at MRC, Imperial College London.
- IBN (Integrated Biological Networks), ARC INRIA (2005-06), for Integrated Biological Networks. I was the principal investigator for Mistis of this project that was coordinated by Marie-France Sagot from former INRIA team Helix. Its main objective was to analyse the links between regulation, organisation and evolution of genomes and biological networks. The other partners included two other INRIA teams (Helix and Symbiose), Pasteur Institute and INRA, Jouy-en-Josas.
- Labex Persyvact Exploratory project (2013-2015). I initiated with O. Francois (TIMC) the Persyvact Exploratory project whose road map was widely inspired by the MISTIS directions of research. The main goal was to build collaborations between different laboratories in the Grenoble area around the development of tools for analyzing hierarchically structured models for high dimensional complex data.
- The LOCUS project (2011-12). I was the scientific coordinator of the 18-month LOCUS project supported by [GRAVIT] which stands for "Grenoble Alpes Valorisation Innovation Technologies". The project was focused on the development of the LOCUS software for industrial transfer.
- Biomerieux, Grenoble, 2008. On the statistical analysis of a quantification process.
- Veolia-eau, Lyon, 2008. The goal was to study and possibly detect groups of individuals in time series describing various quantities linked to water consumption and billing in the Lyon area.
- HEMERA, Grenoble, 2014. I was contacted by the HEMERA company for a contract including the internships of A. Charlier and L. Qianru. %Hemera designs, produces and sells online liquid and gaz analyzers. The aim of HEMERA was to measure, in any gaseous or liquid environment, with a minimized environmental impact and in a selective way, all compounds seen nowadays as pollutants. HEMERA's analyzers measure gaz concentrations using optical techniques. The goal of the collaboration was to investigate the use of statistical methods to improve both the determination of the present gaz and their respective concentrations from the analysis of spectra representing a mixture of the different gaz.