Visitez notre page

 

 

 

 

 

 


Nathalie Mejean

Nathalie Mejean
nathalie.mejean@inrae.fr

Recherche:

Ma recherche est au croisement des systèmes du vivant en agriculture et alimentation, des sciences cognitives et des méthodes d'ellicitation et de formalisation des savoirs par intelligence artificielle. Proposer, explorer avec les experts une représentation pour aider à la décision aux différentes échelles. Intégration des connaissances expertes et couplage à des méthodes d'apprentissage automatique.

My research is located at the interface of life science for agri-food systems, cognitive science and artificial intelligence. Propose, explore with the experts a representation for decision help, crossing over scales, is the challenge of my research. Computing tools are developed to enhance the interaction between the expert reasoning, his know-how and machine learning automatic process.

Mots clés:  expertise humaine et formalisation, outil digital, aide à la décision, intelligence artificielle, agriculture, procédés alimentaires, pâturage de troupeaux ovins

Keywords: Agri-Food systems, fuzzy logic, human expertise formalization, computing tools frameworks for experts and machine learning cooperation, digital tool for sheep pasture

Parcours:

  • IR Cemagref de 1998 à 2005
  • IR INRA de 2005 à 2010
  • DR INRAE depuis 2010 - et membre associée ISCPIF (Institut des Systèmes Complexes de Paris Ile de France)

Formation:

  • Ingénieure INSA Toulouse, 1993.
  • Docteure de l’ENSIA Massy (AgroParisTech) en Génie des Procédés Alimentaires (qualifiée section 61 et 62), 1997.
  • Habilitée à Diriger des recherches (thèse d’état) en Sciences Pour l’Ingénieur de l’université de Clermont Ferrand, 2004.

Des projets phares:

  • 2024-2026 et +: SERIOUSPAN outil digital pour aider le berger dans ses choix de trajectoires de pâture sur un territoire agricole avec couverts". Projet en étroite collaboration avec l'UMR SADAPT. Financements Métaprogramme INRAE XRISQUES et GS Biosphera Agro-écologie.
  • 2024-et+: FutureFoods European partnership for a sustainable Future of Food Systems. https://www.futurefoodspartnership.eu/
  • 2008-2012 : European collaborative project on food, fisheries and biotechnology. Montage et leader du WP "Mathematical knowledge integration for food models numeric simulation"
  • 2007-2010 : Montage et coordination du projet PNRA INCALIN (INtégration des Connaissances en ALImeNtaire). Application à des procédés traditionnels: affinage de fromage et fabrication du pain.

 

Quelques publications clés (*nom d'usage Perrot):

  1. Biosys-LiDeOGraM: A visual analytics framework for interactive modelling of multiscale biosystems. Nathalie Mejean Perrot, Severine Layec, Alberto Tonda, Nadia Boukhelifa, Fernanda Fonseca, Evelyne Lutton. doi: https://doi.org/10.1101/2023.06.23.54620913/09/23  Colloque Ferment’IA Nathalie Mejean

  2. Nathalie Mejean Perrot; Nathalie Mejean Perrot; Alberto Tonda; Ilaria Brunetti; Hervé Guillemin; Bruno Perret; Etienne Goulet; Laurence Guerin; Daniel Picque. (2022). A decision-support system to predict grape berry quality and wine potential for a Chenin vineyard. Computers and Electronics in Agriculture 2022-09 | Journal article DOI: 10.1016/j.compag.2022.107167  Part of ISSN: 0168-1699  

  3. Nathalie Mejean Perrot, Alberto Tonda, Nadia Boukhelifa, Ilaria Brunetti, Anastasia Bezerianos Evelyne Lutton (2022). Machine learning for agri-food processes: learning from data, human knowledge, and interactions, current developments in biotechnology and bioengineering 2022 | Book chapter | Part of ISBN: 9780323984836.
  4. Nadia Boukhelifa, Anastasia Bezerianos, Ioan Cristian Trelea, Nathalie Perrot, and Evelyne Lutton.“An Exploratory Study on Visual Exploration of Model Simulations by Multiple Types of Experts”. In: CHI 2019 The ACM CHI Conference on Human Factors in Computing Systems. Glasgow, United Kingdom, May 2019. doi: 10.1145/3290605. url: https://hal.inria.fr/hal-02005699

  5. Evelyne Lutton and Nathalie Perrot. “Human in the loop for modelling food and biological systems: a perspective based on Artificial Intelligence”. In: FOODSIM’2018. Ghent, Belgium, Apr. 2018. url: https://hal.inrae.fr/hal-02786708.
  6. Roche, A., Perrot, N., Chabin, T., Villiere, A., Symoneaux, R., Thomas-Danguin, T. (2017), In silico modelling to predict the odor profile of food from its molecular composition using experts' knowledge, fuzzy logic and optimization: Application on wines, 2017 ISOCS/IEEE International Symposium on Olfaction and Electronic Nose (ISOEN), Montreal, QC, 2017, pp. 1-3. doi: 10.1109/ISOEN.2017.7968875.
  7. Perrot, N., De Vries, H., Lutton, E., Van Mil, H.G.J., Donner, M., Tonda, A., Martin, S., alvarez, A., Bourgine, P., van der Linden, E. Axelos, M. (2016). Some remarks on computational approaches towards sustainable complex agri-food systems. Trends in Food Science and Technology, 48, 88-101.
  8. Van Mil, H.G.J., Foegeding, A.E. , Windhab, E.J. , Perrot, N., Van der Linden, E. (2014). A complex system approach to address world challenges in food and agriculture. Trends in Food Science and Technology, 40 (1), 20-32.
  9. Lutton, E., Tonda, A., Gaucel, S. Riaublanc, A., Perrot, N. (2014) Food model exploration through evolutionary optimisation coupled with visualisation: application to the prediction of a milk gel structure. Innovative Food Science and Emerging Technologies, 25, 67-77.
  10. Perrot, N., Baudrit, C., Brousset, J.M., Abbal, P., Guillemin, H., Perret, B., Goulet, E., Guerin, L., Barbeau, G., Picque, D. (2015). A Decision Support System Coupling Fuzzy Logic and Probabilistic Graphical Approaches for the Agri-Food Industry: Prediction of Grape Berry Maturity. PlosOne, 10(7). 10.1371/journal.pone.0134373.
  11. Sicard, M., Perrot, N., Reuillon, R., Mesmoudi, S., Alvarez, I., Martin, S. (2012) A viability approach to control food processes: Application to a Camembert cheese ripening process. Food Control, 23, 312-319.
  12. Perrot, N., Baudrit, C., Trelea, I.C., Trystram, G., Bourgine, P. (2011). Modelling and analysis of complex food systems: state of the art and new trends. Trends in Food Science and Technology, 22(6), 304-314.
  13. Baudrit, C., Sicard, M., Wuillemin, P.H., Perrot N. (2010). Towards a global modelling of the Camembert-type cheese ripening process by coupling heterogeneous knowledge with dynamic Bayesian networks, Journal of Food Engineering, 98 (3), 283-293.
  14. Barrière, O., Lutton, E., Baudrit, C., Sicard, M., Pinaud B., Perrot, N. (2008). Modeling Human Expertise on a Cheese Ripening Industrial Process Using GP. Lecture Notes in Computer Science, Parallel Problem Solving from Nature – PPSNX , Springer Berlin/Heidelberg (Eds). Vol 5199, pp. 859-868.
  15. Allais, I., Perrot, N., Curt, C., Trystram, G., (2007) Modelling the operator know-how to control sensory quality in traditional processes. Journal of Food engineering. 83 (2): 156-166.
  16. Perrot, N. (2006). Fuzzy concepts applied to food product quality control. Editorial. Fuzzy Sets and Systems, 157, 1143-1144. Special edition.

 

Publications