Search

Your search keyword '"Poli, Jean-Philippe"' showing total 113 results
Start Over Author "Poli, Jean-Philippe"
113 results on '"Poli, Jean-Philippe"'

1. DiffGuard: Text-Based Safety Checker for Diffusion Models

Author

Khader, Massine El, Bouzidi, Elias Al, Oumida, Abdellah, Sbaihi, Mohammed, Binard, Eliott, Poli, Jean-Philippe, Ouerdane, Wassila, Addad, Boussad, and Kapusta, Katarzyna

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence
Abstract

Recent advances in Diffusion Models have enabled the generation of images from text, with powerful closed-source models like DALL-E and Midjourney leading the way. However, open-source alternatives, such as StabilityAI's Stable Diffusion, offer comparable capabilities. These open-source models, hosted on Hugging Face, come equipped with ethical filter protections designed to prevent the generation of explicit images. This paper reveals first their limitations and then presents a novel text-based safety filter that outperforms existing solutions. Our research is driven by the critical need to address the misuse of AI-generated content, especially in the context of information warfare. DiffGuard enhances filtering efficacy, achieving a performance that surpasses the best existing filters by over 14%.

Published
2024

3. Causal discovery for time series with constraint-based model and PMIME measure

Author

Arsac, Antonin, Lomet, Aurore, and Poli, Jean-Philippe

Subjects
Statistics - Methodology, Computer Science - Information Theory, Computer Science - Machine Learning
Abstract

Causality defines the relationship between cause and effect. In multivariate time series field, this notion allows to characterize the links between several time series considering temporal lags. These phenomena are particularly important in medicine to analyze the effect of a drug for example, in manufacturing to detect the causes of an anomaly in a complex system or in social sciences... Most of the time, studying these complex systems is made through correlation only. But correlation can lead to spurious relationships. To circumvent this problem, we present in this paper a novel approach for discovering causality in time series data that combines a causal discovery algorithm with an information theoretic-based measure. Hence the proposed method allows inferring both linear and non-linear relationships and building the underlying causal graph. We evaluate the performance of our approach on several simulated data sets, showing promising results.

Published
2023

4. Towards an Interpretable Fuzzy Approach to Experimental Design

Author

Rousselle, Olivier, Poli, Jean-Philippe, Abdallah, Nadia Ben, Kacprzyk, Janusz, Series Editor, Gomide, Fernando, Advisory Editor, Kaynak, Okyay, Advisory Editor, Liu, Derong, Advisory Editor, Pedrycz, Witold, Advisory Editor, Polycarpou, Marios M., Advisory Editor, Rudas, Imre J., Advisory Editor, Wang, Jun, Advisory Editor, Lesot, Marie-Jeanne, editor, Vieira, Susana, editor, Reformat, Marek Z., editor, Carvalho, João Paulo, editor, Batista, Fernando, editor, Bouchon-Meunier, Bernadette, editor, and Yager, Ronald R., editor

Published
2024
Full Text
View/download PDF

5. A New Approach for Explainable Multiple Organ Annotation with Few Data

Author

Pierrard, Régis, Poli, Jean-Philippe, and Hudelot, Céline

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Image and Video Processing
Abstract

Despite the recent successes of deep learning, such models are still far from some human abilities like learning from few examples, reasoning and explaining decisions. In this paper, we focus on organ annotation in medical images and we introduce a reasoning framework that is based on learning fuzzy relations on a small dataset for generating explanations. Given a catalogue of relations, it efficiently induces the most relevant relations and combines them for building constraints in order to both solve the organ annotation task and generate explanations. We test our approach on a publicly available dataset of medical images where several organs are already segmented. A demonstration of our model is proposed with an example of explained annotations. It was trained on a small training set containing as few as a couple of examples.

Published
2019

6. Embedded Constrained Feature Construction for High-Energy Physics Data Classification

Author

Cherrier, Noëlie, Defurne, Maxime, Poli, Jean-Philippe, and Sabatié, Franck

Subjects
Computer Science - Machine Learning, Statistics - Machine Learning
Abstract

Before any publication, data analysis of high-energy physics experiments must be validated. This validation is granted only if a perfect understanding of the data and the analysis process is demonstrated. Therefore, physicists prefer using transparent machine learning algorithms whose performances highly rely on the suitability of the provided input features. To transform the feature space, feature construction aims at automatically generating new relevant features. Whereas most of previous works in this area perform the feature construction prior to the model training, we propose here a general framework to embed a feature construction technique adapted to the constraints of high-energy physics in the induction of tree-based models. Experiments on two high-energy physics datasets confirm that a significant gain is obtained on the classification scores, while limiting the number of built features. Since the features are built to be interpretable, the whole model is transparent and readable., Comment: Accepted at the NeurIPS 2019 workshop on Machine Learning for the Physical Sciences (https://ml4physicalsciences.github.io)

Published
2019

7. Sim-to-Real Domain Adaptation For High Energy Physics

Author

Baalouch, Marouen, Defurne, Maxime, Poli, Jean-Philippe, and Cherrier, Noëlie

Subjects
Computer Science - Machine Learning, Statistics - Machine Learning
Abstract

Particle physics or High Energy Physics (HEP) studies the elementary constituents of matter and their interactions with each other. Machine Learning (ML) has played an important role in HEP analysis and has proven extremely successful in this area. Usually, the ML algorithms are trained on numerical simulations of the experimental setup and then applied to the real experimental data. However, any discrepancy between the simulation and real data may lead to dramatic consequences concerning the performances of the algorithm on real data. In this paper, we present an application of domain adaptation using a Domain Adversarial Neural Network trained on public HEP data. We demonstrate the success of this approach to achieve sim-to-real transfer and ensure the consistency of the ML algorithms performances on real and simulated HEP datasets., Comment: Accepted at the NeurIPS 2019 workshop on Machine Learning for the Physical Sciences (https://ml4physicalsciences.github.io)

Published
2019

8. Consistent Feature Construction with Constrained Genetic Programming for Experimental Physics

Author

Cherrier, Noëlie, Poli, Jean-Philippe, Defurne, Maxime, and Sabatié, Franck

Subjects
Computer Science - Neural and Evolutionary Computing, Computer Science - Machine Learning, Statistics - Machine Learning
Abstract

A good feature representation is a determinant factor to achieve high performance for many machine learning algorithms in terms of classification. This is especially true for techniques that do not build complex internal representations of data (e.g. decision trees, in contrast to deep neural networks). To transform the feature space, feature construction techniques build new high-level features from the original ones. Among these techniques, Genetic Programming is a good candidate to provide interpretable features required for data analysis in high energy physics. Classically, original features or higher-level features based on physics first principles are used as inputs for training. However, physicists would benefit from an automatic and interpretable feature construction for the classification of particle collision events. Our main contribution consists in combining different aspects of Genetic Programming and applying them to feature construction for experimental physics. In particular, to be applicable to physics, dimensional consistency is enforced using grammars. Results of experiments on three physics datasets show that the constructed features can bring a significant gain to the classification accuracy. To the best of our knowledge, it is the first time a method is proposed for interpretable feature construction with units of measurement, and that experts in high-energy physics validate the overall approach as well as the interpretability of the built features., Comment: Accepted in this version to CEC 2019

Published
2019
Full Text
View/download PDF

9. Representation of Explanations of Possibilistic Inference Decisions

Author

Baaj, Ismaïl, Poli, Jean-Philippe, Ouerdane, Wassila, Maudet, Nicolas, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Vejnarová, Jiřina, editor, and Wilson, Nic, editor

Published
2021
Full Text
View/download PDF

11. Interpretable Machine Learning with Bitonic Generalized Additive Models and Automatic Feature Construction

Author

Cherrier, Noëlie, Mayo, Michael, Poli, Jean-Philippe, Defurne, Maxime, Sabatié, Franck, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Appice, Annalisa, editor, Tsoumakas, Grigorios, editor, Manolopoulos, Yannis, editor, and Matwin, Stan, editor

Published
2020
Full Text
View/download PDF

13. Design of a Decision Support System for Buried Pipeline Corrosion Assessment

Author

Boudet, Laurence, Poli, Jean-Philippe, Bel, Alicia, Castillon, François, Gaigne, Frédéric, Casula, Olivier, Barbosa, Simone Diniz Junqueira, Series Editor, Chen, Phoebe, Series Editor, Filipe, Joaquim, Series Editor, Kotenko, Igor, Series Editor, Sivalingam, Krishna M., Series Editor, Washio, Takashi, Series Editor, Yuan, Junsong, Series Editor, Zhou, Lizhu, Series Editor, Medina, Jesús, editor, Ojeda-Aciego, Manuel, editor, Verdegay, José Luis, editor, Perfilieva, Irina, editor, Bouchon-Meunier, Bernadette, editor, and Yager, Ronald R., editor

Published
2018
Full Text
View/download PDF

14. A Fuzzy Close Algorithm for Mining Fuzzy Association Rules

Author

Pierrard, Régis, Poli, Jean-Philippe, Hudelot, Céline, Barbosa, Simone Diniz Junqueira, Series Editor, Chen, Phoebe, Series Editor, Filipe, Joaquim, Series Editor, Kotenko, Igor, Series Editor, Sivalingam, Krishna M., Series Editor, Washio, Takashi, Series Editor, Yuan, Junsong, Series Editor, Zhou, Lizhu, Series Editor, Medina, Jesús, editor, Ojeda-Aciego, Manuel, editor, Verdegay, José Luis, editor, Pelta, David A., editor, Cabrera, Inma P., editor, Bouchon-Meunier, Bernadette, editor, and Yager, Ronald R., editor

Published
2018
Full Text
View/download PDF

15. Fuzzy Rule Learning for Material Classification from Imprecise Data

Author

Grivet Sébert, Arnaud, Poli, Jean-Philippe, Barbosa, Simone Diniz Junqueira, Series Editor, Chen, Phoebe, Series Editor, Filipe, Joaquim, Series Editor, Kotenko, Igor, Series Editor, Sivalingam, Krishna M., Series Editor, Washio, Takashi, Series Editor, Yuan, Junsong, Series Editor, Zhou, Lizhu, Series Editor, Medina, Jesús, editor, Ojeda-Aciego, Manuel, editor, Verdegay, José Luis, editor, Pelta, David A., editor, Cabrera, Inma P., editor, Bouchon-Meunier, Bernadette, editor, and Yager, Ronald R., editor

Published
2018
Full Text
View/download PDF

18. Online Fuzzy Temporal Operators for Complex System Monitoring

Author

Poli, Jean-Philippe, Boudet, Laurence, Espinosa, Bruno, Cornez, Laurence, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Weikum, Gerhard, Series editor, Antonucci, Alessandro, editor, Cholvy, Laurence, editor, and Papini, Odile, editor

Published
2017
Full Text
View/download PDF

21. A Modular Fuzzy Expert System Architecture for Data and Event Streams Processing

Author

Poli, Jean-Philippe, Boudet, Laurence, Diniz Junqueira Barbosa, Simone, Series editor, Chen, Phoebe, Series editor, Du, Xiaoyong, Series editor, Filipe, Joaquim, Series editor, Kara, Orhun, Series editor, Liu, Ting, Series editor, Kotenko, Igor, Series editor, Sivalingam, Krishna M., Series editor, Washio, Takashi, Series editor, Carvalho, Joao Paulo, editor, Lesot, Marie-Jeanne, editor, Kaymak, Uzay, editor, Vieira, Susana, editor, Bouchon-Meunier, Bernadette, editor, and Yager, Ronald R., editor

Published
2016
Full Text
View/download PDF

23. A Fuzzy Spatio-temporal-Based Approach for Activity Recognition

Author

Le Yaouanc, Jean-Marie, Poli, Jean-Philippe, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Doug, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Castano, Silvana, editor, Vassiliadis, Panos, editor, Lakshmanan, Laks V., editor, and Lee, Mong Li, editor

Published
2012
Full Text
View/download PDF

24. Modeling Television Schedules for Television Stream Structuring

Author

Poli, Jean-Philippe, Carrive, Jean, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Cham, Tat-Jen, editor, Cai, Jianfei, editor, Dorai, Chitra, editor, Rajan, Deepu, editor, Chua, Tat-Seng, editor, and Chia, Liang-Tien, editor

Published
2006
Full Text
View/download PDF

25. Causal discovery for fuzzy rule learning

Author

Kunitomo Jacquin, Lucie, Lomet, Aurore, Poli, Jean-Philippe, Laboratoire Sciences des Données et de la Décision (LS2D), Département Métrologie Instrumentation & Information (DM2I), Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA)), Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, This work is funded by the CEA Cross-Cutting Program on Materials and Processes Skills., and IEEE

Subjects
[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], fuzzy rules, Online learning, [INFO.INFO-IT]Computer Science [cs]/Information Theory [cs.IT], [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST], Machine learning, constraint-based causal discovery, fuzzy logic, imperfect causality, artificial intelligence, entropy, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract

International audience; Fuzzy rules induction algorithms are usually based on statistical criteria such as correlation or on examples covering.Although these algorithms can be efficient to predict the outputs, some studies also aim to provide insight about the mechanism that links inputs and outputs.In our work, we focus on allying fuzzy logic, which is a suitable model for human-like information, and causality, which is a key concept for humans to generate knowledge from observations and also to build explanations. If a fuzzy premise causes a fuzzy consequence, then acting on the fuzzy premise will have an impact on the fuzzy consequence. This is not necessarily the case for common fuzzy rules based on correlation. Indeed, correlations may be due to some latent common cause of fuzzy premise and consequence, thus acting on the fuzzy premise will have no impact on the fuzzy consequence.This article proposes an approach to construct a set of causality-based fuzzy rules from crisp observational data. The idea is to identify causal relationships on the set of fuzzified inputs and outputs by well-known constraints-based causal discovery algorithms such as Peter-Clark and Fast Causal Inference. The causal discovery algorithms are combined with entropy-based conditional independent testing that avoids making hypotheses on the data distribution.Experiments are conducted to evaluate our approach in terms of ability to recover causal relationships between fuzzy sets in the presence of a latent common cause. The results illustrate the interest of our approach compared to a correlation-based approach and state-of-the-art approaches.

Published
2022
Full Text
View/download PDF

27. OSL/FO remote dosimetry for radiological investigations in hard-to-access zones

Author

Magne, Sylvain, Husson, Wilfrid, Horpin, Margaux, Payet, Lucas, Grigaut-Desbrosses, Hans, Sutra, Guillaume, Poli, Jean-Philippe, Dogny, Stéphane, Helbert, Christopher, Ledieu, Marion, Gueton, Olivier, Loubet, Laurent, Laboratoire Capteurs Fibres Optiques (LCFO), Département Métrologie Instrumentation & Information (DM2I), Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA)), Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Laboratoire Capteurs et Architectures Electroniques (LCAE), Intelligence Artificielle et Apprentissage Automatique (LI3A), ORANO, Laboratoire de Mesures Nucléaires (LMN), Service Mesures et modélisation des Transferts et des Accidents graves (SMTA), Département Technologie Nucléaire (DTN), CEA-Direction des Energies (ex-Direction de l'Energie Nucléaire) (CEA-DES (ex-DEN)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-CEA-Direction des Energies (ex-Direction de l'Energie Nucléaire) (CEA-DES (ex-DEN)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Département Technologie Nucléaire (DTN), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), and projet INSPECT 'Dosimétrie répartie, en ligne et à distance, appliquée à l’inspection d’équipements et d’infrastructures nucléaires' financé par le programme Investissements d’avenir et l’Andra dans le cadre du programme « Nucléaire de Demain »

Subjects
instrumentation, [PHYS]Physics [physics], dosimetry, Distributed and Quasi-distributed sensing, Dismantling, Optically Stimulated Luminescence (OSL), [SPI]Engineering Sciences [physics], Optical Fiber Sensor, radioactivity, dose rate, remote dosimetry, ionizing radiation, nuclear instrumentation, Decommissioning
Abstract

Session “Fibre dosimetry and beam monitoring”; International audience; Radiological investigations in the context of Decommissioning and Dismantling (D&D) of nuclear installations are still challenging in hard-to-access zones. OSL/FO (Optically Stimulated Luminescence/Fiber Optics) remote dosimetry is a cost-effective solution in the constrained budget framework of D&D. Within the INSPECT Project, a newly-designed OSL/FO readout device and innovative multichannel probes have been designed and successfully field-tested at CEA/Marcoule, CEA/Cadarache and ORANO/La Hague in France. The monitoring of dose rate profiles improves localization accuracy and speeds up investigations. We report current device performance and future improvements.

Published
2021

28. Towards Monotonous Functions Approximation from Few Data With Gradual Generalized Modus Ponens: Application to Materials Science

Author

Hajri, Hiba, Poli, Jean-Philippe, Boudet, Laurence, Intelligence Artificielle et Apprentissage Automatique (LI3A), Département Métrologie Instrumentation & Information (DM2I), Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA)), Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA)), and Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay

Subjects
Knowledge Extraction, Materials science and technology, Fuzzy sets, Materials Science, online learning, [CHIM.MATE]Chemical Sciences/Material chemistry, Gradual Generalized Modus Ponens, artificial intelligence, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Fuzzy logic, Predictive models, Toy manufacturing industry, machine learning, Monotonous Function Prediction, Model Interpretability, Manufacturing processes
Abstract

International audience; In this paper, we present a new approach to predict monotonous functions based on approximate reasoning and in particular on the Gradual Generalized Modus Ponens (GGMP) in fuzzy logic. We propose to optimise the parameters of such fuzzy rules with a genetic algorithm considering few experimental data.We use our approach to predict some properties of materials from their manufacturing process parameters. We automatically extract causality, seek for graduality and then set up the GGMP. We tested on both toy and real world datasets. We also discuss the importance of gradual knowledge in materials science.

Published
2021
Full Text
View/download PDF

29. Vers l'approximation de fonctions monotones avec le modus ponens généralisé graduel à partir de peu de données: application à la Science des Matériaux

Author

Hajri, Hiba, Poli, Jean-Philippe, BOUDET, Laurence, Intelligence Artificielle et Apprentissage Automatique (LI3A), Département Métrologie Instrumentation & Information (DM2I), Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA)), Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Ce travail est financé par le plan transverse de compétences 'Matériaux et Procédés' du CEA, Collectif LFA, Laboratoire d'Intégration des Systèmes et des Technologies (LIST), and Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Laboratoire d'Intégration des Systèmes et des Technologies (LIST)

Subjects
Knowledge Extraction, Artificial intelligence, Materials Science, Gradual Generalized Modus Ponens, Intelligence artificielle, Science des matériaux, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Extraction de connaissances, Online learning, Machine learning, [PHYS.COND.CM-MS]Physics [physics]/Condensed Matter [cond-mat]/Materials Science [cond-mat.mtrl-sci], fuzzy logic, Modus ponens généralisé graduel, data processing
Abstract

I.S.B.N. : 9782364939066; International audience; La science des matériaux suscite un intérêt grandissant et l'intelligence artificielle a un rôle à jouer dans l'évolution de ce domaine. Prédire les propriétés d'un nouveau matériau à partir des paramètres de son processus de fabrication est une tâche d'une importance primordiale car elle pourrait permettre de cibler les bonnes propriétés plus rapidement. Dans cet article, nous présentons une approche basée sur le Modus Ponens Généralisé Graduel pour approcher des fonctions monotones et ainsi modéliser en particulier les relations graduelles entre les paramètres du processus et les propriétés des matériaux. L'approche est testée par la suite sur des données synthétiques et réelles.

Published
2021

30. Evaluation d'une zone d'écoulement floue basée sur la topographie à l'aide de prédicats spatiaux 3D

Author

Iphar, Clément, Boudet, Laurence, Poli, Jean-Philippe, Intelligence Artificielle et Apprentissage Automatique (LI3A), Département Métrologie Instrumentation & Information (DM2I), Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA)), Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, and European Project: 833717,H2020-SU-SEC-2018,RESPONDRONE

Subjects
[INFO.INFO-DS]Computer Science [cs]/Data Structures and Algorithms [cs.DS], [INFO.INFO-LO]Computer Science [cs]/Logic in Computer Science [cs.LO], artificial intelligence, machine learning, online learning, fuzzy logic, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract

International audience; La logique floue peut jouer un rôle important dans la modélisation de la connaissance géographique, en particulier dans la gestion de crise. De tels systèmes se basent principalement sur des Systèmes d'Information Géographique qui se consacrent à une information en 2D. Dans cet article, nous utilisons le cadre de la morphologie mathématique floue pour définir de nouvelles relations afin de raisonner sur la topographie au sein d'un modèle numérique de terrain. En particulier, nous nous concentrons sur la caractérisation de la ligne de plus grande pente. Sans réduire le caractère général de l'approche, nous illustrons ces relations sur un cas d'écoulement depuis un bâtiment sur un terrain donné.

Published
2021

31. Discussion sur la causalité imparfaite et son application aux sciences expérimentales

Author

JACQUIN, Lucie, Lomet, Aurore, Poli, Jean-Philippe, Laboratoire Sciences des Données et de la Décision (LS2D), Département Métrologie Instrumentation & Information (DM2I), Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA)), Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Intelligence Artificielle et Apprentissage Automatique (LI3A), Ces travaux sont finances par le programme transverse de competences 'Materiaux et Procedes' du CEA, Université La Sorbonne, Laboratoire d'Intégration des Systèmes et des Technologies (LIST), and Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Laboratoire d'Intégration des Systèmes et des Technologies (LIST)

Subjects
Causalité, Logique floue, [STAT.AP]Statistics [stat]/Applications [stat.AP], online learning, Imperfect causality, Material science, [CHIM.MATE]Chemical Sciences/Material chemistry, artificial intelligence, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Causality, machine learning, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], fuzzy logic, Causalité imparfaite, Sciences des matériaux
Abstract

I.S.B.N. : 9782364939066; International audience; Material discovery is mainly based on the analysis of experimental data obtained by varying the parameters of the manufacturing processes and by observing the properties of the created materials. Artificial Intelligence (AI) has been applied to this field, providing models that can predict the performance of new materials. Our work rather ims at an application of AI in connection with materials experts to provide them with knowledge extracted from their data. An important first step is to determine the causal relations between parameters, properties and performance. In this article, we position our interest on causality extraction within the framework of fuzzy logic.; La découverte de matériaux repose principalement sur l'analyse de données expérimentales obtenues par variation des paramètres des procédés de fabrication et en observant les propriétés des matériaux ainsi créés. L'Intelligence Artificielle (IA) a été appliquée à ce domaine, proposant des modèles pouvant prédire les performances des nouveaux matériaux. Nos travaux visent plutôt une application de l'IA en lien avec les experts des matériaux afin de leur fournir des connaissances extraites de leurs données.Une première étape d'importance est la détermination des liens causaux entre paramètres, propriétés et performances.Dans cet article, nous positionnons notre intérêt sur l'extraction de causalité dans le cadre de la logique floue.

Published
2021

39. Embedded Constrained Feature Construction for High-Energy Physics Data Classification

Author

Cherrier, No��lie, Defurne, Maxime, Poli, Jean-Philippe, Sabati��, Franck, Laboratoire d'Intégration des Systèmes et des Technologies (LIST), Université Paris-Saclay-Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Institut de Recherches sur les lois Fondamentales de l'Univers (IRFU), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Direction de Recherche Technologique (CEA) (DRT (CEA)), Intelligence Artificielle et Apprentissage Automatique (LI3A), Département Métrologie Instrumentation & Information (DM2I), Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA)), and Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay

Subjects
FOS: Computer and information sciences, [PHYS]Physics [physics], Computer Science - Machine Learning, online learning, Machine Learning (stat.ML), artificial intelligence, Machine Learning (cs.LG), [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], machine learning, statistical analysis, classification, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Statistics - Machine Learning, tree-based model, [INFO]Computer Science [cs], signal processing
Abstract

Before any publication, data analysis of high-energy physics experiments must be validated. This validation is granted only if a perfect understanding of the data and the analysis process is demonstrated. Therefore, physicists prefer using transparent machine learning algorithms whose performances highly rely on the suitability of the provided input features. To transform the feature space, feature construction aims at automatically generating new relevant features. Whereas most of previous works in this area perform the feature construction prior to the model training, we propose here a general framework to embed a feature construction technique adapted to the constraints of high-energy physics in the induction of tree-based models. Experiments on two high-energy physics datasets confirm that a significant gain is obtained on the classification scores, while limiting the number of built features. Since the features are built to be interpretable, the whole model is transparent and readable., Accepted at the NeurIPS 2019 workshop on Machine Learning for the Physical Sciences (https://ml4physicalsciences.github.io)

Published
2019

40. Fuzzy4U : un moteur d’adaptation en logique floue pour l’accessibilité des interfaces utilisateurs

Author

Giuffrida, Tanguy, Céret, Eric, Dupuy-Chessa, Sophie, Poli, Jean-Philippe, Laboratoire d'Informatique de Grenoble (LIG ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), Laboratoire d'analyse des données et d'intelligence des systèmes (LADIS), Département Métrologie Instrumentation & Information (DM2I), Laboratoire d'Intégration des Systèmes et des Technologies (LIST), Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Laboratoire d'Intégration des Systèmes et des Technologies (LIST), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Intelligence Artificielle et Apprentissage Automatique (LI3A), Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA)), and Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA))

Subjects
Fuzzy logic, Context of use, ACM: H.: Information Systems/H.5: INFORMATION INTERFACES AND PRESENTATION (e.g., HCI)/H.5.2: User Interfaces/H.5.2.4: Graphical user interfaces (GUI), Logique floue, User Interface adaptation, Contexte d'usage, Règles d'adaptation, [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], Adaptation rules, Adaptation d'Interface Utilisateur, artificial intelligence, Accessibility, Accessibilité
Abstract

With the massive spread of Internet use, the accessibility of user interfaces (UI) is an ever more pressing need. Much work has been developed on this subject in order to define generic or situational accessibility recommendations and to propose tools for user interface adaptation. However, difficulties remain, particularly related to the complexity of possible contexts of use, such as the multiplicity of characteristics of the context of use, the imprecision of the values assigned to these characteristics and the combination of multiple adaptation rules. This article shows how a dynamic adaptation engine based on fuzzy logic can be used to implement accessibility recommendations. We show how this approach makes it possible to overcome these difficulties through fuzzy logic with the capacity to manage combinatorial rules, making it possible to take into account potentially complex contexts of use. This approach is illustrated with a concrete example., Avec la diffusion massive de l'utilisation d'Internet, l'accessibilité des interfaces est un besoin toujours plus prégnant. De nombreux travaux se sont penchés sur ce sujet afin de définir des recommandations d'accessibilité génériques ou situationnelles, et proposer des outils d'adaptation des interfaces utilisateurs. Cependant, des difficultés, notamment liées à la complexité des contextes d'usage possibles, demeurent tels que la multiplicité des caractéristiques du contexte d'usage, l'imprécision des valeurs attribuées à ces caractéristiques et la combinaison de multiples règles d'adaptation. Cet article montre comment un moteur d'adaptation dynamique basé sur la logique floue peut être utilisé pour implémenter les préconisations en accessibilité. Il montre comment cette approche permet de dépasser ces verrous grâce à la logique floue et sa gestion de la combinatoire des règles, permettant de prendre en compte un contexte d'usage potentiellement complexe que nous illustrons avec un exemple concret.

Published
2019
Full Text
View/download PDF

41. Learning Fuzzy Relations from Few Data for Explainable Semantic Annotation

Author

Pierrard, Régis, Poli, Jean-Philippe, Hudelot, Céline, Intelligence Artificielle et Apprentissage Automatique (LI3A), Département Métrologie Instrumentation & Information (DM2I), Laboratoire d'Intégration des Systèmes et des Technologies (LIST), Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Laboratoire d'Intégration des Systèmes et des Technologies (LIST), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Mathématiques et Informatique pour la Complexité et les Systèmes (MICS), CentraleSupélec, Toulouse Institute of Computer Science Research (IRIT), and the French AI Society (AFIA), Maxime Lefrançois, MINES Saint-Étienne, and France

Subjects
logique floue, annotation, peu de données, fuzzy logic, Explainability, few-data learning, [INFO.INFO-MO]Computer Science [cs]/Modeling and Simulation, Explicabilité, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract

Co-localisées avec la Plate-Forme Intelligence Artificielle (PFIA 2019); International audience; Despite the recent successes of deep learning, such models are still far from some human abilities like learning from few examples, reasoning and explaining their decisions. In this paper, we focus on object annotation in images and we introduce a reasoning framework that is based on learning fuzzy relations on a dataset for generating explanations. Given a catalogue of relations, it efficiently induces the most relevant relations and combines them for building constraints in order to both solve the target task and generate explanations. We test our approach on a publicly available dataset on which the goal was both to perform multiple organ annotation and to provide explanations. We show that our model can generate explanations and achieve high performance despite being trained on a small dataset containing as few as a couple of examples.; Malgré son récent succès, l’apprentissage profond semble loin d’égaler certaines capacités humaines comme l’apprentissage à partir de peu d’exemples, le raisonnement ou encore l’explicabilité. Dans cet article, nous mettons l’accent sur l’annotation d’objets dans des images et nous présentons un cadre de raisonnement s’appuyant sur l’apprentissage de relations floues qui permet notamment de générer des explications. Étant donné un ensemble de relations, les plus pertinentes d’entre elles sont induites et combinées pour construire des contraintes permettant de définir un problème de satisfaction de contraintes floues. La résolution de ce probléme nous permet d’annoter l’image et de générer des explications à l’aide des contraintes utilisées. Nous testons notre approche sur un jeu de données public avec deux objectifs : effectuer une annotation d’organes et fournir une explication à chaque annotation. Nous montrons que le modèle que nous obtenons peut générer des explications tout en atteignant des performances élevées malgré un jeu de données pouvant être constitué de seulement deux exemples.

Published
2019

42. Mineral Identification And Characterization: An Integrated Approach To Recover Mineralogical Information From Hyperspectral Images

Author

Rialland, Ronan, Marion, Rodolphe, Carrere, V., Soussen, Charles, Poli, Jean-Philippe, Laboratoire des signaux et systèmes (L2S), Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Laboratoire de Planétologie et Géodynamique [UMR 6112] (LPG), Université d'Angers (UA)-Université de Nantes - UFR des Sciences et des Techniques (UN UFR ST), Université de Nantes (UN)-Université de Nantes (UN)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS), EARSeL, and CzechGlobe

Subjects
Hyperspectral remote sensing, expert rules, AGM, mineral mapping, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, reflectance spectra
Abstract

International audience; Mineral mapping and soil analysis, from airborne or satellite sensors, are two growing topics for the study of environmental issues and the evaluation of the geological interest of large areas. For example, it can provide important information for the supervision of industrial activities. The development of new and more performing imaging spectrometers such as AVIRIS-NG or EnMAP, makes possible the acquisition of hyperspectral images in the Visible Near-InfraRed [0,4 – 1,3] μm and the Short-Wave InfraRed [1,3 – 2,5] μm domains with high spectral resolution and signal-to-noise ratios allowing the analysis of the reflectance spectra of minerals. Indeed, those spectral signatures may give access to several physical and chemical parameters (e.g., composition, grain size, humidity) of minerals.The purpose of this poster is to present an integrated approach giving the possibility to a non expert to automatically study the mineralogy of an area from a hyperspectral image. It is based on the AGM (Automatized Gaussian Model) procedure [1] for which several evolutions have been developed. This procedure uses the EGO (Exponential Gaussian Optimization) model which decomposes the reflectance spectra of minerals as the sum of a continuum and generalized Gaussians functions. Each Gaussian, defined by five parameters (center, amplitude, width, asymmetry and saturation), represents an absorption band of the spectrum. Using this model, several physical and chemical parameters of minerals can be estimated.The new AGM procedure is divided in four main parts. A first step, based on the estimation of the signal dependent and independent noises in the imaging spectrometer, gives information about the measurement uncertainties. Then, the parameters of the EGO model are estimated. A nonlinear least-square solver, such as Levenberg-Marquardt or Optimal Estimation, is considered depending on the a priori knowledge (geology of the area, measurement uncertainties, etc.). A third step, using a fuzzy logic system developed at CEA [2], allows, from the estimated model parameters and considering a set of expert rules, to identify the diagnostic absorption features of the reflectance spectra and so the mineral or the mixture of minerals associated to it. Thus, the database consists in absorption features rather than reflectance spectra. Finally, several physical and chemical parameters of the minerals can be mapped (e.g., composition, grain size) from the mineral identification and some of the model parameters.This new approach, automatic and adapted to non-experts operational needs, is validated on AVIRIS and AVIRIS-NG data for areas of geological interest. It allows to identify mixtures of minerals and gives access to several of their physical and chemical parameters. Future work will include the development of new optimization methods and the creation of new expert rules.[1] R. Marion and V. Carrère, Mineral Mapping Using the Automatized Gaussian Model (AGM) - Application to Two Industrial French Sites at Gardanne and Thann, Remote Sensing 2018, 10, 146.[2] J.P. Poli and L. Boudet, A fuzzy expert system architecture for data and event stream processing, Fuzzy Sets and Systems, 2018, 343, p.20-34

Published
2019

44. Fuzzy4U: a fuzzy logic system for user interfaces adaptation

Author

Giuffrida, Tanguy, Dupuy-Chessa, Sophie, Poli, Jean-Philippe, Ceret, Eric, Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), Centre National de la Recherche Scientifique (CNRS), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP ), Laboratoire d'Informatique de Grenoble (LIG ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), and AFIHM

Subjects
Adaptation d’IHM, logique floue, HCI adaptation, context of use, fuzzy logic, [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], uncertainty, contexte d’usage, incertitude
Abstract

International audience; User Interfaces adaptation is a well-known requirement in human-computer interaction. However, even if many works address this topic, some challenges such as context uncertainty and a combination of adaptation rules, are still remaining. This article tackles these challenges by using fuzzy logic to manage adaptation. It proposes an architecture where an adaptation engine is supported by fuzzy logic. It shows its benefits and compares it with an approach using crisp logic.; L’adaptation des interfaces est un besoin reconnu en interaction homme-machine. Cependant, même si de nombreux travaux ont abordé cette thématique, il demeure des verrous tels que l’incertitude du contexte d’usage et de la combinaison des règles d’adaptation. Cet article aborde ces verrous en proposant d’utiliser la logique floue pour gérer l’adaptation. Il propose une architecture dans laquelle le moteur d’adaptation s’appuie sur la logique floue. Il en montre les bénéfices et compare l’approche avec une approche en logique booléenne.

Published
2018

45. Deployment of the First Photofission Measurement System Dedicated to SNM Detection in Europe: Outcomes and Future Prospects

Author

Sari, Adrien, primary, Carrel, Frederick, additional, Grabowski, Amelie, additional, Laine, Frederic, additional, Espinosa, Bruno, additional, Poli, Jean-Philippe, additional, Sibczynski, Pawel, additional, Della-Rocca, Ian, additional, Foster, Mark, additional, Etile, Asenath, additional, Roig, Olivier, additional, Maitrejean, Serge, additional, Rogerat, Sebastien, additional, Berthelier, Thibaut, additional, Gasser, Estelle, additional, Slegt, Micha, additional, de Goede, Rene, additional, Groeneveld, Joris, additional, de Wilde, Hans, additional, and Heerschop, Marcel, additional

Published
2019
Full Text
View/download PDF

48. Vers la classification de matériaux à partir de compositions chimiques incertaines

Author

Grivet Sébert, Arnaud, Poli, Jean-Philippe, Intelligence Artificielle et Apprentissage Automatique (LI3A), Département Métrologie Instrumentation & Information (DM2I), Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA)), Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, European Project: 653323,H2020,H2020-BES-2014,C-BORD(2015), Laboratoire d'analyse des données et d'intelligence des systèmes (LADIS), Laboratoire d'Intégration des Systèmes et des Technologies (LIST), and Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Laboratoire d'Intégration des Systèmes et des Technologies (LIST)

Subjects
fuzzy rules, online learning, [INFO.INFO-LO]Computer Science [cs]/Logic in Computer Science [cs.LO], artificial intelligence, incertitude, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], [SPI.MAT]Engineering Sciences [physics]/Materials, machine learning, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Fuzzy decision tree, fuzzy logic, uncertainty, material classification, classification de matériaux, Arbre de décision flou, règles floues
Abstract

I.S.B.N. : 9782364936140; National audience; In this paper, a study about the classification of materials from their chemical composition is realized. The used method relies on a fuzzy decision tree and focuses on handling the uncertainty of the data by a technique we will explain. The complete algorithm is tested on simulated data sets, in the expectation of real data.; Dans cet article, une étude sur la classification de matériaux à partir de leur composition chimique est réalisée. La méthode utilisée se base sur un arbre de décision flou et l'accent est mis sur la gestion de l'incertitude des données, qui fait l'objet d'un traitement particulier que nous exposerons. L'algorithme complet est testé sur des jeux de données simulés, dans l'attente de données réelles.

Published
2017

50. Fuzzy4U

Author

Giuffrida, Tanguy, primary, Dupuy-Chessa, Sophie, additional, Poli, Jean-Philippe, additional, and Céret, Eric, additional

Published
2018
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results