Author: "François Poulet" / Topic: computer science - Searchworks@Jio Institute Digital Library Search Results

Your search keyword '"François Poulet"' showing total 33 results

Start Over Author "François Poulet" Topic computer science

33 results on '"François Poulet"'

1. The thermal-vacuum and security system of the characterization facility for MAJIS/JUICE VIS-NIR FM and SM detectors

Author: Özgür Karatekin, Miriam E. Cisneros-González, P. Gerard, Michel Le Du, Cydalise Dumesnil, Nuno Pereira, Laurent Picot, Jean Pierre Dubois, François Poulet, Lionel Van Laeken, Ann Carine Vandaele, Jérémie Hansotte, Séverine Robert, and David Bolsée
Subjects: Data processing, Ground support equipment, Payload, Computer science, Nuclear engineering, Pipeline (computing), Interface (computing), Control system, Detector, Vacuum chamber
Abstract: MAJIS is part of the science payload of the JUICE mission to be launched in 2022. BIRA-IASB and ROB contribute to MAJIS with the characterization of the VIS-NIR Flight Model (FM) and Spare Model (SM) detectors, including the design, development, and validation of the setup, as well as the data processing pipeline. The VIS-NIR detectors are thermalized within a temperature range from 125 K to 150 K during their characterization campaigns. Moreover, the temperature of their electronic units must always remain above 120 K to avoid any irreparable damage, and below 160 K for operative conditions. Likewise, to avoid any risk of contamination, the detector should preferably be operated below 10-5 mbar of vacuum. To fulfill these requirements, a complete security system was developed; it includes redundant thermal control loops, alarms from every pressure and temperature monitoring devices in use, and a robust semi-automatic control system for the pumping and cryocooling equipment. Moreover, the security system is complemented by the Temperature Ground Support Equipment (TGSE), which provides a LabVIEW user-friendly interface to communicate the status of the detector and the vacuum chamber in real-time. This subsystem was successfully validated in May 2020, before the delivery of the FM detector in June 2020. In this paper, we summarize the design, implementation and validation tests of the security system as well as the thermal and vacuum performances of the facility. We also show the thermal behavior of the detector during acquisitions representative of typical MAJIS observations.
Published: 2020

2. Planetary Terrestrial Analogues Library project: 2. building a laboratory facility for MicrOmega characterization

Author: Damien Loizeau, Lionel Meslier-Lourit, J. P. Bibring, François Poulet, Guillaume Lequertier, Cedric Pilorget, Stephanie C. Werner, Vincent Hamm, Cateline Lantz, Fernando Rull, Institut d'astrophysique spatiale (IAS), Institut national des sciences de l'Univers (INSU - CNRS)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS), Centre for Earth Evolution and Dynamics [Oslo] (CEED), Department of Geosciences [Oslo], Faculty of Mathematics and Natural Sciences [Oslo], University of Oslo (UiO)-University of Oslo (UiO)-Faculty of Mathematics and Natural Sciences [Oslo], University of Oslo (UiO)-University of Oslo (UiO), and University of Valladolid
Subjects: 010504 meteorology & atmospheric sciences, [SDU.ASTR]Sciences of the Universe [physics]/Astrophysics [astro-ph], Computer science, Natural Earth, Hyperspectral imaging, Astronomy and Astrophysics, Mars Exploration Program, 01 natural sciences, Characterization (materials science), Laboratory facility, Spectral database, Space and Planetary Science, Flight model, [SDU]Sciences of the Universe [physics], 0103 physical sciences, Systems engineering, 010303 astronomy & astrophysics, 0105 earth and related environmental sciences
Abstract: International audience; Multiple spectroscopic techniques have been selected on previous, present and forthcoming missions to explore planetary surfaces in the Solar System. In particular, forthcoming ESA/Roscosmos and NASA missions to the surface of Mars will bring instruments capable of near-infrared (NIR), Raman and Laser Induced Breakdown Spectroscopies to analyze the mineralogy and chemistry of rocks. The PTAL (Planetary Terrestrial Analogues Library) project aims at building a multi-instrument spectral database of a large variety of natural Earth rock samples, including Mars analogues. The NIR hyperspectral microscope MicrOmega was selected to characterize the mineralogy of these analogues within the PTAL project. The instrument model used for the PTAL project is a spare flight model that requires specific care. For the safety of the instrument, and because of the large number of samples in the PTAL library and the requirement to optimize the observational conditions, a dedicated and semiautomated setup was built for the use of the MicrOmega instrument for this project. This paper presents the requirements specified for this setup, the technical solutions that have been selected, their implementation and the performances of the setup. Sample preparation and operations during sample observations are explained, and a characterization example is presented to briefly illustrate the capabilities of MicrOmega in this setup. The complete results from the MicrOmega characterizations of the PTAL rock analogues will be presented in a forthcoming paper (Loizeau et al. in prep).
Published: 2020

3. SIMBIO-SYS: Scientific Cameras and Spectrometer for the BepiColombo Mission

Author: Marilena Amoroso, Francesca Esposito, Giancarlo Bellucci, Y. Langevin, Marco Baroni, Océane Barraud, Francesca Altieri, Giacomo Colombatti, Michael Mendillo, M. I. Blecka, M. T. Capria, Romolo Politi, Ernesto Palomba, Pasquale Palumbo, Olivier Forni, Gianfranco Forlani, E. Flamini, Francesca Ferri, P. Borin, Lionel Wilson, Andrea Cicchetti, Vito Mennella, Carlo Bettanini, Riccardo Paolinetti, Alice Lucchetti, Davide Perna, Nicolas Thomas, Marcello Fulchignoni, V. Della Corte, Maria Sgavetti, Daniela Fantinel, M. El yazidi, A. Doressoundiram, Luigi Ferranti, Simone Marchi, John Robert Brucato, T. Van Hoolst, Cedric Leyrat, Sebastien Besse, Stéphane Erard, Elena Martellato, Y. Li, Diego Turrini, Francesco Marzari, W-H. Ip, Maurizio Pajola, Cristian Carli, Raffaella Noschese, Matteo Massironi, Sabrina Ferrari, Alessio Aboudan, Giuseppe Salemi, I. Ficai Veltroni, Lorenza Giacomini, Karri Muinonen, Emanuele Simioni, Jessica Flahaut, Priscilla Cerroni, Mathieu Vincendon, V. Da Deppo, Alessandra Slemer, L. M. Lara, M. C. De Sanctis, Raffaele Mugnuolo, M. Dami, Francesca Zambon, G. Piccioni, L. Guzzetta, Fabrizio Capaccioni, Giampiero Naletto, E. Mazzotta Epifani, G. Aroldi, Andrea Turella, Michele Zusi, Maurizio Rossi, Stefano Debei, Gabriele Cremonese, A. Barucci, Johannes Benkhoff, Gloria Tognon, Cristina Re, François Poulet, Donato Borrelli, Sonia Fornasier, Valentina Galluzzi, Gianrico Filacchione, Leonardo Tommasi, François Leblanc, Laurent Jorda, Lucia Marinangeli, Roberto Ragazzoni, V. Carlier, Alessandra Rotundi, N. Bott, Luigi Colangeli, Klaus Gwinner, Cremonese, G., Capaccioni, F., Capria, M. T., Doressoundiram, A., Palumbo, P., Vincendon, M., Massironi, M., Debei, S., Zusi, M., Altieri, F., Amoroso, M., Aroldi, G., Baroni, M., Barucci, A., Bellucci, G., Benkhoff, J., Besse, S., Bettanini, C., Blecka, M., Borrelli, D., Brucato, J. R., Carli, C., Carlier, V., Cerroni, P., Cicchetti, A., Colangeli, L., Dami, M., Da Deppo, V., Della Corte, V., De Sanctis, M. C., Erard, S., Esposito, F., Fantinel, D., Ferranti, L., Ferri, F., Ficaiveltroni, I., Filacchione, G., Flamini, E., Forlani, G., Fornasier, S., Forni, O., Fulchignoni, M., Galluzzi, V., Gwinner, K., Ip, W., Jorda, L., Langevin, Y., Lara, L., Leblanc, F., Leyrat, C., Li, Y., Marchi, S., Marinangeli, L., Marzari, F., Mazzottaepifani, E., Mendillo, M., Mennella, V., Mugnuolo, R., Muinonen, K., Naletto, G., Noschese, R., Palomba, E., Paolinetti, R., Perna, D., Piccioni, G., Politi, R., Poulet, F., Ragazzoni, R., Re, C., Rossi, M., Rotundi, A., Salemi, G., Sgavetti, M., Simioni, E., Thomas, N., Tommasi, L., Turella, A., Van Hoolst, T., Wilson, L., Zambon, F., Aboudan, A., Barraud, O., Bott, N., Borin, P., Colombatti, G., Elyazidi, M., Ferrari, S., Flahaut, J., Giacomini, L., Guzzetta, L., Lucchetti, A., Martellato, E., Pajola, M., Slemer, A., Tognon, G., Turrini, D., INAF - Osservatorio Astronomico di Padova (OAPD), Istituto Nazionale di Astrofisica (INAF), Istituto di Astrofisica e Planetologia Spaziali - INAF (IAPS), Laboratoire d'études spatiales et d'instrumentation en astrophysique = Laboratory of Space Studies and Instrumentation in Astrophysics (LESIA), Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire de Paris, Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité), Dipartimento di Fisica 'Ettore Pancini', University of Naples Federico II = Università degli studi di Napoli Federico II, Institut d'astrophysique spatiale (IAS), Université Paris-Sud - Paris 11 (UP11)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Centre National d’Études Spatiales [Paris] (CNES), Dipartimento di Geoscienze [Padova], Università degli Studi di Padova = University of Padua (Unipd), Centro di Ateneo di Studi e Attività Spaziali 'Giuseppe Colombo' (CISAS), Agenzia Spaziale Italiana (ASI), Leonardo SpA, European Space Research and Technology Centre (ESTEC), Agence Spatiale Européenne = European Space Agency (ESA), European Space Astronomy Centre (ESAC), Space Research Centre of Polish Academy of Sciences (CBK), Polska Akademia Nauk = Polish Academy of Sciences (PAN), INAF - Osservatorio Astrofisico di Arcetri (OAA), Istituti di Ricovero e Cura a Carattere Scientifico (IRCCS), CNR Institute for Photonics and Nanotechnologies (IFN), National Research Council of Italy | Consiglio Nazionale delle Ricerche (CNR), INAF - Osservatorio Astronomico di Capodimonte (OAC), Università degli studi 'G. d'Annunzio' Chieti-Pescara [Chieti-Pescara] (Ud'A), Department og Engineering and Architecture [Parma] (DIA), Università degli studi di Parma = University of Parma (UNIPR), Institut de recherche en astrophysique et planétologie (IRAP), Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire Midi-Pyrénées (OMP), Institut de Recherche pour le Développement (IRD)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France -Institut de Recherche pour le Développement (IRD)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France -Centre National de la Recherche Scientifique (CNRS), DLR Institute of Planetary Research, German Aerospace Center (DLR), DLR Institut für Planetenforschung, Deutsches Zentrum für Luft- und Raumfahrt [Berlin] (DLR), Institute of Space Science [Taiwan], National Central University [Taiwan] (NCU), Laboratoire d'Astrophysique de Marseille (LAM), Aix Marseille Université (AMU)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS), Instituto de Astrofísica de Andalucía (IAA), Consejo Superior de Investigaciones Científicas [Madrid] (CSIC), HELIOS - LATMOS, Laboratoire Atmosphères, Milieux, Observations Spatiales (LATMOS), Université de Versailles Saint-Quentin-en-Yvelines (UVSQ)-Institut national des sciences de l'Univers (INSU - CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Université de Versailles Saint-Quentin-en-Yvelines (UVSQ)-Institut national des sciences de l'Univers (INSU - CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), Suzhou Vocational University, Southwest Research Institute [Boulder] (SwRI), International Research School of Planetary Sciences [Pescara] (IRSPS), Dipartimento di Fisica e Astronomia 'Galileo Galilei', INAF - Osservatorio Astronomico di Roma (OAR), Center for Space Physics [Boston] (CSP), Boston University [Boston] (BU), Department of Physics [Helsinki], Falculty of Science [Helsinki], Helsingin yliopisto = Helsingfors universitet = University of Helsinki-Helsingin yliopisto = Helsingfors universitet = University of Helsinki, Finnish Geospatial Research Institute (FGI), Università degli Studi di Napoli 'Parthenope' = University of Naples (PARTHENOPE), Department of Cultural Heritage [Padova], Dipartimento di Scienze della Terra [Parma], Physikalisches Institut [Bern], Universität Bern [Bern] (UNIBE), Royal Observatory of Belgium [Brussels] (ROB), Environmental Sciences [Lancaster], Lancaster University, Centre de Recherches Pétrographiques et Géochimiques (CRPG), Institut national des sciences de l'Univers (INSU - CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), CNR Istituto di Fotonica e Nanotecnologie [Padova] (IFN), Laboratoire d'études spatiales et d'instrumentation en astrophysique (LESIA (UMR_8109)), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Université de Paris (UP), Università degli studi di Napoli Federico II, Université Paris-Sud - Paris 11 (UP11)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS), Universita degli Studi di Padova, European Space Agency (ESA), Consiglio Nazionale delle Ricerche [Roma] (CNR), University of Parma = Università degli studi di Parma [Parme, Italie], Institut national des sciences de l'Univers (INSU - CNRS)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Observatoire Midi-Pyrénées (OMP), Météo France-Centre National d'Études Spatiales [Toulouse] (CNES)-Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche pour le Développement (IRD)-Météo France-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche pour le Développement (IRD)-Centre National de la Recherche Scientifique (CNRS), Sorbonne Université (SU)-Université de Versailles Saint-Quentin-en-Yvelines (UVSQ)-Centre National de la Recherche Scientifique (CNRS)-Institut national des sciences de l'Univers (INSU - CNRS)-Sorbonne Université (SU)-Université de Versailles Saint-Quentin-en-Yvelines (UVSQ)-Centre National de la Recherche Scientifique (CNRS)-Institut national des sciences de l'Univers (INSU - CNRS), University of Helsinki-University of Helsinki, Universita degli studi di Napoli 'Parthenope' [Napoli], Universität Bern [Bern], and Agenzia Spaziale Italiana
Subjects: 010504 meteorology & atmospheric sciences, Computer science, BepiColombo, MPO, Astronomy & Astrophysics, INFRARED REFLECTANCE SPECTRA, 01 natural sciences, 7. Clean energy, Spectrometer, MECHANISMS, law.invention, Orbiter, EXPLOSIVE VOLCANISM, law, 0103 physical sciences, instrument, Spectral resolution, 010303 astronomy & astrophysics, Image resolution, BASIN, 0105 earth and related environmental sciences, Remote sensing, SIMBIO-SYS, ONBOARD, Science & Technology, SPECTROSCOPY, GRAVITY-FIELD, 520 Astronomy, Hyperspectral imaging, MERCURYS SURFACE, Astronomy and Astrophysics, Spectral bands, Mercury, 620 Engineering, HOLLOWS, Imageur, Stereo imaging, 13. Climate action, Space and Planetary Science, [SDU]Sciences of the Universe [physics], Physical Sciences, MESSENGER, Stereo camera
Abstract: Full list of authors: Cremonese, G.; Capaccioni, F.; Capria, M. T.; Doressoundiram, A.; Palumbo, P.; Vincendon, M.; Massironi, M.; Debei, S.; Zusi, M.; Altieri, F.; Amoroso, M.; Aroldi, G.; Baroni, M.; Barucci, A.; Bellucci, G.; Benkhoff, J.; Besse, S.; Bettanini, C.; Blecka, M.; Borrelli, D.; Brucato, J. R.; Carli, C.; Carlier, V.; Cerroni, P.; Cicchetti, A.; Colangeli, L.; Dami, M.; Da Deppo, V.; Della Corte, V.; De Sanctis, M. C.; Erard, S.; Esposito, F.; Fantinel, D.; Ferranti, L.; Ferri, F.; FicaiÂ Veltroni, I.; Filacchione, G.; Flamini, E.; Forlani, G.; Fornasier, S.; Forni, O.; Fulchignoni, M.; Galluzzi, V.; Gwinner, K.; Ip, W.; Jorda, L.; Langevin, Y.; Lara, L.; Leblanc, F.; Leyrat, C.; Li, Y.; Marchi, S.; Marinangeli, L.; Marzari, F.; MazzottaÂ Epifani, E.; Mendillo, M.; Mennella, V.; Mugnuolo, R.; Muinonen, K.; Naletto, G.; Noschese, R.; Palomba, E.; Paolinetti, R.; Perna, D.; Piccioni, G.; Politi, R.; Poulet, F.; Ragazzoni, R.; Re, C.; Rossi, M.; Rotundi, A.; Salemi, G.; Sgavetti, M.; Simioni, E.; Thomas, N.; Tommasi, L.; Turella, A.; Van Hoolst, T.; Wilson, L.; Zambon, F.; Aboudan, A.; Barraud, O.; Bott, N.; Borin, P.; Colombatti, G.; ElÂ Yazidi, M.; Ferrari, S.; Flahaut, J.; Giacomini, L.; Guzzetta, L.; Lucchetti, A.; Martellato, E.; Pajola, M.; Slemer, A.; Tognon, G.; Turrini, D. -- This is an open access article, The SIMBIO-SYS (Spectrometer and Imaging for MPO BepiColombo Integrated Observatory SYStem) is a complex instrument suite part of the scientific payload of the Mercury Planetary Orbiter for the BepiColombo mission, the last of the cornerstone missions of the European Space Agency (ESA) Horizon + science program. The SIMBIO-SYS instrument will provide all the science imaging capability of the BepiColombo MPO spacecraft. It consists of three channels: the STereo imaging Channel (STC), with a broad spectral band in the 400-950 nm range and medium spatial resolution (at best 58 m/px), that will provide Digital Terrain Model of the entire surface of the planet with an accuracy better than 80 m; the High Resolution Imaging Channel (HRIC), with broad spectral bands in the 400-900 nm range and high spatial resolution (at best 6 m/px), that will provide high-resolution images of about 20% of the surface, and the Visible and near-Infrared Hyperspectral Imaging channel (VIHI), with high spectral resolution (6 nm at finest) in the 400-2000 nm range and spatial resolution reaching 120 m/px, it will provide global coverage at 480 m/px with the spectral information, assuming the first orbit around Mercury with periherm at 480 km from the surface. SIMBIO-SYS will provide high-resolution images, the Digital Terrain Model of the entire surface, and the surface composition using a wide spectral range, as for instance detecting sulphides or material derived by sulphur and carbon oxidation, at resolutions and coverage higher than the MESSENGER mission with a full co-alignment of the three channels. All the data that will be acquired will allow to cover a wide range of scientific objectives, from the surface processes and cartography up to the internal structure, contributing to the libration experiment, and the surface-exosphere interaction. The global 3D and spectral mapping will allow to study the morphology and the composition of any surface feature. In this work, we describe the on-ground calibrations and the results obtained, providing an important overview of the instrument performances. The calibrations have been performed at channel and at system levels, utilizing specific setup in most of the cases realized for SIMBIO-SYS. In the case of the stereo camera (STC), it has been necessary to have a validation of the new stereo concept adopted, based on the push-frame. This work describes also the results of the Near-Earth Commissioning Phase performed few weeks after the Launch (20 October 2018). According to the calibration results and the first commissioning the three channels are working very well. © 2020, The Author(s)., We gratefully acknowledge funding from the Italian Space Agency (ASI) under ASI-INAF agreement 2017-47-H.0. The SIMBIO-SYS instrument has been developed by Leonardo under ASI contract I/054/10/0.
Published: 2020

4. Parallel learning of local SVM algorithms for classifying large datasets

Author: Thanh-Nghi Do, François Poulet, Can Tho University [Vietnam] (CTU), MEDIA ET INTERACTIONS (IRISA-D6), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), CentraleSupélec-Télécom Bretagne-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Université de Bretagne Sud (UBS)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-CentraleSupélec-Télécom Bretagne-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA), Poulet, François, Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), and Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)
Subjects: Computer Science::Machine Learning, Computer science, Training time, Decision tree, 02 engineering and technology, Machine learning, computer.software_genre, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], 020204 information systems, Support Vector Machines, 0202 electrical engineering, electronic engineering, information engineering, high-dimensional and large-scale multi-class data classification, Color image, business.industry, Decision tree learning, k-means clustering, Pattern recognition, [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], Partition (database), Support vector machine, ComputingMethodologies_PATTERNRECOGNITION, Parallel learning, 020201 artificial intelligence & image processing, Artificial intelligence, business, Algorithm, computer
Abstract: International audience; We propose new parallel learning algorithms of local support vector machines (local SVMs) for effectively non-linear classification of large datasets. The algorithms of local SVMs perform the training task of large datasets with two main steps. The first one is to partition the full dataset into k subsets of data, and then the second one is to learn non-linear SVMs from k subsets to locally classify them in parallel way on multi-core computers. The k local SVMs algorithm (kSVM) uses kmeans clustering algorithm to partition the data into k clusters, then constructs in parallel non-linear SVM models to classify data clusters locally. The decision tree with labeling support vector machines (tSVM) uses C4.5 decision tree algorithm to split the full dataset into terminal-nodes, and then it learns in parallel local SVM models for classifying impurity terminal-nodes with mixture of labels. The krSVM algorithm is to train random ensemble of kSVM. The numerical test results! on 4 datasets from UCI repository, 3 benchmarks of handwritten letters recognition and a color image collection of one-thousand small objects show that our proposed algorithms of local SVMs (kSVM, tSVM, krSVM) are efficient compared to the standard SVM (LibSVM) in terms of training time and accuracy for dealing with large datasets.
Published: 2017

5. Parallel incremental power mean SVM for the classification of large-scale image datasets

Author: Thanh-Nghi Do, François Poulet, and Thanh-Nghi Doan
Subjects: Computer science, business.industry, Pattern recognition, Linear classifier, Library and Information Sciences, Supercomputer, computer.software_genre, Image (mathematics), Support vector machine, Statistical classification, Media Technology, Benchmark (computing), Data mining, Artificial intelligence, business, Time complexity, Image resolution, computer, Information Systems
Abstract: The amount of image data becomes larger and larger, both image size (due the higher resolution) and image number. It is estimated for personal use only, an average single user will take 100,000 images during his life. The growth of image data is illustrated by the dataset size, for example ImageNet benchmark dataset is made of more than 14 million images and more than 21,000 classes. This is very challenging for classification algorithms. They have to deal with time and space complexity and very imbalanced data when using SVM algorithms. We present extensions of Power Mean SVM to deal with such data. The first one is an incremental version to deal with the space complexity, the second one is a parallel version of the incremental version to deal with time complexity and the last one is the use of a balanced bagging algorithm for training binary classifiers to deal with imbalanced data. We evaluate our parallel incremental version of balanced bagging PmSVM on the 1,000 classes of ImageNet (ILSVRC 2010). The results show that our algorithm can be run on standard PC (with eg. 2 or 4 GB RAM); it is 255 times faster than the original version and 1,276 times faster than state-of-the-art linear classifier, LIBLINEAR with 80 cores.
Published: 2014

6. Classifying very high-dimensional and large-scale multi-class image datasets with Latent-lSVM

Author: Thanh-Nghi Do, François Poulet, Can Tho University [Vietnam] (CTU), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), CentraleSupélec-Télécom Bretagne-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Université de Bretagne Sud (UBS)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA), Université de Rennes (UR), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), and Poulet, François
Subjects: Computer Science::Machine Learning, Computer science, Scale-invariant feature transform, 02 engineering and technology, computer.software_genre, Latent Dirichlet allocation, Data modeling, Multiclass classification, symbols.namesake, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], high-dimensional and large-scale multi-class image classification, 0202 electrical engineering, electronic engineering, information engineering, Cluster analysis, Contextual image classification, business.industry, Latent Dirichlet Allocation (LDA), 020207 software engineering, Pattern recognition, [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], Support vector machine, Statistical classification, ComputingMethodologies_PATTERNRECOGNITION, symbols, 020201 artificial intelligence & image processing, Data mining, Artificial intelligence, Support Vector Machines (SVM), business, computer
Abstract: International audience; We propose a new learning algorithm of latent local support vector machines (SVM), called Latent-lSVM for effectively classifying the very-high-dimensional and large-scale multi-class image datasets. The common framework of imageclassification tasks using the Scale-Invariant Feature Transform method (SIFT) and the Bag-of-visual-Words (BoW), leads tohard classification problem with thousands of dimensions and hundreds of classes. Our Latent-lSVM algorithm performs these complex tasks into two main steps. The first one is to use latent Dirichlet allocation (LDA) for assigning the image to some topics (clusters) with the corresponding probabilities. This aim is to reduce the number of classes and the number of datapoints in the cluster compared to the full dataset, followed by the second one: to learn a SVM model for each cluster to non-linearly classify the data locally. The numerical test results on seven real datasets showed that the Latent-lSVM algorithm achieves very high accuracy compared to state-of-the-art algorithms. An example of its effectiveness is given with an accuracy of 97.75% obtained in the classification of fingerprint dataset having 5000 dimensions into 389 classes.
Published: 2016

7. Dynamic local interaction model. Modèle et algorithms

Author: Arnaud Canu, Abdel-Illah Mouaddib, and François Poulet
Subjects: Interdependence, Set (abstract data type), Artificial Intelligence, Computer science, Combinatorial complexity, media_common.quotation_subject, Interaction model, Scaling, Algorithm, Software, media_common
Abstract: This article introduces DyLIM, a model derivated from DEC-POMDP. DyLIM is an interaction based approach, in which the agents are supposed to interact only sometimes, with some other agents (contrary to classical approaches which are based on the assumption of permanent and strong interactions). Moreover, DyLIM deals with evolving interactions (as opposed to predeﬁned ones). We are then able to describe the multiagent problem as a set of individual ones (sometimes interdependent), which breaks the combinatorial complexity. In a second time, we describe two different algorithms able to compute a solution for DyLIM, and we give experimental results based on a set of standard benchmarks. We ﬁnally show how our approach computes near-optimal policies, while scaling up to many agents.
Published: 2012

8. TreeView, exploration interactive des arbres de décision

Author: François Poulet, Thanh-Nghi Do, Annie Morin, Nguyen-Khang Pham, Multimedia content-based indexing (TEXMEX), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), College of Information and Communication Technology (CICT), Can Tho University [Vietnam] (CTU), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), and Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique
Subjects: Computer science, exploration interactive, Decision tree, 02 engineering and technology, computer.software_genre, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Artificial Intelligence, 020204 information systems, 0202 electrical engineering, electronic engineering, information engineering, Zoom, ComputingMilieux_MISCELLANEOUS, fouille visuelle de données, Radial tree, Incremental decision tree, business.industry, Usability, Visualization, Tree (data structure), qualité de connaissances, 020201 artificial intelligence & image processing, Data mining, post-traitement des arbres de décision, User interface, business, computer, Software
Abstract: We propose a graphical environment using the new radial tree layout, zoom/pan techniques and some existing methods, including explorer-like, hierarchical visualization, interactive techniques to represent large decision trees in a graphical mode more intuitive than the results in output of usual decision tree algorithms. The interactive exploration system on one hand can present the global view and on the other hand, it also provides a very good performance for an interesting sub-tree with simplicity, speed of task completion, ease of use and user understanding. The user can easily extract inductive rules and prune the tree in the post-processing stage. The numerical test results with real datasets show that the proposed methods have given an insight into decision tree results. It can guide the user towards for evaluating the models and also making more accurate decisions.
Published: 2008

9. Random Local SVMs for Classifying Large Datasets

Author: Thanh-Nghi Do and François Poulet
Subjects: Computer Science::Machine Learning, Correctness, business.industry, Computer science, k-means clustering, Pattern recognition, Machine learning, computer.software_genre, Ensemble learning, Partition (database), Support vector machine, ComputingMethodologies_PATTERNRECOGNITION, Computer Science::Computer Vision and Pattern Recognition, Artificial intelligence, Numerical tests, business, computer
Abstract: We propose a new parallel ensemble learning algorithm of random local support vector machines, called krSVM for the effectively non-linear classification of large datasets. The random local SVM in the krSVM learning strategy uses kmeans algorithm to partition the data into k clusters, followed which it constructs a non-linear SVM in each cluster to classify the data locally in the parallel way on multi-core computers. The krSVM algorithm is faster than the standard SVM in the non-linear classification of large datasets while maintaining the classification correctness. The numerical test results on 4 datasets from UCI repository and 3 benchmarks of handwritten letters recognition showed that our proposed algorithm is efficient compared to the standard SVM.
Published: 2015

10. Parallel Multiclass Logistic Regression for Classifying Large Scale Image Datasets

Author: François Poulet, Thanh-Nghi Do, Poulet, François, and Hoai An Le Thi - Ngoc Thanh Nguyen - Tien Van Do
Subjects: business.industry, Computer science, Parallel algorithm, Large numbers, Pattern recognition, [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], Logistic regression, Machine learning, computer.software_genre, Image (mathematics), Multiclass classification, Artificial intelligence, Numerical tests, business, Scale (map), computer, ComputingMilieux_MISCELLANEOUS
Abstract: The new parallel multiclass logistic regression algorithm (PAR-MC-LR) aims at classifying a very large number of images with very-high-dimensional signatures into many classes. We extend the two-class logistic regression algorithm (LR) in several ways to develop the new multiclass LR for efficiently classifying large image datasets into hundreds of classes. We propose the balanced batch stochastic gradient descend of logistic regression (BBatch-LR-SGD) for trainning two-class classifiers used in the one-versus-all strategy of the multiclass problems and the parallel training process of classifiers with several multi-core computers. The numerical test results on ImageNet datasets show that our algorithm is efficient compared to the state-of-the-art linear classifiers.
Published: 2015

11. FULL-VIEW: A VISUAL DATA-MINING ENVIRONMENT

Author: François Poulet
Subjects: Computer science, business.industry, Decision tree, computer.software_genre, Computer Graphics and Computer-Aided Design, Computer Science Applications, Visualization, Set (abstract data type), Information visualization, Interactivity, Software, Personal computer, Domain knowledge, Computer Vision and Pattern Recognition, Data mining, business, computer
Abstract: This paper presents a 3D user-centered interactive graphical environment dedicated to data mining. The aims of this environment are to involve the user in the data mining process (to use domain knowledge during the process), to improve comprehensibility (of both the data and the results of data mining algorithms), to improve interactivity and to use algorithms from various research areas: statistics, data analysis, visualization and machine learning. The environment is made of a set of bulletin boards where the graphical tools will be mapped; bulletin boards are predefined or can be user-defined. Several different visualization tools might be used in a single display, these tools are linked together to improve data comprehensibility. The tools available in the environment are both graphical and non-graphical tools, they can be used alone or in a cooperative way. One of these tools is more detailed: CIAD, a new graphical interactive decision tree construction algorithm that allows bivariate splits and so gives smaller trees (improving result comprehensibility). Its results are compared to existing decision tree algorithms. This environment can be used on any personal computer (it is based on open-source software and so, is platform independent) as well as on high performance graphical systems like reality centers.
Published: 2002

12. Large Scale Classifiers for Visual Classification Tasks

Author: François Poulet, Thanh-Nghi Do, Thanh-Nghi Doan, Multimedia content-based indexing (TEXMEX), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), Département Logique des Usages, Sciences sociales et Sciences de l'Information (LUSSI), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, and Institut Mines-Télécom [Paris] (IMT)-Télécom Bretagne-Université européenne de Bretagne - European University of Brittany (UEB)
Subjects: Computer Networks and Communications, business.industry, Computer science, 020207 software engineering, Pattern recognition, Linear classifier, 02 engineering and technology, Machine learning, computer.software_genre, Support vector machine, ComputingMethodologies_PATTERNRECOGNITION, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Hardware and Architecture, Incremental learning, 0202 electrical engineering, electronic engineering, information engineering, Media Technology, 020201 artificial intelligence & image processing, Artificial intelligence, business, computer, Classifier (UML), Software, ComputingMilieux_MISCELLANEOUS
Abstract: ImageNet dataset with more than 14 million images and 21,000 classes makes the problem of visual classification more difficult to deal with. One of the most difficult tasks is to train a fast and accurate visual classifier on several multi-core computers with limited individual memory resource. In this paper we address this challenge by extending both state-of-the-art large scale linear classifier (LIBLINEAR-CDBLOCK) and non-linear classifier (Power Mean SVM) for large scale visual classification tasks in these following ways: (1) an incremental learning method for Power Mean SVM, (2) a balanced bagging algorithm for training binary classifiers. Our approach has been evaluated on the 100 largest classes of ImageNet and ILSVRC 2010. The evaluation shows that our approach can save up to 82.01 % memory usage and the learning process is much faster than the original implementation and LIBLINEAR SVM.
Published: 2014

13. Large Scale Image Classification: Fast Feature Extraction, Multi-codebook Approach and Multi-core SVM Training

Author: François Poulet and Thanh-Nghi Doan
Subjects: Multi-core processor, Contextual image classification, business.industry, Computer science, Feature extraction, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Codebook, Scale-invariant feature transform, Pattern recognition, Support vector machine, ComputingMethodologies_PATTERNRECOGNITION, Discriminative model, Artificial intelligence, business, Classifier (UML)
Abstract: The usual frameworks for image classification involve three steps: extracting features, building codebook and encoding features, and training the classifier with a standard classification algorithm (e.g. SVMs). However, the task complexity becomes very large when applying these frameworks on a large scale dataset like ImageNet containing more than 14million images and 21,000 classes. The complexity is both about the time needed to perform each task and the memory and disk usage (e.g. 11TB are needed to store SIFT descriptors computed on the full dataset). We have developed a parallel version of LIBSVM to deal with very large datasets in reasonable time. Furthermore, a lot of information is lost when performing the quantization step and the obtained bag-of-words (or bag-of-visual-words) are often not enough discriminative for large scale image classification. We present a novel approach using several local descriptors simultaneously to try to improve the classification accuracy on large scale image datasets.We show our first results on a dataset made of the ten largest classes (24,807 images) from ImageNet.
Published: 2014

14. Community detection and visualization in social networks: integrating structural and semantic information

Author: Cécile Bothorel, Juan David Cruz, François Poulet, Lab-STICC_TB_CID_DECIDE, Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance (Lab-STICC), Université européenne de Bretagne - European University of Brittany (UEB)-École Nationale d'Ingénieurs de Brest (ENIB)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-Télécom Bretagne-Institut Brestois du Numérique et des Mathématiques (IBNM), Université de Brest (UBO)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Institut Mines-Télécom [Paris] (IMT)-Centre National de la Recherche Scientifique (CNRS)-Université européenne de Bretagne - European University of Brittany (UEB)-École Nationale d'Ingénieurs de Brest (ENIB)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-Télécom Bretagne-Institut Brestois du Numérique et des Mathématiques (IBNM), Université de Brest (UBO)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Institut Mines-Télécom [Paris] (IMT)-Centre National de la Recherche Scientifique (CNRS), Département Logique des Usages, Sciences sociales et Sciences de l'Information (LUSSI), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Multimedia content-based indexing (TEXMEX), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance ( Lab-STICC ), École Nationale d'Ingénieurs de Brest ( ENIB ) -Université de Bretagne Sud ( UBS ) -Université de Brest ( UBO ) -Télécom Bretagne-Institut Brestois du Numérique et des Mathématiques ( IBNM ), Université de Brest ( UBO ) -Université européenne de Bretagne ( UEB ) -ENSTA Bretagne-Institut Mines-Télécom [Paris]-Centre National de la Recherche Scientifique ( CNRS ) -École Nationale d'Ingénieurs de Brest ( ENIB ) -Université de Bretagne Sud ( UBS ) -Université de Brest ( UBO ) -Télécom Bretagne-Institut Brestois du Numérique et des Mathématiques ( IBNM ), Université de Brest ( UBO ) -Université européenne de Bretagne ( UEB ) -ENSTA Bretagne-Institut Mines-Télécom [Paris]-Centre National de la Recherche Scientifique ( CNRS ), Département Logique des Usages, Sciences sociales et Sciences de l'Information ( LUSSI ), Université européenne de Bretagne ( UEB ) -Télécom Bretagne-Institut Mines-Télécom [Paris], Multimedia content-based indexing ( TEXMEX ), Institut de Recherche en Informatique et Systèmes Aléatoires ( IRISA ), Université de Rennes 1 ( UR1 ), Université de Rennes ( UNIV-RENNES ) -Université de Rennes ( UNIV-RENNES ) -Institut National des Sciences Appliquées - Rennes ( INSA Rennes ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -Centre National de la Recherche Scientifique ( CNRS ) -Université de Rennes 1 ( UR1 ), Université de Rennes ( UNIV-RENNES ) -Université de Rennes ( UNIV-RENNES ) -Institut National des Sciences Appliquées - Rennes ( INSA Rennes ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -Centre National de la Recherche Scientifique ( CNRS ) -Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique ( Inria ), École Nationale d'Ingénieurs de Brest (ENIB)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-Télécom Bretagne-Institut Brestois du Numérique et des Mathématiques (IBNM), Université de Brest (UBO)-Université européenne de Bretagne - European University of Brittany (UEB)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Institut Mines-Télécom [Paris] (IMT)-Centre National de la Recherche Scientifique (CNRS)-École Nationale d'Ingénieurs de Brest (ENIB)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-Télécom Bretagne-Institut Brestois du Numérique et des Mathématiques (IBNM), Université de Brest (UBO)-Université européenne de Bretagne - European University of Brittany (UEB)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Institut Mines-Télécom [Paris] (IMT)-Centre National de la Recherche Scientifique (CNRS), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), and Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique
Subjects: Information retrieval, Social network, Computer science, business.industry, Information sharing, Community structure, 020207 software engineering, 02 engineering and technology, [ INFO.INFO-LG ] Computer Science [cs]/Machine Learning [cs.LG], Theoretical Computer Science, Visualization, World Wide Web, Knowledge extraction, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Artificial Intelligence, 0202 electrical engineering, electronic engineering, information engineering, Unsupervised learning, 020201 artificial intelligence & image processing, Cluster analysis, business, ComputingMilieux_MISCELLANEOUS, Clustering coefficient
Abstract: Due to the explosion of social networking and the information sharing among their users, the interest in analyzing social networks has increased over the recent years. Two general interests in this kind of studies are community detection and visualization. In the first case, most of the classic algorithms for community detection use only the structural information to identify groups, that is, how clusters are formed according to the topology of the relationships. However, these methods do not take into account any semantic information which could guide the clustering process, and which may add elements to conduct further analyses. In the second case most of the layout algorithms for clustered graphs have been designed to differentiate the groups within the graph, but they are not designed to analyze the interactions between such groups. Identifying these interactions gives an insight into the way different communities exchange messages or information, and allows the social network researcher to identify key actors, roles, and paths from one community to another. This article presents a novel model to use, in a conjoint way, the semantic information from the social network and its structural information to, first, find structurally and semantically related groups of nodes, and second, a layout algorithm for clustered graphs which divides the nodes into two types, one for nodes with edges connecting other communities and another with nodes connecting nodes only within their own community. With this division the visualization tool focuses on the connections between groups facilitating deep studies of augmented social networks.
Published: 2013

15. Parallel incremental SVM for classifying million images with very high-dimensional signatures into thousand classes

Author: Thanh-Nghi Do, Thanh-Nghi Doan, François Poulet, Multimedia content-based indexing (TEXMEX), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), Département Logique des Usages, Sciences sociales et Sciences de l'Information (LUSSI), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Angelov, Plamen and Levine, Daniel and Erdi, Péter, Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, and Institut Mines-Télécom [Paris] (IMT)-Télécom Bretagne-Université européenne de Bretagne - European University of Brittany (UEB)
Subjects: Contextual image classification, business.industry, Computer science, Pattern recognition, Linear classifier, 02 engineering and technology, High dimensional, 010501 environmental sciences, Machine learning, computer.software_genre, 01 natural sciences, Support vector machine, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Incremental learning, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Artificial intelligence, business, Classifier (UML), computer, ComputingMilieux_MISCELLANEOUS, 0105 earth and related environmental sciences
Abstract: ImageNet dataset [1] with more than 14M images and 21K classes makes the problem of visual classification more difficult to deal with. One of the most difficult tasks is to train a fast and accurate classifier on computers with limited memory resource. In this paper, we address this challenge by extending the state-of-the-art large scale classifier Power Mean SVM (PmSVM) proposed by Jianxin Wu [2] in three ways: (1) An incremental learning for PmSVM, (2) A balanced bagging algorithm for training binary classifiers, (3) Parallelize the training process of classifiers with several multi-core computers. Our approach is evaluated on 1K classes of ImageNet (ILSVRC 1000 [3]). The evaluation shows that our approach can save up to 84.34% memory usage and the training process is 297 times faster than the original implementation and 1508 times faster than the state-of-the-art linear classifier (LIBLINEAR [4]).
Published: 2013

16. Multi-way Classification for Large Scale Visual Object Dataset

Author: François Poulet, Thanh-Nghi Doan, Thanh-Nghi Do, Multimedia content-based indexing (TEXMEX), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), Département Logique des Usages, Sciences sociales et Sciences de l'Information (LUSSI), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), László Czúni, Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, and Institut Mines-Télécom [Paris] (IMT)-Télécom Bretagne-Université européenne de Bretagne - European University of Brittany (UEB)
Subjects: Multi-core processor, Power mean, Computer science, business.industry, Binary number, 020207 software engineering, Pattern recognition, Linear classifier, 02 engineering and technology, Machine learning, computer.software_genre, Support vector machine, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Incremental learning, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Artificial intelligence, business, Classifier (UML), computer, ComputingMilieux_MISCELLANEOUS
Abstract: ImageNet dataset [1] with more than 14M images and 21K classes makes the problem of visual classification more difficult to deal with. One of the most difficult tasks is to train a fast and accurate classifier. In this paper, we address this challenge by extending the state-of-the-art large scale classifier Power Mean SVM (PmSVM) proposed by Jianxin Wu [2] in three ways: (1) An incremental learning for PmSVM, (2) A balanced bagging algorithm for training binary classifiers, (3) Parallelize the training process of classifiers with several multicore computers. Our approach is evaluated on 1K classes of ImageNet (ILSVRC 1000 [3]). The evaluation shows that our approach can save up to 82.01% memory usage and the training process is 255 times faster than the original implementation and 1276 times faster than the state-of-the-art linear classifier (LIBLINEAR [4]).
Published: 2013

17. Layout Algorithm for Clustered Graphs to Analyze Community Interactions in Social Networks

Author: Cécile Bothorel, François Poulet, Juan David Cruz, Lab-STICC_TB_CID_DECIDE, Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance (Lab-STICC), École Nationale d'Ingénieurs de Brest (ENIB)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-Télécom Bretagne-Institut Brestois du Numérique et des Mathématiques (IBNM), Université de Brest (UBO)-Université européenne de Bretagne - European University of Brittany (UEB)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Institut Mines-Télécom [Paris] (IMT)-Centre National de la Recherche Scientifique (CNRS)-École Nationale d'Ingénieurs de Brest (ENIB)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-Télécom Bretagne-Institut Brestois du Numérique et des Mathématiques (IBNM), Université de Brest (UBO)-Université européenne de Bretagne - European University of Brittany (UEB)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Institut Mines-Télécom [Paris] (IMT)-Centre National de la Recherche Scientifique (CNRS), Département Logique des Usages, Sciences sociales et Sciences de l'Information (LUSSI), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Multimedia content-based indexing (TEXMEX), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), Université européenne de Bretagne - European University of Brittany (UEB)-École Nationale d'Ingénieurs de Brest (ENIB)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-Télécom Bretagne-Institut Brestois du Numérique et des Mathématiques (IBNM), Université de Brest (UBO)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Institut Mines-Télécom [Paris] (IMT)-Centre National de la Recherche Scientifique (CNRS)-Université européenne de Bretagne - European University of Brittany (UEB)-École Nationale d'Ingénieurs de Brest (ENIB)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-Télécom Bretagne-Institut Brestois du Numérique et des Mathématiques (IBNM), Université de Brest (UBO)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Institut Mines-Télécom [Paris] (IMT)-Centre National de la Recherche Scientifique (CNRS), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, Poulet, François, Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance ( Lab-STICC ), École Nationale d'Ingénieurs de Brest ( ENIB ) -Université de Bretagne Sud ( UBS ) -Université de Brest ( UBO ) -Télécom Bretagne-Institut Brestois du Numérique et des Mathématiques ( IBNM ), Université de Brest ( UBO ) -Université européenne de Bretagne ( UEB ) -ENSTA Bretagne-Institut Mines-Télécom [Paris]-Centre National de la Recherche Scientifique ( CNRS ) -École Nationale d'Ingénieurs de Brest ( ENIB ) -Université de Bretagne Sud ( UBS ) -Université de Brest ( UBO ) -Télécom Bretagne-Institut Brestois du Numérique et des Mathématiques ( IBNM ), Université de Brest ( UBO ) -Université européenne de Bretagne ( UEB ) -ENSTA Bretagne-Institut Mines-Télécom [Paris]-Centre National de la Recherche Scientifique ( CNRS ), Département Logique des Usages, Sciences sociales et Sciences de l'Information ( LUSSI ), Université européenne de Bretagne ( UEB ) -Télécom Bretagne-Institut Mines-Télécom [Paris], Multimedia content-based indexing ( TEXMEX ), Institut de Recherche en Informatique et Systèmes Aléatoires ( IRISA ), Université de Rennes 1 ( UR1 ), Université de Rennes ( UNIV-RENNES ) -Université de Rennes ( UNIV-RENNES ) -Institut National des Sciences Appliquées - Rennes ( INSA Rennes ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -Centre National de la Recherche Scientifique ( CNRS ) -Université de Rennes 1 ( UR1 ), Université de Rennes ( UNIV-RENNES ) -Université de Rennes ( UNIV-RENNES ) -Institut National des Sciences Appliquées - Rennes ( INSA Rennes ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -Centre National de la Recherche Scientifique ( CNRS ) -Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique ( Inria ), Institut Mines-Télécom [Paris] (IMT)-Télécom Bretagne-Université européenne de Bretagne - European University of Brittany (UEB), and Télécom Bretagne (devenu IMT Atlantique), Ex-Bibliothèque
Subjects: Computer science, Community interactions, Clustered graphs layout, 02 engineering and technology, Machine learning, computer.software_genre, Multi-Dimensional Scaling, [ INFO.INFO-LG ] Computer Science [cs]/Machine Learning [cs.LG], [INFO.INFO-SI]Computer Science [cs]/Social and Information Networks [cs.SI], [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], 0202 electrical engineering, electronic engineering, information engineering, Multidimensional scaling, Cluster analysis, ComputingMilieux_MISCELLANEOUS, [ INFO.INFO-SI ] Computer Science [cs]/Social and Information Networks [cs.SI], Social network, Community, business.industry, [INFO.INFO-SI] Computer Science [cs]/Social and Information Networks [cs.SI], 020207 software engineering, Graph theory, [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], Data science, Graph, Visualization, Node centrality, 020201 artificial intelligence & image processing, Algorithm design, Artificial intelligence, business, computer
Abstract: International audience; Most layout algorithms for clustered graphs have been designed to differentiate the groups within the graph, however they do not take into account the interactions between such groups. Identifying these interactions allows to understand how the different communities exchange messages or information, and allows the social network researcher identifying key actors, social roles and paths from one community to another. These interactions are performed by actors who actually share links with different communities. Thus, dividing the set of nodes into those who interact with several communities and those who only interact with their own communities, will give some insight about how the communities interact.
Published: 2013

18. Large Scale Image Classification with Many Classes, Multi-features and Very High-Dimensional Signatures

Author: François Poulet, Thanh-Nghi Do, Thanh-Nghi Doan, Multimedia content-based indexing (TEXMEX), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), Département Logique des Usages, Sciences sociales et Sciences de l'Information (LUSSI), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, and Institut Mines-Télécom [Paris] (IMT)-Télécom Bretagne-Université européenne de Bretagne - European University of Brittany (UEB)
Subjects: Contextual image classification, business.industry, Computer science, Codebook, Process (computing), Pattern recognition, Scale (descriptive set theory), 02 engineering and technology, Supercomputer, ComputingMethodologies_PATTERNRECOGNITION, 020401 chemical engineering, Discriminative model, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Encoding (memory), 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Artificial intelligence, 0204 chemical engineering, Quantization (image processing), business, ComputingMilieux_MISCELLANEOUS
Abstract: The usual frameworks for image classification involve three steps: extracting features, building codebook and encoding features, and training the classifiers with a standard classification algorithm. However, the task complexity becomes very large when performing on a large dataset ImageNet [1] containing more than 14M images and 21K classes. The complexity is about the time needed to perform each task and the memory. In this paper, we propose an efficient framework for large scale image classification. We extend LIBLINEAR developed by Rong-En Fan [2] in two ways: (1) The first one is to build the balanced bagging classifiers with under-sampling strategy. Our algorithm avoids training on full data, and the training process rapidly converges to the solution, (2) The second one is to parallelize the training process of all classifiers with a multi-core computer. The evaluation on the 100 largest classes of ImageNet shows that our approach is 10 times faster than the original LIBLINEAR, 157 times faster than our parallel version of LIBSVM and 690 times faster than OCAS [3]. Furthermore, a lot of information is lost in quantization step and the obtained bag-of-words is not enough discriminative power for classification. Therefore, we propose a novel approach using several local descriptors simultaneously.
Published: 2013

19. Large Scale Visual Classification with Many Classes

Author: François Poulet, Thanh-Nghi Doan, Thanh-Nghi Do, Multimedia content-based indexing (TEXMEX), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), Département Logique des Usages, Sciences sociales et Sciences de l'Information (LUSSI), Institut Mines-Télécom [Paris] (IMT)-Télécom Bretagne-Université européenne de Bretagne - European University of Brittany (UEB), Petra Perner, Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, and Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT)
Subjects: Power mean, business.industry, Computer science, Codebook, Linear classifier, Pattern recognition, 02 engineering and technology, Machine learning, computer.software_genre, Supercomputer, Support vector machine, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], 020401 chemical engineering, Full data, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Artificial intelligence, 0204 chemical engineering, business, computer, Classifier (UML), ComputingMilieux_MISCELLANEOUS
Abstract: The usual frameworks for visual classification involve three steps: extracting features, building codebook and encoding features, and training classifiers. The current release of ImageNet dataset [1] with more than 14M images and 21K classes makes the problem of visual classification become more difficult to deal with. One of the most difficult tasks is to train a fast and accurate classifier. In this paper, we address this challenge by extending the state-of-the-art large scale classifier Power Mean SVM (PmSVM) proposed by Jianxin Wu [2] in two ways: (1) The first one is to build the balanced bagging classifiers with under-sampling strategy. Our algorithm avoids training on full data and the training process of PmSVM rapidly converges to the optimal solution, (2) The second one is to parallelize the training process of all classifiers with multi-core computers. We have developed the parallel versions of PmSVM based on high performance computing models. The evaluation on 1000 classes of ImageNet (ILSVRC 1000 [3]) shows that our approach is 90 times faster than the original implementation of PmSVM and 240 times faster than the state-of-the-art linear classifier (LIBLINEAR [4]).
Published: 2013

20. Entropy based community detection in augmented social networks

Author: Cécile Bothorel, François Poulet, Juan David Cruz, Département Logique des Usages, Sciences sociales et Sciences de l'Information (LUSSI), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Lab-STICC_TB_CID_DECIDE, Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance (Lab-STICC), Université européenne de Bretagne - European University of Brittany (UEB)-École Nationale d'Ingénieurs de Brest (ENIB)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-Télécom Bretagne-Institut Brestois du Numérique et des Mathématiques (IBNM), Université de Brest (UBO)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Institut Mines-Télécom [Paris] (IMT)-Centre National de la Recherche Scientifique (CNRS)-Université européenne de Bretagne - European University of Brittany (UEB)-École Nationale d'Ingénieurs de Brest (ENIB)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-Télécom Bretagne-Institut Brestois du Numérique et des Mathématiques (IBNM), Université de Brest (UBO)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Institut Mines-Télécom [Paris] (IMT)-Centre National de la Recherche Scientifique (CNRS), Multimedia content-based indexing (TEXMEX), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), École Nationale d'Ingénieurs de Brest (ENIB)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-Télécom Bretagne-Institut Brestois du Numérique et des Mathématiques (IBNM), Université de Brest (UBO)-Université européenne de Bretagne - European University of Brittany (UEB)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Institut Mines-Télécom [Paris] (IMT)-Centre National de la Recherche Scientifique (CNRS)-École Nationale d'Ingénieurs de Brest (ENIB)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-Télécom Bretagne-Institut Brestois du Numérique et des Mathématiques (IBNM), Université de Brest (UBO)-Université européenne de Bretagne - European University of Brittany (UEB)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Institut Mines-Télécom [Paris] (IMT)-Centre National de la Recherche Scientifique (CNRS), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, Département Logique des Usages, Sciences sociales et Sciences de l'Information ( LUSSI ), Université européenne de Bretagne ( UEB ) -Télécom Bretagne-Institut Mines-Télécom [Paris], Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance ( Lab-STICC ), École Nationale d'Ingénieurs de Brest ( ENIB ) -Université de Bretagne Sud ( UBS ) -Université de Brest ( UBO ) -Télécom Bretagne-Institut Brestois du Numérique et des Mathématiques ( IBNM ), Université de Brest ( UBO ) -Université européenne de Bretagne ( UEB ) -ENSTA Bretagne-Institut Mines-Télécom [Paris]-Centre National de la Recherche Scientifique ( CNRS ) -École Nationale d'Ingénieurs de Brest ( ENIB ) -Université de Bretagne Sud ( UBS ) -Université de Brest ( UBO ) -Télécom Bretagne-Institut Brestois du Numérique et des Mathématiques ( IBNM ), Université de Brest ( UBO ) -Université européenne de Bretagne ( UEB ) -ENSTA Bretagne-Institut Mines-Télécom [Paris]-Centre National de la Recherche Scientifique ( CNRS ), Multimedia content-based indexing ( TEXMEX ), Institut de Recherche en Informatique et Systèmes Aléatoires ( IRISA ), Université de Rennes 1 ( UR1 ), Université de Rennes ( UNIV-RENNES ) -Université de Rennes ( UNIV-RENNES ) -Institut National des Sciences Appliquées - Rennes ( INSA Rennes ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -Centre National de la Recherche Scientifique ( CNRS ) -Université de Rennes 1 ( UR1 ), Université de Rennes ( UNIV-RENNES ) -Université de Rennes ( UNIV-RENNES ) -Institut National des Sciences Appliquées - Rennes ( INSA Rennes ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -Centre National de la Recherche Scientifique ( CNRS ) -Inria Rennes – Bretagne Atlantique, and Institut National de Recherche en Informatique et en Automatique ( Inria )
Subjects: Graph Clustering, Dynamic network analysis, Computer science, Entropy, [INFO.INFO-DS]Computer Science [cs]/Data Structures and Algorithms [cs.DS], Network science, 02 engineering and technology, [ MATH.MATH-IT ] Mathematics [math]/Information Theory [math.IT], computer.software_genre, Clique percolation method, [ INFO.INFO-LG ] Computer Science [cs]/Machine Learning [cs.LG], [ INFO.INFO-IT ] Computer Science [cs]/Information Theory [cs.IT], [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], 020204 information systems, 0202 electrical engineering, electronic engineering, information engineering, Entropy (information theory), Social Networks Analysis, Cluster analysis, [ INFO.INFO-DS ] Computer Science [cs]/Data Structures and Algorithms [cs.DS], Clustering coefficient, Community structure, [MATH.MATH-IT]Mathematics [math]/Information Theory [math.IT], Graph theory, [INFO.INFO-IT]Computer Science [cs]/Information Theory [cs.IT], 020201 artificial intelligence & image processing, Data mining, computer, Community Detection
Abstract: International audience; Social network analysis has become a major subject in recent times, bringing also several challenges in the computer science field. One aspect of the social network analysis is the community detection problem, which is seen as a graph clustering problem. However, social networks are more than a graph, they have an interesting amount of information derived from its social aspect, such as profile information, content sharing and annotations, among others. Most of the community detection algorithms use only the structure of the network, i.e., the graph. In this paper we propose a new method which uses the semantic information along with the network structure in the community detection process. Thus, our method combines an algorithm for optimizing modularity and an entropy-based data clustering algorithm, which tries to find a partition with low entropy and keeping in mind the modularity.
Published: 2011

21. High Dimensional Image Categorization

Author: François Poulet, Nguyen-Khang Pham, Multimedia content-based indexing (TEXMEX), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), College of Information and Communication Technology (CICT), Can Tho University [Vietnam] (CTU), Longbing Cao, Yong Feng, Jiang Zhong, Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), and Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique
Subjects: Analysis of parallel algorithms, Computer science, business.industry, Parallel algorithm, Pattern recognition, 010103 numerical & computational mathematics, 02 engineering and technology, Orders of magnitude (volume), 01 natural sciences, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Support vector machine, Data point, Categorization, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Artificial intelligence, 0101 mathematics, Graphics, Quantization (image processing), business, ComputingMilieux_MISCELLANEOUS
Abstract: We are interested in varying the vocabulary size in the image categorization task with a bag-of-visual-words to investigate its influence on the classification accuracy in two cases: in the first one, both the test-set and the training set contains the same objects (with only different view points in the test-set) and the second one where objects in the test-set do not appear at all in the training set (only other objects from the same category appear). In order to perform these tasks, we need to scale-up the algorithms used to deal with millions data points in hundred of thousand dimensions. We present k-means (used in the quantization step) and SVM (used in the classification step) algorithms extended to deal with very large datasets. These new incremental and parallel algorithms can be used on various distributed architectures, like multithread computer, cluster or GPU (graphics processing units). The efficiency of the approach is shown with the categorization of the 3D-Dataset from Savarese and Fei-Fei containing about 6700 images of 3D objects from 10 different classes. The obtained incremental and parallel SVM algorithm is several orders of magnitude faster than usual ones (like lib-SVM, SVM-perf or CB-SVM) and the incremental and parallel k-means is at least one order of magnitude faster than usual implementations.
Published: 2010

22. Speed Up SVM Algorithm for Massive Classification Tasks

Author: François Poulet, Van Hoa Nguyen, and Thanh-Nghi Do
Subjects: Speedup, Computer science, business.industry, Population-based incremental learning, Parallel algorithm, Parallel computing, Machine learning, computer.software_genre, Support vector machine, ComputingMethodologies_PATTERNRECOGNITION, Kernel (statistics), Least squares support vector machine, Artificial intelligence, SIMD, Graphics, business, Algorithm, computer
Abstract: We present a new parallel and incremental Support Vector Machine (SVM) algorithm for the classification of very large datasets on graphics processing units (GPUs). SVM and kernel related methods have shown to build accurate models but the learning task usually needs a quadratic program so that this task for large datasets requires large memory capacity and long time. We extend a recent Least Squares SVM (LS-SVM) proposed by Suykens and Vandewalle for building incremental and parallel algorithm. The new algorithm uses graphics processors to gain high performance at low cost. Numerical test results on UCI and Delve dataset repositories showed that our parallel incremental algorithm using GPUs is about 70 times faster than a CPU implementation and often significantly faster (over 1000 times) than state-of-the-art algorithms like LibSVM, SVM-perf and CB-SVM.
Published: 2008

23. Towards Effective Visual Data Mining with Cooperative Approaches

Author: François Poulet
Subjects: Visualization methods, Computer science, business.industry, Decision tree learning, Visualization algorithms, computer.software_genre, Machine learning, Tree node, Visualization, Support vector machine, Mode (computer interface), Coupling (computer programming), Data mining, Artificial intelligence, business, computer
Abstract: Visual data-mining strategy lies in tightly coupling the visualizations and analytical processes into one data-mining tool that takes advantage of the strengths from multiple sources. We present concrete cooperation between automatic algorithms, interactive algorithms and visualization methods. The first kind of cooperation is an interactive decision tree algorithm CIAD. It allows the user to be helped by an automatic algorithm based on a support vector machine (SVM) to optimize the interactive split performed in the current tree node or to compute the best split in an automatic mode. Another effective cooperation is a visualization algorithm used to explain the results of SVM algorithm. The same visualization method can also be used to help the user in the parameters tuning step in input of automatic SVM algorithms. Then we present methods using both automatic and interactive methods to deal with very large datasets. The obtained results let us think it is a promising way to deal with very large datasets.
Published: 2008

24. Interactive Decision Tree Construction for Interval and Taxonomical Data

Author: François Poulet, Thanh-Nghi Do, Multimedia content-based indexing (TEXMEX), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), College of Information and Communication Technology (CICT), Can Tho University [Vietnam] (CTU), Simeon Simoff, Mihael Boehlen, Arturas Mazeikas, Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), and Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique
Subjects: Incremental decision tree, Computer science, Decision tree learning, Decision tree, Mode (statistics), 020207 software engineering, 02 engineering and technology, Interval (mathematics), computer.software_genre, Tree node, Continuous data, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Coupling (computer programming), [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Data mining, [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], computer, ComputingMilieux_MISCELLANEOUS
Abstract: Visual data-mining strategy lies in tightly coupling the visualizations and analytical processes into one data-mining tool that takes advantage of the assets from multiple sources. This paper presents two graphical interactive decision tree construction algorithms able to deal either with (usual) continuous data or with interval and taxonomical data. They are the extensions of two existing algorithms: CIAD [17] and PBC [3]. Both CIAD and PBC algorithms can be used in an interactive or cooperative mode (with an automatic algorithm to find the best split of the current tree node). We have modified the corresponding help mechanisms to allow them to deal with interval-valued attributes. Some of the results obtained on interval-valued and taxonomical data sets are presented with the methods we have used to create these data sets.
Published: 2008

25. High Dimensional Visual Data Classification

Author: François Poulet
Subjects: Interactive visual analysis, Computer science, Data stream mining, Decision tree learning, Pattern recognition (psychology), Data classification, Decision tree, Data mining, External Data Representation, computer.software_genre, computer, Visualization
Abstract: We present new visual data mining algorithms for interactive decision tree construction with large datasets. The size of data stored in the world is constantly increasing but the limits of current visual data mining (and visualization) methods concerning the number of items and dimensions of the dataset treated are well known (even with pixellisation methods). One solution to improve these methods is to use a higher-level representation of the data, for example a symbolic data representation. Our new interactive decision tree construction algorithms deal with interval and taxonomical data. With such a representation, we are able to deal with potentially very large datasets because we do not use the original data but higher-level data representation. Interactive algorithms are examples of new data mining approach aiming at involving more intensively the user in the process. The main advantages of this user-centered approach are the increased confidence and comprehensibility of the obtained model, because the user was involved in its construction and the possible use of human pattern recognition capabilities. We present some results we obtained on very large datasets.
Published: 2007

26. Classifying one billion data with a new distributed svm algorithm

Author: François Poulet and Thanh-Nghi Do
Subjects: Computer Science::Machine Learning, business.industry, Computer science, Pentium, Pattern recognition, Linear classifier, Machine learning, computer.software_genre, Support vector machine, Kernel (linear algebra), ComputingMethodologies_PATTERNRECOGNITION, Distributed algorithm, Least squares support vector machine, Artificial intelligence, Quadratic programming, Cluster analysis, business, Algorithm, computer
Abstract: The new incremental, parallel and distributed Support Vector Machine (SVM) algorithm using linear or non linear kernels proposed in this paper aims at classifying very large datasets on standard personal computers (PCs). SVM and kernel related methods have shown to build accurate models but the learning task usually needs a quadratic program so that the learning task for large datasets requires large memory capacity and long time. We extend a recent Least Squares SVM (LS-SVM) proposed by Suykens and Vandewalle for building incremental, parallel and distributed SVM algorithm. The new algorithm is very fast and can handle very large datasets in linear or non- linear classification tasks on PCs. An example of the effectiveness is given with the linear classification into two classes of one billion datapoints in 20-dimensional input space in some minutes on ten PCs (3 GHz Pentium IV, 512 MB RAM).
Published: 2006

27. Mining Very Large Datasets with Support Vector Machine Algorithms

Author: Thanh-Nghi Do and François Poulet
Subjects: Structured support vector machine, business.industry, Computer science, Pentium, Pattern recognition, Extension (predicate logic), Machine learning, computer.software_genre, Least squares, Support vector machine, Relevance vector machine, symbols.namesake, ComputingMethodologies_PATTERNRECOGNITION, Incremental learning, symbols, Artificial intelligence, business, Newton's method, Algorithm, computer
Abstract: In this paper, we present new support vector machines (SVM) algorithms that can be used to classify very large datasets on standard personal computers. The algorithms have been extended from three recent SVMs algorithms: least squares SVM classification, finite Newton method for classification and incremental proximal SVM classification. The extension consists in building incremental, parallel and distributed SVMs for classification. Our three new algorithms are very fast and can handle very large datasets. An example of the effectiveness of these new algorithms is given with the classification into two classes of one billion points in 10-dimensional input space in some minutes on ten personal computers (800 MHz Pentium III, 256 MB RAM, Linux).
Published: 2006

28. SVM and Graphical Algorithms: A Cooperative Approach

Author: François Poulet
Subjects: Structured support vector machine, Computer science, business.industry, media_common.quotation_subject, computer.software_genre, Machine learning, Visualization, Data set, Support vector machine, ComputingMethodologies_PATTERNRECOGNITION, Data visualization, Ranking SVM, Quality (business), Data mining, Artificial intelligence, business, Representation (mathematics), Algorithm, computer, media_common
Abstract: We present a cooperative approach using both support vector machine (SVM) algorithms and visualization methods. SVM are widely used today and often give high quality results, but they are used as "black-box" (it is very difficult to explain the obtained results) and cannot treat easily very large datasets. We have developed graphical methods to help the user to evaluate and explain the SVM results. The first method is a graphical representation of the separating frontier quality, it is then linked with other visualization tools to help the user explaining SVM results. The information provided by these graphical methods is also used for SVM parameter tuning, they are then used together with automatic algorithms to deal with very large datasets on standard computers. We present an evaluation of our approach with the UCI and the Kent Ridge Bio-medical data sets.
Published: 2005

29. Visual Interactive Evolutionary Algorithm for High Dimensional Data Clustering and Outlier Detection

Author: Lydia Boudjeloud and François Poulet
Subjects: Clustering high-dimensional data, Computer science, business.industry, Evolutionary algorithm, Interactive evolutionary computation, computer.software_genre, Machine learning, Visualization, Matrix (mathematics), Data visualization, Search algorithm, Genetic algorithm, Outlier, Anomaly detection, Data mining, Artificial intelligence, business, Cluster analysis, computer, Curse of dimensionality
Abstract: Usual visualization techniques for multidimensional data sets, such as parallel coordinates and scatter-plot matrices, do not scale well to high numbers of dimensions. A common approach to solve this problem is dimensionality selection. Existing dimensionality selection techniques usually select pertinent dimension subsets that are significant to the user without loose of information. We present concrete cooperation between automatic algorithms, interactive algorithms and visualization tools: the evolutionary algorithm is used to obtain optimal dimension subsets which represent the original data set without loosing information for unsupervised mode (clustering or outlier detection). The last effective cooperation is a visualization tool used to present the user interactive evolutionary algorithm results and let him actively participate in evolutionary algorithm searching with more efficiency resulting in a faster evolutionary algorithm convergence. We have implemented our approach and applied it to real data set to confirm this approach is effective for supporting the user in the exploration of high dimensional data sets.
Published: 2005

30. User guidance: from theory to practice, the case of visual data mining

Author: François Poulet and E.F. Badjio
Subjects: Data set, Text mining, business.industry, Data stream mining, Computer science, Theory to practice, Concept mining, Data mining, Marketing and artificial intelligence, computer.software_genre, business, computer, Domain (software engineering)
Abstract: We present two modules for users' guidance in visual data mining (VDM) domain which use artificial intelligence. User guidance refers to the available ways to advise, orient, instruct, and inform the users throughout their interactions with a computer. The first module allows recommending best available data mining algorithms to users and the second module aims at reducing attributes and/or data items in very large data sets to be visually mined
Published: 2005

31. Enhancing SVM with Visualization

Author: François Poulet and Thanh-Nghi Do
Subjects: Computer science, business.industry, computer.software_genre, Machine learning, Task (project management), Visualization, Support vector machine, Information extraction, ComputingMethodologies_PATTERNRECOGNITION, Black box, Ranking SVM, Pattern recognition (psychology), Data mining, Artificial intelligence, Graphics, business, computer
Abstract: Understanding the result produced by a data-mining algorithm is as important as the accuracy. Unfortunately, support vector machine (SVM) algorithms provide only the support vectors used as “black box” to efficiently classify the data with a good accuracy. This paper presents a cooperative approach using SVM algorithms and visualization methods to gain insight into a model construction task with SVM algorithms. We show how the user can interactively use cooperative tools to support the construction of SVM models and interpret them. A pre-processing step is also used for dealing with large datasets. The experimental results on Delve, Statlog, UCI and bio-medical datasets show that our cooperative tool is comparable to the automatic LibSVM algorithm, but the user has a better understanding of the obtained model.
Published: 2004

32. Latent‐lSVM classification of very high‐dimensional and large‐scale multi‐class datasets

Author: Thanh-Nghi Do, François Poulet, Can Tho University [Vietnam] (CTU), MEDIA ET INTERACTIONS (IRISA-D6), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), and Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes 1 (UR1)
Subjects: parallel learning on multi-core computers, Computer Networks and Communications, Computer science, Scale (descriptive set theory), 02 engineering and technology, computer.software_genre, Latent Dirichlet allocation, Theoretical Computer Science, Image (mathematics), symbols.namesake, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], 0202 electrical engineering, electronic engineering, information engineering, high-dimensional and large-scale multi-class data classification, business.industry, Latent Dirichlet Allocation (LDA), 020206 networking & telecommunications, Pattern recognition, support vector machines (SVMs), Class (biology), Computer Science Applications, Support vector machine, Nonlinear system, ComputingMethodologies_PATTERNRECOGNITION, Computational Theory and Mathematics, symbols, 020201 artificial intelligence & image processing, Data mining, Artificial intelligence, business, computer, Software
Abstract: We propose a new parallel learning algorithm of latent local support vector machines (SVM), called latent-lSVM for effectively classifying very high-dimensional and large-scale multi-class datasets. The common framework of texts/images classification tasks using the Bag-Of-(visual)-Words model for the data representation leads to hard classification problem with thousands of dimensions and hundreds of classes.Ourlatent-lSVM algorithm performs these complex tasks into two main steps. The first one is to use latent Dirichlet allocation for assigning the datapoint (text/image) to some topics (clusters) with the corresponding probabilities. This aims at reducing the number of classes and the number of datapoints in the cluster compared to the full dataset, followed by the second one: to learn in a parallel way nonlinear SVM models to classify data clusters locally. The numerical test results on nine real datasets show that the latent-lSVM algorithm achieves very high accuracy compared to state-of-the-art algorithms. An example of its effectiveness is given with an accuracy of 70.14% obtained in the classification of Book dataset having 100 000 individuals in 89 821 dimensional input space and 661 classes in 11.2minutes using a PC Intel(R) Core i7-4790 CPU, 3.6 GHz, 4 cores.
Full Text: View/download PDF

33. Multiscale scatterplot matrix for visual and interactive exploration of metabonomic data

Author: Pierre-Yves Koenig, Fabien Jourdan, Alain Paris, Guy Melançon, ProdInra, Migration, Xénobiotiques, Institut National de la Recherche Agronomique (INRA)-Ecole Nationale Vétérinaire de Toulouse (ENVT), Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées, Fouille de données environnementales (TATOO), Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier (LIRMM), Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM), Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM), Pierre Levy, François Poulet, Ecole Nationale Vétérinaire de Toulouse (ENVT), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut National de la Recherche Agronomique (INRA), Université Montpellier 2 - Sciences et Techniques (UM2), Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS), and Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)
Subjects: interface humain-ordinateur, Computer science, Drug taking, [SDV]Life Sciences [q-bio], gaussian blur, Gaussian blur, Image processing, 02 engineering and technology, filtre statistique de densité, Machine learning, computer.software_genre, 01 natural sciences, matrix de scatterplot, 010104 statistics & probability, symbols.namesake, Information visualization, [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST], human-computer interaction, 0202 electrical engineering, electronic engineering, information engineering, [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], 0101 mathematics, statistical density function, business.industry, 020207 software engineering, Pattern recognition, Density estimation, scatterplot matrix, [SDV] Life Sciences [q-bio], flou gaussien, symbols, Artificial intelligence, business, computer, Intuition
Abstract: International audience; We describe a method turning scatterplot matrix visualizations into malleable graphical objects facilitating interaction and selection of pixelized data elements. The method relies on density estimation techniques [1, 2] applied through standard image processing. A 2D scatterplot is considered as an image and is then transformed into nested regions that can be easily selected. Based on Wattenberg and Fisher, and as confirmed by our experience, we believe users have a good intuition interpreting and interacting with these multiscale graphical objects. Bio-molecular data serves here as a case study for our methodology. The method was discussed and designed in collaboration with experts in metabonomics and has proven to be useful and complementary to classical statistical methods.
Published: 2007

Catalog

Books, media, physical & digital resources

See catalog results

Searchworks

Select search scope, currently: Articles

Catalog

books, media & more in Jio Institute collections

Articles

journal articles & other e-resources

Refine your results

33 results on '"François Poulet"'

1. The thermal-vacuum and security system of the characterization facility for MAJIS/JUICE VIS-NIR FM and SM detectors

2. Planetary Terrestrial Analogues Library project: 2. building a laboratory facility for MicrOmega characterization

3. SIMBIO-SYS: Scientific Cameras and Spectrometer for the BepiColombo Mission

4. Parallel learning of local SVM algorithms for classifying large datasets

5. Parallel incremental power mean SVM for the classification of large-scale image datasets

6. Classifying very high-dimensional and large-scale multi-class image datasets with Latent-lSVM

7. Dynamic local interaction model. Modèle et algorithms

8. TreeView, exploration interactive des arbres de décision

9. Random Local SVMs for Classifying Large Datasets

10. Parallel Multiclass Logistic Regression for Classifying Large Scale Image Datasets

11. FULL-VIEW: A VISUAL DATA-MINING ENVIRONMENT

12. Large Scale Classifiers for Visual Classification Tasks

13. Large Scale Image Classification: Fast Feature Extraction, Multi-codebook Approach and Multi-core SVM Training

14. Community detection and visualization in social networks: integrating structural and semantic information

15. Parallel incremental SVM for classifying million images with very high-dimensional signatures into thousand classes

16. Multi-way Classification for Large Scale Visual Object Dataset

17. Layout Algorithm for Clustered Graphs to Analyze Community Interactions in Social Networks

18. Large Scale Image Classification with Many Classes, Multi-features and Very High-Dimensional Signatures

19. Large Scale Visual Classification with Many Classes

20. Entropy based community detection in augmented social networks

21. High Dimensional Image Categorization

22. Speed Up SVM Algorithm for Massive Classification Tasks

23. Towards Effective Visual Data Mining with Cooperative Approaches

24. Interactive Decision Tree Construction for Interval and Taxonomical Data

25. High Dimensional Visual Data Classification

26. Classifying one billion data with a new distributed svm algorithm

27. Mining Very Large Datasets with Support Vector Machine Algorithms

28. SVM and Graphical Algorithms: A Cooperative Approach

29. Visual Interactive Evolutionary Algorithm for High Dimensional Data Clustering and Outlier Detection

30. User guidance: from theory to practice, the case of visual data mining

31. Enhancing SVM with Visualization

32. Latent‐lSVM classification of very high‐dimensional and large‐scale multi‐class datasets

33. Multiscale scatterplot matrix for visual and interactive exploration of metabonomic data

Catalog

Searchworks

Select search scope, currently: Articles Catalog books, media & more in Jio Institute collections Articles journal articles & other e-resources

Search

Search Constraints

Refine your results

Search Limiters

Topic

Publication Year Range

Language

Journal

Database

Publisher

33 results on '"François Poulet"'

Search Results

Catalog

Select search scope, currently: Articles

Catalog

books, media & more in Jio Institute collections

Articles

journal articles & other e-resources