Author: "Institute for Infocomm Research (I2R)" - Searchworks@Jio Institute Digital Library Search Results

Your search keyword '"Institute for Infocomm Research (I2R)"' showing total 294 results

Start Over Author "Institute for Infocomm Research (I2R)"

294 results on '"Institute for Infocomm Research (I2R)"'

51. Differential regulation of mouse pancreatic islet insulin secretion and Smad proteins by activin ligands

Author: Annalena Moliner, Patricia Marmol, Haiya Wu, Tingqing Guo, Carlos F. Ibáñez, Karima Mezghenna, Shao Nian Yang, Per Olof Berggren, Biocommunication en Cardio-Métabolique (BC2M), Université de Montpellier (UM), Image & Pervasive Access Lab (IPAL), Institute for Infocomm Research - I²R [Singapore]-Centre National de la Recherche Scientifique (CNRS)-Agency for science, technology and research [Singapore] (A*STAR)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-National University of Singapore (NUS)-Université Pierre et Marie Curie - Paris 6 (UPMC), Estación Biológica de Doñana (EBD), Consejo Superior de Investigaciones Científicas [Madrid] (CSIC), and Université Joseph Fourier - Grenoble 1 (UJF)-Université Pierre et Marie Curie - Paris 6 (UPMC)-National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore]
Subjects: Male, medicine.medical_specialty, endocrine system, animal structures, Endocrinology, Diabetes and Metabolism, medicine.medical_treatment, [SDV]Life Sciences [q-bio], Smad Proteins, SMAD, Biology, Real-Time Polymerase Chain Reaction, Paracrine signalling, Islets of Langerhans, Mice, Internal medicine, Insulin Secretion, Internal Medicine, medicine, Glucose homeostasis, Animals, Insulin, Inhibin-beta Subunits, geography, Glucose tolerance test, geography.geographical_feature_category, medicine.diagnostic_test, Pancreatic islets, Glucose Tolerance Test, Islet, Mice, Mutant Strains, Microscopy, Electron, Endocrinology, medicine.anatomical_structure, embryonic structures, Homeostasis, hormones, hormone substitutes, and hormone antagonists
Abstract: Glucose-stimulated insulin secretion (GSIS) from pancreatic beta cells is regulated by paracrine factors, the identity and mechanisms of action of which are incompletely understood. Activins are expressed in pancreatic islets and have been implicated in the regulation of GSIS. Activins A and B signal through a common set of intracellular components, but it is unclear whether they display similar or distinct functions in glucose homeostasis. We examined glucose homeostatic responses in mice lacking activin B and in pancreatic islets derived from these mutants. We compared the ability of activins A and B to regulate downstream signalling, ATP production and GSIS in islets and beta cells. Mice lacking activin B displayed elevated serum insulin levels and GSIS. Injection of a soluble activin B antagonist phenocopied these changes in wild-type mice. Isolated pancreatic islets from mutant mice showed enhanced GSIS, which could be rescued by exogenous activin B. Activin B negatively regulated GSIS and ATP production in wild-type islets, while activin A displayed the opposite effects. The downstream mediator Smad3 responded preferentially to activin B in pancreatic islets and beta cells, while Smad2 showed a preference for activin A, indicating distinct signalling effects of the two activins. In line with this, overexpression of Smad3, but not Smad2, decreased GSIS in pancreatic islets. These results reveal a tug-of-war between activin ligands in the regulation of insulin secretion by beta cells, and suggest that manipulation of activin signalling could be a useful strategy for the control of glucose homeostasis in diabetes and metabolic disease.
Published: 2013
Full Text: View/download PDF

52. Hybrid segmentation of depth images using a watershed and region merging based method for tree species recognition

Author: Alexandre Piboule, Lew F.C. Lew Yan Voon, Ahlem Othmani, Laboratoire Electronique, Informatique et Image [UMR6306] (Le2i), Université de Bourgogne (UB)-École Nationale Supérieure d'Arts et Métiers (ENSAM), Arts et Métiers Sciences et Technologies, HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-Arts et Métiers Sciences et Technologies, HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement-Centre National de la Recherche Scientifique (CNRS), Image Science for Interventional Techniques (ISIT), Université d'Auvergne - Clermont-Ferrand I (UdA)-Clermont Université-Centre National de la Recherche Scientifique (CNRS), Image & Pervasive Access Lab (IPAL), Université Joseph Fourier - Grenoble 1 (UJF)-Université Pierre et Marie Curie - Paris 6 (UPMC)-National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], Office national des forêts (ONF), Université de Bourgogne (UB)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Arts et Métiers (ENSAM), HESAM Université (HESAM)-HESAM Université (HESAM)-Arts et Métiers Sciences et Technologies, HESAM Université (HESAM)-HESAM Université (HESAM)-AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement, Université d'Auvergne - Clermont-Ferrand I (UdA)-Centre National de la Recherche Scientifique (CNRS)-Clermont Université, Institute for Infocomm Research - I²R [Singapore]-Centre National de la Recherche Scientifique (CNRS)-Agency for science, technology and research [Singapore] (A*STAR)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-National University of Singapore (NUS)-Université Pierre et Marie Curie - Paris 6 (UPMC), Office National des Forêts (ONF), Laboratoire Electronique, Informatique et Image ( Le2i ), Université de Bourgogne ( UB ) -AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement-Centre National de la Recherche Scientifique ( CNRS ), Image Science for Interventional Techniques ( ISIT ), Université d'Auvergne - Clermont-Ferrand I ( UdA ) -Clermont Université-Centre National de la Recherche Scientifique ( CNRS ), Image & Pervasive Access Lab ( IPAL ), Université Pierre et Marie Curie - Paris 6 ( UPMC ) -National University of Singapore ( NUS ) -MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] ( A*STAR ) -Centre National de la Recherche Scientifique ( CNRS ) -Institute for Infocomm Research - I²R [Singapore], and Office National des Forêts - ONF (FRANCE)
Subjects: Watershed, [ INFO.INFO-TS ] Computer Science [cs]/Signal and Image Processing, Point cloud, 02 engineering and technology, [ INFO.INFO-CV ] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 01 natural sciences, 010309 optics, 3D geometric texture classification, Image texture, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0103 physical sciences, [ INFO.INFO-TI ] Computer Science [cs]/Image Processing, 0202 electrical engineering, electronic engineering, information engineering, Segmentation, Computer vision, [STAT.AP]Statistics [stat]/Applications [stat.AP], Forest inventory, Contextual image classification, business.industry, [ STAT.AP ] Statistics [stat]/Applications [stat.AP], [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Pattern recognition, Image segmentation, 15. Life on land, Random forest, Geography, Index Terms— Forest inventory, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 020201 artificial intelligence & image processing, single tree species recognition, Artificial intelligence, terrestrial laser scanning, business
Abstract: International audience; Tree species recognition from Terrestrial Light Detection and Ranging (T-LiDAR) scanner data is essential for estimating forest inventory attributes in a mixed planting. In this paper, we propose a new method for individual tree species recognition based on the analysis of the 3D geometric texture of tree barks. Our method transforms the 3D point cloud of a 30 cm segment of the tree trunk into a depth image on which a hybrid segmentation method using watershed and region merging techniques is applied in order to reveal bark shape characteristics. Finally, shape and intensity features are calculated on the segmented depth image and used to classify five different tree species using a Random Forest (RF) classifier. Our method has been tested using two datasets acquired in two different French forests with different terrain characteristics. The accuracy and precision rates obtained for both datasets are over 89%.
Published: 2013
Full Text: View/download PDF

53. Challenges, Experiences and Lessons Learned from Deploying Patient Monitoring and Assistance System at Dementia Care Hostel

Author: Aung Aung Phyo Wai, Philip Yap, Jit Biswas, Lin Jin Hong Kenneth, Thibaut Tiberghien, Alwyn Lee Vwen Yen, Hamdi Aloulou, Clifton Phua, Liu Yan, Xian Zhang, Institute for Infocomm Research - I²R [Singapore], Institut Mines-Télécom [Paris] (IMT), Image & Pervasive Access Lab (IPAL), Institute for Infocomm Research - I²R [Singapore]-Centre National de la Recherche Scientifique (CNRS)-Agency for science, technology and research [Singapore] (A*STAR)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-National University of Singapore (NUS)-Université Pierre et Marie Curie - Paris 6 (UPMC), National University of Singapore (NUS), Khoo Teck Puat Hospital (KTPH), Alexandra Health, and Université Joseph Fourier - Grenoble 1 (UJF)-Université Pierre et Marie Curie - Paris 6 (UPMC)-National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore]
Subjects: Service (systems architecture), Population ageing, Computer science, Remote patient monitoring, media_common.quotation_subject, 02 engineering and technology, [INFO.INFO-IU]Computer Science [cs]/Ubiquitous Computing, Activity recognition, 0202 electrical engineering, electronic engineering, information engineering, medicine, Dementia, Quality (business), activity recognition, Simulation, media_common, 020203 distributed computing, Medical education, business.industry, service reasoning, clinical trial, Usability, medicine.disease, Clinical trial, Demented elderly, scenario verification, 020201 artificial intelligence & image processing, business
Abstract: International audience; With growing aging population around the world, there is urgent need of effective solution to improve the quality of life of demented elderly. In order to provide real-time monitoring and timely assistance to elderly in their home settings, we designed and developed a system employing model-based scenario verification, sensing-assisted activity recognition and semantic service reasoning. In this paper, we present the results achieved and lessons learned from conducting clinical trials with our developed solution at a dementia hostel. From trial data analysis, we could determine good system performance but no concrete evidences obtained on how the daily care operations and quality can be improved. Especially, we gained technical experiences and learned usability issues from end-user perspectives that could lead to designing and developing better elderly care solutions in near future.
Published: 2013
Full Text: View/download PDF

54. Dynamic recommender system : using cluster-based biases to improve the accuracy of the predictions

Author: Hubert Naacke, Talel Abdessalem, Modou Gueye, Laboratoire Traitement et Communication de l'Information (LTCI), Télécom ParisTech-Institut Mines-Télécom [Paris] (IMT)-Centre National de la Recherche Scientifique (CNRS), Bases de Données (BD), Laboratoire d'Informatique de Paris 6 (LIP6), Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS), Image & Pervasive Access Lab (IPAL), Institute for Infocomm Research - I²R [Singapore]-Centre National de la Recherche Scientifique (CNRS)-Agency for science, technology and research [Singapore] (A*STAR)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-National University of Singapore (NUS)-Université Pierre et Marie Curie - Paris 6 (UPMC), School of computing [Singapore] (NUS), National University of Singapore (NUS), Gueye, Modou, and Université Joseph Fourier - Grenoble 1 (UJF)-Université Pierre et Marie Curie - Paris 6 (UPMC)-National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore]
Subjects: FOS: Computer and information sciences, Mean squared error, Computer science, media_common.quotation_subject, 02 engineering and technology, Recommender system, computer.software_genre, Machine Learning (cs.LG), Computer Science - Information Retrieval, Matrix decomposition, Matrix (mathematics), Computer Science - Databases, H.3.3, Factorization, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], 020204 information systems, H.2.8, 0202 electrical engineering, electronic engineering, information engineering, [INFO.INFO-DB] Computer Science [cs]/Databases [cs.DB], Quality (business), [INFO]Computer Science [cs], Cluster analysis, media_common, [INFO.INFO-DB]Computer Science [cs]/Databases [cs.DB], Databases (cs.DB), [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], Computer Science - Learning, [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], 020201 artificial intelligence & image processing, [INFO.INFO-IR] Computer Science [cs]/Information Retrieval [cs.IR], Data mining, computer, Information Retrieval (cs.IR), Drawback
Abstract: It is today accepted that matrix factorization models allow a high quality of rating prediction in recommender systems. However, a major drawback of matrix factorization is its static nature that results in a progressive declining of the accuracy of the predictions after each factorization. This is due to the fact that the new obtained ratings are not taken into account until a new factorization is computed, which can not be done very often because of the high cost of matrix factorization. In this paper, aiming at improving the accuracy of recommender systems, we propose a cluster-based matrix factorization technique that enables online integration of new ratings. Thus, we significantly enhance the obtained predictions between two matrix factorizations. We use finer-grained user biases by clustering similar items into groups, and allocating in these groups a bias to each user. The experiments we did on large datasets demonstrated the efficiency of our approach., 31 pages, 7 figures
Published: 2012
Full Text: View/download PDF

55. Unsupervised and supervised visual codes with restricted Boltzmann machines

Author: Joo-Hwee Lim, Nicolas Thome, Matthieu Cord, Hanlin Goh, Institute for Infocomm Research - I²R [Singapore], Laboratoire d'Informatique de Paris 6 (LIP6), Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS), Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], Machine Learning and Information Retrieval (MALIRE), Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS), and National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore]
Subjects: Restricted Boltzmann machine, business.industry, Supervised learning, Codebook, Boltzmann machine, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020206 networking & telecommunications, Pattern recognition, 02 engineering and technology, Machine learning, computer.software_genre, Generative model, ComputingMethodologies_PATTERNRECOGNITION, Discriminative model, Bag-of-words model, 0202 electrical engineering, electronic engineering, information engineering, Unsupervised learning, 020201 artificial intelligence & image processing, Artificial intelligence, business, computer, Mathematics
Abstract: International audience; Recently, the coding of local features (e.g. SIFT) for image categorization tasks has been extensively studied. Incorporated within the Bag of Words (BoW) framework, these techniques optimize the projection of local features into the visual codebook, leading to state-of-the-art performances in many benchmark datasets. In this work, we propose a novel visual codebook learning approach using the restricted Boltzmann machine (RBM) as our generative model. Our contribution is three-fold. Firstly, we steer the unsupervised RBM learning using a regularization scheme, which decomposes into a combined prior for the sparsity of each feature's representation as well as the selectivity for each codeword. The codewords are then fine-tuned to be discriminative through the supervised learning from top-down labels. Secondly, we evaluate the proposed method with the Caltech-101 and 15-Scenes datasets, either matching or outperforming state-of-the-art results. The codebooks are compact and inference is fast. Finally, we introduce an original method to visualize the codebooks and decipher what each visual codeword encodes.
Published: 2012
Full Text: View/download PDF

56. Haptic identification of raised-line drawings: high visuospatial imagers outperform low visuospatial imagers

Author: Samuel Lebaz, Delphine Picard, Christophe Jouffrais, Octogone Unité de Recherche Interdisciplinaire (Octogone), Université Toulouse - Jean Jaurès (UT2J), Etude de L’Interaction Personne SystèmE (IRIT-ELIPSE), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Image & Pervasive Access Lab (IPAL), Institute for Infocomm Research - I²R [Singapore]-Centre National de la Recherche Scientifique (CNRS)-Agency for science, technology and research [Singapore] (A*STAR)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-National University of Singapore (NUS)-Université Pierre et Marie Curie - Paris 6 (UPMC), Laboratoire Cherchons Pour Voir (CPV), Université Fédérale Toulouse Midi-Pyrénées-Institut des Jeunes Aveugles [Toulouse] (IJA)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Centre National de la Recherche Scientifique (CNRS), Centre de Recherche en Psychologie de la Connaissance, du Langage et de l'Émotion (PsyCLÉ), Aix Marseille Université (AMU), Université de Toulouse (UT)-Université de Toulouse (UT), Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Toulouse Mind & Brain Institut (TMBI), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT), Université Joseph Fourier - Grenoble 1 (UJF)-Université Pierre et Marie Curie - Paris 6 (UPMC)-National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], and Université de Toulouse (UT)-Institut des Jeunes Aveugles [Toulouse] (IJA)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP)
Subjects: Adult, Male, genetic structures, media_common.quotation_subject, 050109 social psychology, Experimental and Cognitive Psychology, 050105 experimental psychology, [SCCO]Cognitive science, Arts and Humanities (miscellaneous), Perception, Reaction Time, Developmental and Educational Psychology, Psychophysics, Humans, 0501 psychology and cognitive sciences, Self report, ComputingMilieux_MISCELLANEOUS, media_common, Haptic technology, 05 social sciences, Line drawings, General Medicine, Identification (information), Pattern Recognition, Visual, Touch Perception, Space Perception, [SCCO.PSYC]Cognitive science/Psychology, Female, Self Report, Psychology, Mental image, Cognitive psychology
Abstract: It has been assumed (Lederman et al. 1990, Perception & psychophysics) that a visual imagery process is involved in the haptic identification of raised-line drawings of common objects. The finding of significant correlations between visual imagery ability and performance on picture-naming tasks was taken as experimental evidence in support of this assumption. However, visual imagery measures came from self-report procedures, which can be unreliable. The present study therefore used an objective measure of visuospatial imagery abilities in sighted participants and compared three groups of high, medium and low visuospatial imagers on their accuracy and response times in identifying raised-line drawings by touch. Results revealed between-group differences on accuracy, with high visuospatial imagers outperforming low visuospatial imagers, but not on response times. These findings lend support to the view that visuospatial imagery plays a role in the identification of raised-line drawings by sighted adults.
Published: 2012
Full Text: View/download PDF

57. Point Sets Morphological Filtering and Semantic Spatial Configurations Modeling: application to microscopic image analysis

Author: Loménie, Nicolas, Racoceanu, Daniel, Laboratoire d'Informatique Paris Descartes (LIPADE - EA 2517), Université Paris Descartes - Paris 5 (UPD5), Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS) - MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF) - Agency for science, technology and research [Singapore] (A*STAR) - Centre National de la Recherche Scientifique (CNRS) - Institute for Infocomm Research - I²R [Singapore], and National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore]
Subjects: unorganized point set, [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], spatial relation modeling, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], mesh analysis, image exploration, sparse representation, Shape analysis, morphological operator
Abstract: International audience; Spatial relation and configuration modeling issues are gaining momentum in image analysis and pattern recognition fields in the perspective of mining high-content images or large scale image databases in a more expressive way than purely statistically. Continuing our previous efforts whereby we developed specific efficient morphological tools performing on mesh representation like Delaunay triangulations, we propose to formalize spatial relation modeling techniques dedicated to unorganized point sets. We provide an original mesh lattice framework more convenient for structural representations of large image data by the means of interest points sets and their morphological analysis. The set of designed numerical operators is based on a specific dilation operator that makes it possible to handle concepts like ''between'' or ''left of'' over sparse representations such as graphs. Then, for the sake of illustration and discussion, we apply these new tools to high-level queries in histo-pathological images.
Published: 2012
Full Text: View/download PDF

58. Concevoir pour et avec les personnes âgées des technologies au service de l'autonomie

Author: ARAB, Farah, RABARDEL, Pierre, Pigot, Hélène, Mokhtari, Mounir, Shtalbi, Haki, Département Réseaux et Services de Télécommunications (TSP - RST), Institut Mines-Télécom [Paris] (IMT)-Télécom SudParis (TSP), Laboratoire Paragraphe (PARAGRAPHE), Université Paris 8 Vincennes-Saint-Denis (UP8)-Université de Cergy Pontoise (UCP), Université Paris-Seine-Université Paris-Seine, DOmotique et informatique Mobile à l'Université de Sherbrooke (DOMUS), Département d'informatique [Sherbrooke] (UdeS), Faculté des sciences [Sherbrooke] (UdeS), Université de Sherbrooke (UdeS)-Université de Sherbrooke (UdeS)-Faculté des sciences [Sherbrooke] (UdeS), Université de Sherbrooke (UdeS)-Université de Sherbrooke (UdeS), Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier (LIRMM), Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS), Image & Pervasive Access Lab (IPAL), Université Joseph Fourier - Grenoble 1 (UJF)-Université Pierre et Marie Curie - Paris 6 (UPMC)-National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], Télécom ParisTech, Département Réseaux et Services de Télécommunications (RST), Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM), and Institute for Infocomm Research - I²R [Singapore]-Centre National de la Recherche Scientifique (CNRS)-Agency for science, technology and research [Singapore] (A*STAR)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-National University of Singapore (NUS)-Université Pierre et Marie Curie - Paris 6 (UPMC)
Subjects: [INFO.INFO-NI]Computer Science [cs]/Networking and Internet Architecture [cs.NI], [INFO.INFO-NI] Computer Science [cs]/Networking and Internet Architecture [cs.NI], ComputingMilieux_MISCELLANEOUS
Abstract: International audience
Published: 2012

59. Learning Invariant Color Features with Sparse Topographic Restricted Boltzmann Machines

Author: Lukasz Kusmierz, Nicolas Thome, Matthieu Cord, Hanlin Goh, Joo-Hwee Lim, Machine Learning and Information Retrieval (MALIRE), Laboratoire d'Informatique de Paris 6 (LIP6), Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS), Institute for Infocomm Research - I²R [Singapore], Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], and National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore]
Subjects: business.industry, Boltzmann machine, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Pattern recognition, 02 engineering and technology, 010501 environmental sciences, 01 natural sciences, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 0202 electrical engineering, electronic engineering, information engineering, Monochrome, Unsupervised learning, 020201 artificial intelligence & image processing, Color filter array, Computer vision, Artificial intelligence, Affine transformation, Invariant (mathematics), Neural coding, business, 0105 earth and related environmental sciences, Coding (social sciences), Mathematics, ComputingMethodologies_COMPUTERGRAPHICS
Abstract: International audience; Our objective is to learn invariant color features directly from data via unsupervised learning. In this paper, we introduce a method to regularize restricted Boltzmann machines during training to obtain features that are sparse and topographically organized. Upon analysis, the features learned are Gabor-like and demonstrate a coding of orientation, spatial position, frequency and color that vary smoothly with the topography of the feature map. There is also differentiation between monochrome and color filters, with some exhibiting color-opponent properties. We also found that the learned represen- tation is more invariant to affine image transformations and changes in illumination color.
Published: 2011
Full Text: View/download PDF

60. State-of-the-Art Assistive Technology for People with Dementia

Author: Phua, Clifton, Roy, Patrice, Aloulou, Hamdi, Biswas, Jit, Tolstikov, Andrei, Foo, Victor Siang Fook, Huang, Weimin, Feki, Mohamed Ali, Jayachandran, Maniyeri, Phyo Wai, Aung Aung, Chu, Alvin Kok-Weng, Xu, Duangui, Institute for Infocomm Research - I²R [Singapore], Image & Pervasive Access Lab (IPAL), Université Joseph Fourier - Grenoble 1 (UJF)-Université Pierre et Marie Curie - Paris 6 (UPMC)-National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], Télécom ParisTech, Temasek Polytechnic, and Institute for Infocomm Research - I²R [Singapore]-Centre National de la Recherche Scientifique (CNRS)-Agency for science, technology and research [Singapore] (A*STAR)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-National University of Singapore (NUS)-Université Pierre et Marie Curie - Paris 6 (UPMC)
Subjects: [INFO.INFO-IU]Computer Science [cs]/Ubiquitous Computing
Published: 2011

61. Un explorateur visuel cognitif (MIcroscope COgnitif - MICO) pour l'histopathologie. Application au diagnostic et à la graduation du cancer du sein

Author: Le Naour, Gilles, Genestie, Catherine, Roux, Ludovic, Veillard, Antoine, Racoceanu, Daniel, Capron, Frédérique, Service d'anatomie pathologique [CHU Pitié-Salpêtrière], Université Pierre et Marie Curie - Paris 6 (UPMC)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-CHU Pitié-Salpêtrière [AP-HP], Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU), Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], National University of Singapore (NUS), ANR TecSan référence ANR-10-TECS-015, Projet MICO, CHU Pitié-Salpêtrière [AP-HP], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU), and National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore]
Subjects: Oncologie, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Traitement et analyse d'images
Abstract: National audience; The objective of our project is to develop a cognitive explorer for histopathology which could be used routinely in an anatomy and cytology pathology service. We focus on breast cancer for the development of this explorer.
Published: 2011

62. Age, memory and time : practices and support

Author: Arab, Farah, Pigot, Helene, Rabardel, Pierre, Folcher, Viviane, Rigaud Monnet, Anne-Sophie, Mokhtari, Mounir, Département Réseaux et Services de Télécommunications (RST), Institut Mines-Télécom - Télécom SudParis, Laboratoire DOmotique et informatique Mobile (DOMUS), Université de Sherbrooke [Sherbrooke], Laboratoire Paragraphe, Université Paris 8, Vincennes-Saint-Denis (UP8), AP-HP - Hôpital Cochin Broca Hôtel Dieu [Paris], Image & Pervasive Access Lab (IPAL), Centre National de la Recherche Scientifique (CNRS) - National University of Singapore (NUS) - MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF) - Institute for Infocomm Research - I²R [Singapore] - A*STAR, Institut Mines-Télécom [Paris] (IMT)-Télécom SudParis (TSP), DOmotique et informatique Mobile à l'Université de Sherbrooke (DOMUS), Département d'informatique [Sherbrooke] (UdeS), Faculté des sciences [Sherbrooke] (UdeS), Université de Sherbrooke (UdeS)-Université de Sherbrooke (UdeS)-Faculté des sciences [Sherbrooke] (UdeS), Université de Sherbrooke (UdeS)-Université de Sherbrooke (UdeS), Laboratoire Paragraphe (PARAGRAPHE), Université Paris 8 Vincennes-Saint-Denis (UP8)-Université de Cergy Pontoise (UCP), Université Paris-Seine-Université Paris-Seine, Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP), National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], and Télécom SudParis & Institut Mines-Télécom Business School, Médiathèque
Subjects: Aging, Habits, Technological aids, Memory, [INFO]Computer Science [cs], [INFO] Computer Science [cs], Time
Abstract: International audience; This study of the capabilities and difficulties of memorization and recalling prospective tasks in the elderly provides a basis for designing services adapted to the needs of this population. Questionnaires were used in a three-pronged approach. The first objective is to evaluate this population's ability to recall future events/activities (e.g. doctors' appointments, taking medicine, etc.) and resumption of an interrupted activity. The second objective is to identify a system of resources to support memorization and task recall in aging subjects. The third objective is to determine the activities that need to be recalled and personal preferences for how these activities should be recalled (frequency, media, etc.) The study group consisted of 35 subjects, age 65 to 87, all living at home: 10 with Alzheimer's, 12 with MCI (Mild cognitive impairment) and 13 with no specific complaints about memory. We describe the study context, design of the study and prospects that arise from our initial results.
Published: 2011

63. Fusion of Artificial Vision and GPS to Improve Blind Pedestrian Positioning

Author: Adrien Brilhault, Slim Kammoun, Christophe Jouffrais, Olivier Gutierrez, Philippe Truillet, Etude de L’Interaction Personne SystèmE (IRIT-ELIPSE), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Centre National de la Recherche Scientifique (CNRS), Image & Pervasive Access Lab (IPAL), Institute for Infocomm Research - I²R [Singapore]-Centre National de la Recherche Scientifique (CNRS)-Agency for science, technology and research [Singapore] (A*STAR)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-National University of Singapore (NUS)-Université Pierre et Marie Curie - Paris 6 (UPMC), Laboratoire Cherchons Pour Voir (CPV), Université Fédérale Toulouse Midi-Pyrénées-Institut des Jeunes Aveugles [Toulouse] (IJA)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Toulouse Mind & Brain Institut (TMBI), Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT), Université Joseph Fourier - Grenoble 1 (UJF)-Université Pierre et Marie Curie - Paris 6 (UPMC)-National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], and Université de Toulouse (UT)-Institut des Jeunes Aveugles [Toulouse] (IJA)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP)
Subjects: 030506 rehabilitation, Situation awareness, Computer science, [SCCO.COMP]Cognitive science/Computer science, 02 engineering and technology, GPS signals, [SCCO]Cognitive science, 03 medical and health sciences, 11. Sustainability, 0202 electrical engineering, electronic engineering, information engineering, Computer vision, [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], ComputingMilieux_MISCELLANEOUS, business.industry, Hybrid positioning system, Orientation and Mobility, Sensor fusion, Assisted GPS, [SCCO.PSYC]Cognitive science/Psychology, Global Positioning System, Robot, [INFO.INFO-ET]Computer Science [cs]/Emerging Technologies [cs.ET], 020201 artificial intelligence & image processing, Artificial intelligence, 0305 other medical science, business
Abstract: Orientation and mobility are tremendous problems for Blind people. Assistive technologies based on Global Positioning System (GPS) could provide them with a remarkable autonomy. Unfortunately, GPS accuracy, Geographical Information System (GIS) data and map-matching techniques are adapted to vehicle navigation only, and fail in assisting pedestrian navigation, especially for the Blind. In this paper, we designed an assistive device for the Blind based on adapted GIS, and fusion of GPS and vision based positioning. The proposed assistive device may improve user positioning, even in urban environment where GPS signals are degraded. The estimated position would then be compatible with assisted navigation for the Blind. Interestingly the vision module may also answer Blind needs by providing them with situational awareness (localizing objects of interest) along the path. Note that the solution proposed for positioning could also enhance autonomous robots or vehicles localization.
Published: 2011
Full Text: View/download PDF

64. A hybrid factored frontier algorithm for dynamic Bayesian network models of biopathways

Author: Blaise Genest, Sucheendra K. Palaniappan, P. S. Thiagarajan, Sundararaman Akshay, School of computing [Singapore] (NUS), National University of Singapore (NUS), Distributed and Iterative Algorithms for the Management of Telecommunications Systems (DISTRIBCOM), 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), Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], 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 National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore]
Subjects: 0303 health sciences, Mathematical optimization, Small number, [INFO.INFO-OH]Computer Science [cs]/Other [cs.OH], Inference, Approximation algorithm, 02 engineering and technology, 03 medical and health sciences, Quadratic equation, Simple (abstract algebra), 0202 electrical engineering, electronic engineering, information engineering, Probability distribution, 020201 artificial intelligence & image processing, Time point, Algorithm, Dynamic Bayesian network, 030304 developmental biology, Mathematics
Abstract: International audience; Dynamic Bayesian Networks (DBNs) can serve as succinct models of large biochemical networks [19]. To analyze these models, one must compute the probability distribution over system states at a given time point. Doing this exactly is infeasible for large models and hence approximate methods are needed. The Factored Frontier algorithm (FF) is a simple and efficient approximate algorithm [25] that has been designed to meet this need. However the errors it incurs can be quite large. The earlier Boyen-Koller (BK) algorithm [3] can also incur significant errors. To address this, we present here a novel approximation algorithm called the Hybrid Factored Frontier (HFF) algorithm. HFF may be viewed as a parametrized version of FF. At each time slice, in addition to maintaining probability distributions over local states -as FF does- we also maintain explicitly the probabilities of a small number of global states called spikes. When the number of spikes is 0, we get FF and with all global states as spikes, we get the - computationally infeasible- exact inference algorithm. We show that by increasing the number of spikes one can reduce errors while the additional computational effort required is only quadratic in the number of spikes. We have validated the performance of our algorithm on large DBN models of biopathways. Each pathway has more than 30 species and the corresponding DBN has more than 3000 nodes. Comparisons with the performances of FF and BK show that HFF can be a useful and powerful approximation algorithm for analyzing DBN models of biopathways.
Published: 2011

65. Minimal Disclosure in Partially Observable Markov Decision Processes

Author: Bertrand, Nathalie, Genest, Blaise, Verification models and techniques applied to testing and control of reactive systems (VERTECS), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], and National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore]
Subjects: 000 Computer science, knowledge, general works, 010201 computation theory & mathematics, Computer Science, [INFO.INFO-OH]Computer Science [cs]/Other [cs.OH], 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, 0102 computer and information sciences, 02 engineering and technology, 01 natural sciences
Abstract: International audience; For security and efficiency reasons, most systems do not give the users a full access to their information. One key specification formalism for these systems are the so called Partially Observable Markov Decision Processes (POMDP for short), which have been extensively studied in several research communities, among which AI and model-checking. In this paper we tackle the problem of the minimal information a user needs at runtime to achieve a simple goal, modeled as reaching an objective with probability one. More precisely, to achieve her goal, the user can at each step either choose to use the partial information, or pay a fixed cost and receive the full information. The natural question is then to minimize the cost the user needs to fulfill her objective. This optimization question gives rise to two different problems, whether we consider to minimize the worst case cost, or the average cost. On the one hand, concerning the worst case cost, we show that efficient techniques from the model checking community can be adapted to compute the optimal worst case cost and give optimal strategies for the users. On the other hand, we show that the optimal average price (a question typically considered in the AI community) cannot be computed in general, nor can it be approximated in polynomial time even up to a large approximation factor.
Published: 2011

66. Inhibitory neurons stabilise the formation of neural assemblies via adaptation and selective stimuli

Author: Bergoin, Raphaël, Zamora-López, Gorka, Torcini, Alessandro, Quoy, Mathias, Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), Universitat Pompeu Fabra [Barcelona] (UPF), CY Cergy Paris Université (CY), Laboratoire de Physique Théorique et Modélisation (LPTM - UMR 8089), Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], GDR Robotique, ANR-18-CE37-0014,ERMUNDY,Réduction exacte de la dynamique neuronale multi-échelle(2018), European Project: 945539,H2020,H2020-SGA-FETFLAG-HBP-2019,HBP SGA3(2020), Quoy, Mathias, APPEL À PROJETS GÉNÉRIQUE 2018 - Réduction exacte de la dynamique neuronale multi-échelle - - ERMUNDY2018 - ANR-18-CE37-0014 - AAPG2018 - VALID, Bergoin, Raphaël, and Human Brain Project Specific Grant Agreement 3 - HBP SGA3 - - H20202020-01-01 - 2023-09-30 - 945539 - VALID
Subjects: coupled oscillator, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Memory, Modular structure, [INFO.INFO-NE] Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], Inhibitory neurons, [INFO]Computer Science [cs], [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], adaptation, [INFO] Computer Science [cs], [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], synchronization, STDP
Abstract: International audience; We investigate the role of inhibition in structuring new neural assemblies following a learning phase in the brain. Although many studies have been devoted to this subject, few of them have considered the specific role of inhibitory neurons. Therefore, this work aims at studying the impact of inhibition in adaptive neural networks. In particular we focus on the role of synchronized dynamics for the creation and maintenance of structural modules in the brain circuits. Specifically, we considered an excitatory-inhibitory neural network made of θ-neurons with plastic Hebbian synapses. The learning process is mimicked by stimulating different areas of the network with temporal alternating external stimuli. This stimulation process leads to the emergence of modular structures. Then, the network dynamics is analysed after the learning phase revealing the maintenance of co-active neural assemblies over the long term. We show that the presence of inhibitory neurons controls the emergence of the modular structures and their maintenance in the resting phase following the learning period. Furthermore, we demonstrate that the number of inhibitory neurons in the network is directly related to the maximal number of neural assemblies that can be maintained. These results support the idea that inhibition has a direct impact on the memory capacity of a neural network.
Published: 2022

67. Biasing Restricted Boltzmann Machines to Manipulate Latent Selectivity and Sparsity

Author: Goh, Hanlin, Thome, Nicolas, Cord, Matthieu, Institute for Infocomm Research - I²R [Singapore], Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], Machine Learning and Information Retrieval (MALIRE), Laboratoire d'Informatique de Paris 6 (LIP6), Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS), and National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore]
Subjects: ComputingMethodologies_PATTERNRECOGNITION, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]
Abstract: International audience; This paper proposes a modification to the restricted Boltzmann machine (RBM) learning algorithm to incorporate inductive biases. These latent activation biases are ideal solutions of the latent activity and may be designed either by modeling neural phenomenon or inductive principles of the task. In this paper, we design activation biases for sparseness and selectivity based on the activation distributions of biological neurons. With this model, one can manipulate the selectivity of individual hidden units and the sparsity of population codes. The biased RBM yields a filter bank of Gabor-like filters when trained on natural images, while modeling handwritten digits results in filters with stroke-like features. We quantitatively verify that the latent representations assume the properties of the activation biases. We further demonstrate that RBMs biased with selectivity and sparsity can significantly outperform standard RBMs for discriminative tasks.
Published: 2010

68. Ontology-driven Image Analysis for Histopathological Images

Author: Nicolas Loménie, Ahlem Othmani, Carole Meziat, Laboratoire Electronique, Informatique et Image ( Le2i ), Université de Bourgogne ( UB ) -AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement-Centre National de la Recherche Scientifique ( CNRS ), Image & Pervasive Access Lab ( IPAL ), National University of Singapore ( NUS ) -MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] ( A*STAR ) -Centre National de la Recherche Scientifique ( CNRS ) -Institute for Infocomm Research - I²R [Singapore], Centre de Recherche en Informatique de Paris 5 ( CRIP5 - EA 2517 ), Université Paris Descartes - Paris 5 ( UPD5 ), Laboratoire Electronique, Informatique et Image [UMR6306] (Le2i), Université de Bourgogne (UB)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Arts et Métiers (ENSAM), Arts et Métiers Sciences et Technologies, HESAM Université (HESAM)-HESAM Université (HESAM)-Arts et Métiers Sciences et Technologies, HESAM Université (HESAM)-HESAM Université (HESAM)-AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement, Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], Centre de Recherche en Informatique de Paris 5 (CRIP5 - EA 2517), Université Paris Descartes - Paris 5 (UPD5), Othmani, Alice Ahlem, Laboratoire Electronique, Informatique et Image [UMR6303] ( Le2i ), and Centre National de la Recherche Scientifique ( CNRS ) -Université de Bourgogne ( UB ) -AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement-École Nationale Supérieure d'Arts et Métiers ( ENSAM )
Subjects: [ INFO.INFO-TS ] Computer Science [cs]/Signal and Image Processing, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, Computer science, [INFO.INFO-IM] Computer Science [cs]/Medical Imaging, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Image processing, Ontology (information science), [ INFO.INFO-CV ] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 030218 nuclear medicine & medical imaging, 03 medical and health sciences, [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 0302 clinical medicine, Software, [STAT.AP] Statistics [stat]/Applications [stat.AP], [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Digital image processing, [ INFO.INFO-TI ] Computer Science [cs]/Image Processing, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Computer vision, RDF, Image analysis, [STAT.AP]Statistics [stat]/Applications [stat.AP], Information retrieval, [ INFO.INFO-IM ] Computer Science [cs]/Medical Imaging, business.industry, [ STAT.AP ] Statistics [stat]/Applications [stat.AP], [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Usability, computer.file_format, Automatic image annotation, [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], 030220 oncology & carcinogenesis, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Artificial intelligence, business, computer
Abstract: International audience; Ontology-based software and image processing engine must cooperate in new fields of computer vision like microscopy acquisition wherein the amount of data, concepts and processing to be handled must be properly controlled. Within our own platform, we need to extract biological objects of interest in huge size and high-content microscopy images. In addition to specific low-level image analysis procedures, we used knowledge formalization tools and high-level reasoning ability of ontology-based software. This methodology made it possible to improve the expressiveness of the clinical models, the usability of the platform for the pathologist and the sensitivity or sensibility of the low-level image analysis algorithms.
Published: 2010

69. Time-efficient sparse analysis of histopathological Whole Slide Images

Author: Chao-Hui Huang, Antoine Veillard, Nicolas Loménie, Ludovic Roux, Daniel Racoceanu, Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS) - MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF) - Agency for science, technology and research [Singapore] (A*STAR) - Centre National de la Recherche Scientifique (CNRS) - Institute for Infocomm Research - I²R [Singapore], National University of Singapore (NUS), Centre de Recherche en Informatique de Paris 5 (CRIP5 - EA 2517), Université Paris Descartes - Paris 5 (UPD5), Image Perception, Access and Language (IPAAL), Université Joseph Fourier - Grenoble 1 (UJF) - École Nationale Supérieure de Physique de Grenoble (ENSPG) - UNIV NATIONALE DE SINGAPOUR - AGENCY FOR SCIENCE TECHNOLOGY AND RESEAR - Centre National de la Recherche Scientifique (CNRS), Racoceanu, Daniel, National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], and Université Joseph Fourier - Grenoble 1 (UJF)-École Nationale Supérieure de Physique de Grenoble (ENSPG)-UNIV NATIONALE DE SINGAPOUR-AGENCY FOR SCIENCE TECHNOLOGY AND RESEAR-Centre National de la Recherche Scientifique (CNRS)
Subjects: Diagnostic Imaging, Breast biopsy, Time Factors, Speedup, Computer science, Graphics processing unit, Histopathology, Health Informatics, Virtual microscope, Pattern Recognition, Automated, User-Computer Interface, breast cancer, multi-scale analysis, [INFO.INFO-TI] Computer Science [cs]/Image Processing, Image Interpretation, Computer-Assisted, medicine, Humans, Radiology, Nuclear Medicine and imaging, Sampling (medicine), Computer vision, Microscopy, Ground truth, virtual microscope, Radiological and Ultrasound Technology, medicine.diagnostic_test, business.industry, Computer Graphics and Computer-Aided Design, Whole Slide Image, dynamic sampling, [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Computer Vision and Pattern Recognition, Artificial intelligence, business, Neural coding, Algorithms, Software, Virtual microscopy, Graphics Processing Unit
Abstract: Histopathological examination is a powerful standard for the prognosis of critical diseases. But, despite significant advances in high-speed and high-resolution scanning devices or in virtual exploration capabilities, the clinical analysis of whole slide images (WSI) largely remains the work of human experts. We propose an innovative platform in which multi-scale computer vision algorithms perform fast analysis of a histopathological WSI. It relies on application-driven for high-resolution and generic for low-resolution image analysis algorithms embedded in a multi-scale framework to rapidly identify the high power fields of interest used by the pathologist to assess a global grading. GPU technologies as well speed up the global time-efficiency of the system. Sparse coding and dynamic sampling constitute the keystone of our approach. These methods are implemented within a computer-aided breast biopsy analysis application based on histopathology images and designed in collaboration with a pathology department. The current ground truth slides correspond to about 36,000 high magnification (40×) high power fields. The processing time to achieve automatic WSI analysis is on a par with the pathologist's performance (about ten minutes a WSI), which constitutes by itself a major contribution of the proposed methodology.
Published: 2010

70. Seamless semantic service provisioning mechanism for ambient assisted living

Author: Mahmoud Ghorbel, Mohd Fadlee A. Rasid, Mounir Mokhtari, Borhanuddin Mohd Ali, Muzaaliff W. Musa, Faculty of Engineering, Universiti Putra Malaysia, Serdang, Selangor, Universiti Putra Malaysia, Département Réseaux et Services de Télécommunications (RST), Institut Mines-Télécom [Paris] (IMT)-Télécom SudParis (TSP), Image & Pervasive Access Lab (IPAL), Institute for Infocomm Research - I²R [Singapore]-Centre National de la Recherche Scientifique (CNRS)-Agency for science, technology and research [Singapore] (A*STAR)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-National University of Singapore (NUS)-Université Pierre et Marie Curie - Paris 6 (UPMC), Alcatel Lucent Bell Labs [Paris], Alcatel-Lucent, Département Réseaux et Services de Télécommunications (TSP - RST), and Université Joseph Fourier - Grenoble 1 (UJF)-Université Pierre et Marie Curie - Paris 6 (UPMC)-National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore]
Subjects: Service (business), Computer science, Service delivery framework, business.industry, Service design, 05 social sciences, Service discovery, AAL, Provisioning, Context (language use), 02 engineering and technology, World Wide Web, [INFO.INFO-NI]Computer Science [cs]/Networking and Internet Architecture [cs.NI], Default gateway, Service provisioning, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, 0501 psychology and cognitive sciences, Network selection, business, Semantic Web, Semantic, 050107 human factors
Abstract: International audience; As the current technology and usage trends in Ambient Assisted Living (AAL) evolves; more and more services were developed for helping dependent people, especially elderly and people with mild dementia to live independently. These services help them to perform Activities of Daily Living (ADL) easily, safely and in a proper manner. The relevant service is delivered to the user seamlessly through a set of devices. As the user moves around, the devices might also move into a new and sometimes unknown domain. This leads to the need for service discovery and provisioning beyond the current capabilities of Open Services Gateway Initiative (OSGi) or other service platforms. A mechanism for seamless semantic service provisioning using semantic web is further discussed in this paper. The challenge here is to produce a platform that supports not only seamless semantic service provisioning, but also to handle user and device mobility through semantic reasoning. The aim of the system is to ensure users are able to use relevant services at a specific location and time with a set of dynamic context
Published: 2010
Full Text: View/download PDF

71. Automatic Working Area Classification in Peripheral Blood Smears

Author: Wei Xiong, Ong, S. H., Joo-Hwee Lim, Kelvin Foong Weng Chiong, Jiang Liu, Daniel RACOCEANU, Alvin Chong, Kevin Tan, Institute for Infocomm Research - I²R [Singapore], Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], and National University of Singapore (NUS)
Subjects: classification, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Peripheral blood smear, working area, clumping, high throughput screening
Abstract: International audience; Cell enumeration and diagnosis using peripheral blood smears are routine tasks in many biological and pathological examinations. Not every area in the smear is appropriate for such tasks due to severe cell clumping or sparsity. Manual working area selection is slow, subjective, inconsistent and statistically biased. Automatic working area classification can reproducibly identify appropriate working smear areas. However, very little research has been reported in the literature. With the aim of providing a preprocessing step for further detailed cell enumeration and diagnosis for high throughput screening, we propose an integrated algorithm for area classification and quantify both cell spreading and cell clumping in terms of individual clumps and the occurrence probabilities of the group of clumps over the image. Comprehensive comparisons are presented to compare the effect of these quantifications and their combinations. Our experiments using images of Giemsa-stained blood smears show that the method is efficient, accurate (above 88.9% hit rates for all areas in the validation set of 140 images) and robust (above 78.1% hit rates for a test set of 4878 images). This lays a good foundation for fast working area selection in high throughput screening.
Published: 2010

72. Mild dementia care at home : integrating activity monitoring, user interface plasticity and scenario verification

Author: Philip Yap, Jit Biswas, Mounir Mokhtari, Jin Song Dong, Institute for Infocomm Research - I²R [Singapore], Département Réseaux et Services de Télécommunications (RST), Institut Mines-Télécom [Paris] (IMT)-Télécom SudParis (TSP), Image & Pervasive Access Lab (IPAL), Institute for Infocomm Research - I²R [Singapore]-Centre National de la Recherche Scientifique (CNRS)-Agency for science, technology and research [Singapore] (A*STAR)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-National University of Singapore (NUS)-Université Pierre et Marie Curie - Paris 6 (UPMC), School of computing [Singapore] (NUS), National University of Singapore (NUS), Department of Geriatric Medicine [Singapore] (Alexandra Hospital), Département Réseaux et Services de Télécommunications (TSP - RST), and Université Joseph Fourier - Grenoble 1 (UJF)-Université Pierre et Marie Curie - Paris 6 (UPMC)-National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore]
Subjects: Computer science, Interface (Java), Human computer interface, 02 engineering and technology, Smart environment, System deployment and replication, Activity recognition, 03 medical and health sciences, [INFO.INFO-NI]Computer Science [cs]/Networking and Internet Architecture [cs.NI], 030502 gerontology, Human–computer interaction, Software deployment, 0202 electrical engineering, electronic engineering, information engineering, Key (cryptography), 020201 artificial intelligence & image processing, User interface, Cognitive decline, 0305 other medical science, Model building, Scenario verification
Abstract: International audience; We discuss an integrated approach towards building systems for monitoring and assisting people with mild dementia in their homes. Our approach differs from existing approaches in three ways. First we improve context acquisition and understanding with the concept of micro-context that takes us beyond existing notions of location and temporal context; second, we incorporate plasticity concept into the human computer interface, in order to provide a natural interaction way and accommodative interface to the user; third we target robust and reliable systems that are easy to scale and deploy in diverse end-user settings, through the use of formal model building tools to specify and verify systems at key stages from requirements generation all the way to deployment and user statistics gathering. In order to address real-life end user requirements we are working closely with geriatric doctors and their staff, so as to get inputs as to precise challenges in caring for mild dementia patients, and how systems targeted at holistic, personalized assistance and care-giving can be built with a view towards scaled up deployment in diverse settings. The main contribution of this paper is an approach for system building that incorporates activity monitoring, user interface plasticity and scenario verification targeting people with cognitive decline in regards to a Singapore initiative called A-Star Home 2015 Phase II. We expect our work to lead to a methodology for systematic development of monitoring and assistive systems for cognitive interventions for mild dementia patients at home. Although the integrated framework is still not completely realized, the three areas mentioned above have each yielded significant results on their own, and these are mentioned in the paper
Published: 2010
Full Text: View/download PDF

73. Anderson localization of matter waves in speckle potentials

Author: Pierre Lugan, Juliette Billy, Vincent Josse, Zhanchun Zuo, Alain Bernard, Patrick Cheinet, David Clément, Philippe Bouyer, Alain Aspect, Laurent Sanchez-Palencia, Dominique Delande, Benoît Grémaud, Müller, Cord A., Christian MINIATURA, Physikalisches Institut [Freiburg], Albert-Ludwigs-Universität Freiburg, laboratoire Charles Fabry de l'Institut d'Optique / Optique atomique, Laboratoire Charles Fabry de l'Institut d'Optique (LCFIO), Centre National de la Recherche Scientifique (CNRS)-Institut d'Optique Graduate School (IOGS)-Université Paris-Sud - Paris 11 (UP11)-Centre National de la Recherche Scientifique (CNRS)-Institut d'Optique Graduate School (IOGS)-Université Paris-Sud - Paris 11 (UP11), Laboratoire Kastler Brossel (LKB (Jussieu)), Université Pierre et Marie Curie - Paris 6 (UPMC)-Fédération de recherche du Département de physique de l'Ecole Normale Supérieure - ENS Paris (FRDPENS), École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS), Centre for Quantum Technologies [Singapore] (CQT), National University of Singapore (NUS), Image & Pervasive Access Lab (IPAL), Institute for Infocomm Research - I²R [Singapore]-Centre National de la Recherche Scientifique (CNRS)-Agency for science, technology and research [Singapore] (A*STAR)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-National University of Singapore (NUS)-Université Pierre et Marie Curie - Paris 6 (UPMC), Institut Non Linéaire de Nice Sophia-Antipolis (INLN), Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS), Université Paris-Sud - Paris 11 (UP11)-Institut d'Optique Graduate School (IOGS)-Centre National de la Recherche Scientifique (CNRS)-Université Paris-Sud - Paris 11 (UP11)-Institut d'Optique Graduate School (IOGS)-Centre National de la Recherche Scientifique (CNRS), Fédération de recherche du Département de physique de l'Ecole Normale Supérieure - ENS Paris (FRDPENS), École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS), Université Joseph Fourier - Grenoble 1 (UJF)-Université Pierre et Marie Curie - Paris 6 (UPMC)-National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], and Université Nice Sophia Antipolis (1965 - 2019) (UNS)
Subjects: [PHYS.COND.GAS]Physics [physics]/Condensed Matter [cond-mat]/Quantum Gases [cond-mat.quant-gas], ComputingMilieux_MISCELLANEOUS
Abstract: International audience
Published: 2010

74. One-dimensional Anderson localization in correlated random potentials

Author: Pierre Lugan, Alain Aspect, Laurent Sanchez-Palencia, Dominique Delande, Benoît Grémaud, Müller, Cord A., Christian MINIATURA, Physikalisches Institut [Freiburg], Albert-Ludwigs-Universität Freiburg, laboratoire Charles Fabry de l'Institut d'Optique / Optique atomique, Laboratoire Charles Fabry de l'Institut d'Optique (LCFIO), Université Paris-Sud - Paris 11 (UP11)-Institut d'Optique Graduate School (IOGS)-Centre National de la Recherche Scientifique (CNRS)-Université Paris-Sud - Paris 11 (UP11)-Institut d'Optique Graduate School (IOGS)-Centre National de la Recherche Scientifique (CNRS), Laboratoire Kastler Brossel (LKB (Jussieu)), Fédération de recherche du Département de physique de l'Ecole Normale Supérieure - ENS Paris (FRDPENS), École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS), Centre for Quantum Technologies [Singapore] (CQT), National University of Singapore (NUS), Image & Pervasive Access Lab (IPAL), Université Joseph Fourier - Grenoble 1 (UJF)-Université Pierre et Marie Curie - Paris 6 (UPMC)-National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], Institut Non Linéaire de Nice Sophia-Antipolis (INLN), Université Nice Sophia Antipolis (1965 - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS), Centre National de la Recherche Scientifique (CNRS)-Institut d'Optique Graduate School (IOGS)-Université Paris-Sud - Paris 11 (UP11)-Centre National de la Recherche Scientifique (CNRS)-Institut d'Optique Graduate School (IOGS)-Université Paris-Sud - Paris 11 (UP11), Université Pierre et Marie Curie - Paris 6 (UPMC)-Fédération de recherche du Département de physique de l'Ecole Normale Supérieure - ENS Paris (FRDPENS), École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS), Institute for Infocomm Research - I²R [Singapore]-Centre National de la Recherche Scientifique (CNRS)-Agency for science, technology and research [Singapore] (A*STAR)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-National University of Singapore (NUS)-Université Pierre et Marie Curie - Paris 6 (UPMC), and Université Nice Sophia Antipolis (... - 2019) (UNS)
Subjects: [PHYS.COND.GAS]Physics [physics]/Condensed Matter [cond-mat]/Quantum Gases [cond-mat.quant-gas], ComputingMilieux_MISCELLANEOUS
Abstract: International audience
Published: 2010

75. Quantifying the discord: Order discrepancies in Message Sequence Charts

Author: Paola Spoletini, Doron Peled, Edith Elkind, Blaise Genest, Nanayang Technological University (NTU), Distributed and Iterative Algorithms for the Management of Telecommunications Systems (DISTRIBCOM), 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), Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], Department of Computer Science [Bar Ilan], Bar-Ilan University [Israël], Department of the Sciences of Culture, Politics and Information (DSCPI), Universitá degli Studi dell’Insubria = University of Insubria [Varese] (Uninsubria), Nanayang Technological University, 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, National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], and Universitá degli Studi dell’Insubria
Subjects: Sequence, Theoretical computer science, Computer science, discord, message sequence charts, order discrepancies, Message passing, [INFO.INFO-OH]Computer Science [cs]/Other [cs.OH], Order (ring theory), Transitive closure, 020207 software engineering, order discrepancies, 0102 computer and information sciences, 02 engineering and technology, 16. Peace & justice, message sequence charts, 01 natural sciences, Rotation formalisms in three dimensions, Race condition, Constant (computer programming), discord, 010201 computation theory & mathematics, Computer Science (miscellaneous), 0202 electrical engineering, electronic engineering, information engineering, Order (group theory), Algorithm
Abstract: Message Sequence Charts (MSCs) and High-level Message Sequence Charts (HMSCs) are formalisms used to describe scenarios of message passing protocols. We propose using Allen's logic to represent the temporal order of the messages. We introduce the concept of discord to quantify the discrepancies between the intuition and the semantics of the ordering between messages in different nodes of an HMSC. We study the algorithmic properties of this concept: we show that while the discord of a pair of messages is hard to compute in general, the problem becomes polynomial-time computable if the number of nodes of the HMSC or the number of processes is constant. Moreover, for a given HMSC, it is always computationally easy to identify a pair of messages that exhibits the worst-case discord and compute the discord of this pair.
Published: 2010

76. Haptic Recognition of Two-Dimensional Raised-Line Patterns by Early-Blind, Late-Blind, and Blindfolded Sighted Adults

Author: Delphine Picard, Samuel Lebaz, Catherine Monnier, Christophe Jouffrais, Centre de Recherche en Psychologie de la Connaissance, du Langage et de l'Émotion (PsyCLÉ), Aix Marseille Université (AMU), Octogone Unité de Recherche Interdisciplinaire (Octogone), Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université de Toulouse (UT), Etude de L’Interaction Personne SystèmE (IRIT-ELIPSE), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Toulouse Mind & Brain Institut (TMBI), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT), Image & Pervasive Access Lab (IPAL), Université Joseph Fourier - Grenoble 1 (UJF)-Université Pierre et Marie Curie - Paris 6 (UPMC)-National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], Laboratoire Cherchons Pour Voir (CPV), Université de Toulouse (UT)-Institut des Jeunes Aveugles [Toulouse] (IJA)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Centre National de la Recherche Scientifique (CNRS), Dynamique des capacités humaines et des conduites de santé (EPSYLON), Université Montpellier 1 (UM1)-Université Paul-Valéry - Montpellier 3 (UPVM)-Université de Montpellier (UM), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Institute for Infocomm Research - I²R [Singapore]-Centre National de la Recherche Scientifique (CNRS)-Agency for science, technology and research [Singapore] (A*STAR)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-National University of Singapore (NUS)-Université Pierre et Marie Curie - Paris 6 (UPMC), and Université Fédérale Toulouse Midi-Pyrénées-Institut des Jeunes Aveugles [Toulouse] (IJA)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP)
Subjects: Adult, Male, Adolescent, [SCCO.COMP]Cognitive science/Computer science, Experimental and Cognitive Psychology, Blindness, 050105 experimental psychology, Task (project management), 03 medical and health sciences, Young Adult, [SCCO]Cognitive science, 0302 clinical medicine, Artificial Intelligence, Humans, 0501 psychology and cognitive sciences, [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], Visual experience, ComputingMilieux_MISCELLANEOUS, Haptic technology, Communication, business.industry, 05 social sciences, Kinesthetic learning, Middle Aged, Sensory Systems, Form Perception, Ophthalmology, Pattern Recognition, Visual, Touch, [SCCO.PSYC]Cognitive science/Psychology, Female, [INFO.INFO-ET]Computer Science [cs]/Emerging Technologies [cs.ET], Line (text file), business, Psychology, 030217 neurology & neurosurgery, Cognitive psychology, Mental image
Abstract: We investigated the role of visual experience and visual imagery in the processing of two-dimensional (2-D) tactile patterns. The performance of early-blind (EB), late-blind (LB), and blindfolded sighted (S) adults in the recognition of 2-D raised-line patterns was compared. We also examined whether recognition of 2-D tactile patterns depends on the type of memory strategy (eg spatial, visuo-spatial, verbal, and kinesthetic) used by EB, LB, and S participants to perform the task. Significant between-group differences in the recognition performance have not been found despite significant between-group differences in self-reported memory strategies. Recognition performance does not vary significantly with the strategy, but correlates positively with visuo-spatial imagery abilities in the S participants. These findings may be taken to suggest that the difficulties some blind people experience with tactile pictures are not due to difficulties in processing 2-D tactile patterns.
Published: 2010
Full Text: View/download PDF

77. Efficient Incremental Plan Recognition Method for Cognitive Assistance

Author: Aloulou, Hamdi, Feki, Mohamed Ali, Phua, Clifton, Biswas, Jit, Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], and Institute for Infocomm Research - I²R [Singapore]
Subjects: [INFO.INFO-IU]Computer Science [cs]/Ubiquitous Computing, Dementia assistance, plan recognition
Abstract: International audience; In this paper we propose an efficient and incremental plan recognition method for cognitive assistance. We design our unique method based on graph matching and heuristic chaining rules in order to deal with interleaved and sequential activities. The finding of this research work is to be applied to predict abnormal behavior of the users, and optimize assistance for them. We have studied a use case of kitchen environment during lunch time that we will discuss in this paper and targeted Dementia patients. We will present implementation details as well as our evaluation plan.
Published: 2009

78. Pervasive health and wellness management : preface

Author: Mokhtari, Mounir, Sow, Daby, Département Réseaux et Services de Télécommunications (RST), Institut Mines-Télécom [Paris] (IMT)-Télécom SudParis (TSP), Image & Pervasive Access Lab (IPAL), Institute for Infocomm Research - I²R [Singapore]-Centre National de la Recherche Scientifique (CNRS)-Agency for science, technology and research [Singapore] (A*STAR)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-National University of Singapore (NUS)-Université Pierre et Marie Curie - Paris 6 (UPMC), IBM Thomas J. Watson Research Center, IBM, Département Réseaux et Services de Télécommunications (TSP - RST), and Université Joseph Fourier - Grenoble 1 (UJF)-Université Pierre et Marie Curie - Paris 6 (UPMC)-National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore]
Subjects: [INFO.INFO-IU]Computer Science [cs]/Ubiquitous Computing, education
Abstract: International audience; The last two centuries have seen tremendous progress in eHealth related domains. Important advancements in science and medicine have allowed the discovery of cures and preventive measures for several acute diseases. One direct impact of these scientific discoveries is on the prolongation of the average lifespan of humans in many regions of the world
Published: 2009
Full Text: View/download PDF

79. One-dimensional Anderson localization in certain correlated random potentials

Author: Laurent Sanchez-Palencia, Christian Miniatura, Pierre Lugan, Alain Aspect, Benoît Grémaud, Cord A. Müller, Dominique Delande, laboratoire Charles Fabry de l'Institut d'Optique / Optique atomique, Laboratoire Charles Fabry de l'Institut d'Optique (LCFIO), Centre National de la Recherche Scientifique (CNRS)-Institut d'Optique Graduate School (IOGS)-Université Paris-Sud - Paris 11 (UP11)-Centre National de la Recherche Scientifique (CNRS)-Institut d'Optique Graduate School (IOGS)-Université Paris-Sud - Paris 11 (UP11), Laboratoire Kastler Brossel (LKB (Jussieu)), Université Pierre et Marie Curie - Paris 6 (UPMC)-Fédération de recherche du Département de physique de l'Ecole Normale Supérieure - ENS Paris (FRDPENS), École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS), Image & Pervasive Access Lab (IPAL), Institute for Infocomm Research - I²R [Singapore]-Centre National de la Recherche Scientifique (CNRS)-Agency for science, technology and research [Singapore] (A*STAR)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-National University of Singapore (NUS)-Université Pierre et Marie Curie - Paris 6 (UPMC), Centre for Quantum Technologies [Singapore] (CQT), National University of Singapore (NUS), Physikalisches Institut [Bayreuth], Universität Bayreuth, Institut Non Linéaire de Nice Sophia-Antipolis (INLN), Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS), Université Paris-Sud - Paris 11 (UP11)-Institut d'Optique Graduate School (IOGS)-Centre National de la Recherche Scientifique (CNRS)-Université Paris-Sud - Paris 11 (UP11)-Institut d'Optique Graduate School (IOGS)-Centre National de la Recherche Scientifique (CNRS), Fédération de recherche du Département de physique de l'Ecole Normale Supérieure - ENS Paris (FRDPENS), École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS), Université Joseph Fourier - Grenoble 1 (UJF)-Université Pierre et Marie Curie - Paris 6 (UPMC)-National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], and Université Nice Sophia Antipolis (1965 - 2019) (UNS)
Subjects: Physics, Anderson localization, [PHYS.PHYS.PHYS-OPTICS]Physics [physics]/Physics [physics]/Optics [physics.optics], Series (mathematics), FOS: Physical sciences, 01 natural sciences, Atomic and Molecular Physics, and Optics, 010305 fluids & plasmas, Condensed Matter - Other Condensed Matter, Orders of magnitude (time), Ultracold atom, Quantum mechanics, [PHYS.COND.CM-GEN]Physics [physics]/Condensed Matter [cond-mat]/Other [cond-mat.other], 0103 physical sciences, Perturbation theory (quantum mechanics), Matter wave, Born approximation, 010306 general physics, Other Condensed Matter (cond-mat.other), Sign (mathematics)
Abstract: International audience; We study Anderson localization of ultracold atoms in weak, one-dimensional speckle potentials, using perturbation theory beyond Born approximation. We show the existence of a series of sharp crossovers (effective mobility edges) between energy regions where localization lengths differ by orders of magnitude. We also point out that the correction to the Born term explicitly depends on the sign of the potential. Our results are in agreement with numerical calculations in a regime relevant for experiments. Finally, we analyze our findings in the light of a diagrammatic approach.
Published: 2009
Full Text: View/download PDF

80. Training the Recurrent neural network by the Fuzzy Min-Max algorithm for fault prediction

Author: Ryad Zemouri, Daniel Racoceanu, Noureddine Zerhouni, Eugenia Minca, Florin Filip, Lotfi Beji, Samir Otmane, Azgal Abichou, CEDRIC. Traitement du signal et architectures électroniques (CEDRIC - LAETITIA), Centre d'études et de recherche en informatique et communications (CEDRIC), Ecole Nationale Supérieure d'Informatique pour l'Industrie et l'Entreprise (ENSIIE)-Conservatoire National des Arts et Métiers [CNAM] (CNAM)-Ecole Nationale Supérieure d'Informatique pour l'Industrie et l'Entreprise (ENSIIE)-Conservatoire National des Arts et Métiers [CNAM] (CNAM), Image & Pervasive Access Lab (IPAL), Université Pierre et Marie Curie - Paris 6 (UPMC)-National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], Laboratoire d'automatique de Besançon (LAB), Centre National de la Recherche Scientifique (CNRS)-Ecole Nationale Supérieure de Mécanique et des Microtechniques (ENSMM)-Université de Franche-Comté (UFC), Université Bourgogne Franche-Comté [COMUE] (UBFC)-Université Bourgogne Franche-Comté [COMUE] (UBFC), Franche-Comté Électronique Mécanique, Thermique et Optique - Sciences et Technologies (UMR 6174) (FEMTO-ST), Université de Technologie de Belfort-Montbeliard (UTBM)-Ecole Nationale Supérieure de Mécanique et des Microtechniques (ENSMM)-Université de Franche-Comté (UFC), Université Bourgogne Franche-Comté [COMUE] (UBFC)-Université Bourgogne Franche-Comté [COMUE] (UBFC)-Centre National de la Recherche Scientifique (CNRS), Valahia University of Targoviste [Roumanie] (UVT), Romanian Academy, Ecole Nationale Supérieure d'Informatique pour l'Industrie et l'Entreprise (ENSIIE)-Conservatoire National des Arts et Métiers [CNAM] (CNAM), HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-Ecole Nationale Supérieure d'Informatique pour l'Industrie et l'Entreprise (ENSIIE)-Conservatoire National des Arts et Métiers [CNAM] (CNAM), HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM), Université Joseph Fourier - Grenoble 1 (UJF)-Université Pierre et Marie Curie - Paris 6 (UPMC)-National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], Ecole Nationale Supérieure de Mécanique et des Microtechniques (ENSMM)-Centre National de la Recherche Scientifique (CNRS)-Université de Franche-Comté (UFC), and Université de Technologie de Belfort-Montbeliard (UTBM)-Ecole Nationale Supérieure de Mécanique et des Microtechniques (ENSMM)-Centre National de la Recherche Scientifique (CNRS)-Université de Franche-Comté (UFC)
Subjects: 0209 industrial biotechnology, Artificial neural network, Mean squared error, business.industry, Computer science, Pattern recognition, 02 engineering and technology, Fuzzy control system, Fault (power engineering), Minimax, Fuzzy logic, ComputingMethodologies_PATTERNRECOGNITION, 020901 industrial engineering & automation, Recurrent neural network, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Pattern recognition (psychology), 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Artificial intelligence, business, ComputingMilieux_MISCELLANEOUS
Abstract: In this paper, we present a training technique of a Recurrent Radial Basis Function neural network for fault prediction. We use the Fuzzy Min‐Max technique to initialize the k‐center of the RRBF neural network. The k‐means algorithm is then applied to calculate the centers that minimize the mean square error of the prediction task. The performances of the k‐means algorithm are then boosted by the Fuzzy Min‐Max technique.
Published: 2009
Full Text: View/download PDF

81. Fermionization of a strongly interacting Bose-Fermi mixture in a one-dimensional harmonic trap

Author: Bess Fang, Patrizia Vignolo, Christian Miniatura, Anna Minguzzi, Centre for Quantum Technologies [Singapore] (CQT), National University of Singapore (NUS), Institut Non Linéaire de Nice Sophia-Antipolis (INLN), Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS), Image & Pervasive Access Lab (IPAL), Institute for Infocomm Research - I²R [Singapore]-Centre National de la Recherche Scientifique (CNRS)-Agency for science, technology and research [Singapore] (A*STAR)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-National University of Singapore (NUS)-Université Pierre et Marie Curie - Paris 6 (UPMC), Laboratoire de physique et modélisation des milieux condensés (LPM2C), Université Joseph Fourier - Grenoble 1 (UJF)-Centre National de la Recherche Scientifique (CNRS), Université Nice Sophia Antipolis (1965 - 2019) (UNS), and Université Joseph Fourier - Grenoble 1 (UJF)-Université Pierre et Marie Curie - Paris 6 (UPMC)-National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore]
Subjects: Physics, Density matrix, Condensed Matter::Quantum Gases, Bose gas, Condensed matter physics, FOS: Physical sciences, Position and momentum space, Fermion, 01 natural sciences, Atomic and Molecular Physics, and Optics, 010305 fluids & plasmas, Momentum, Condensed Matter - Other Condensed Matter, [PHYS.COND.CM-GEN]Physics [physics]/Condensed Matter [cond-mat]/Other [cond-mat.other], 0103 physical sciences, Atomic physics, 010306 general physics, Fermi gas, Quantum statistical mechanics, Boson, Other Condensed Matter (cond-mat.other)
Abstract: We consider a strongly interacting one-dimensional (1D) Bose-Fermi mixture confined in a harmonic trap. It consists of a Tonks-Girardeau (TG) gas (1D Bose gas with repulsive hard-core interactions) and of a non-interacting Fermi gas (1D spin-aligned Fermi gas), both species interacting through hard-core repulsive interactions. Using a generalized Bose-Fermi mapping, we determine the exact particle density profiles, momentum distributions and behaviour of the mixture under 1D expansion when opening the trap. In real space, bosons and fermions do not display any phase separation: the respective density profiles extend over the same region and they both present a number of peaks equal to the total number of particles in the trap. In momentum space the bosonic component has the typical narrow TG profile, while the fermionic component shows a broad distribution with fermionic oscillations at small momenta. Due to the large boson-fermion repulsive interactions, both the bosonic and the fermionic momentum distributions decay as $C p^{-4}$ at large momenta, like in the case of a pure bosonic TG gas. The coefficient $C$ is related to the two-body density matrix and to the bosonic concentration in the mixture. When opening the trap, both momentum distributions "fermionize" under expansion and turn into that of a Fermi gas with a particle number equal to the total number of particles in the mixture., revised version; 8 pages, 7 figures
Published: 2009

82. Unsupervised Learning Method for Image Classification based on Distribution of Hierarchical Feature Tree

Author: Duong, Thach-Thao, Lim, Joo-Hwee, Chevallet, Jean-Pierre, Institute for Infocomm Research - I²R [Singapore], Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], Modélisation et Recherche d’Information Multimédia [Grenoble] (MRIM), Laboratoire d'Informatique de Grenoble (LIG), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF), National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], and Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)
Subjects: [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], ComputingMilieux_MISCELLANEOUS
Abstract: International audience; no abstract
Published: 2008

83. Fusion de multi-modalités et réduction par sémantique latente Application à la recherche de documents multimédia et à l'annotation automatique d'images

Author: Pham, Trong-Ton, Chevallet, Jean-Pierre, Lim, Joo-Hwee, Modélisation et Recherche d’Information Multimédia [Grenoble] (MRIM), Laboratoire d'Informatique de Grenoble (LIG), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF), Institute for Infocomm Research - I²R [Singapore], Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS), and National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore]
Subjects: [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR]
Abstract: International audience; Ce papier étudie la "sémantique latente" entre des éléments visuels et textuels d'une collection multimédia, appliquée à deux tâches : (1) la Recherche de Document Multimédia (RDM) contenant des images et du texte ; et (2) l'Annotation Automatique d'Images (AAI). La sémantique latente, habituellement utilisée dans l'indexation textuelle, est mise à profit ici pour faire apparaître des liens entre les descriptions textuelles et visuelles des images. Nous avons ainsi deux contributions principales. Il s'agit d'une part, de la première étude sur l'influence de la sémantique latente entre termes textuels et visuels, sur une grande collection de documents. En effet, cette méthode est testée sur une collection de 20000 images touristiques. D'autre part, nous démontrons que la fusion des différents modalités d'image (i.e. termes visuels vs textuels, et différentes méthode de représentations d'image) améliore le résultat d'une annotation au- tomatique des images par du texte. Nos collections de test sont la base d'images annotées de COREL et la base d'Image CLEF 2006.
Published: 2008

84. Similarity Learning for Nearest Neighbor Classification

Author: Eric Gaussier, Ali Mustafa Qamar, Joo-Hwee Lim, Jean-Pierre Chevallet, Laboratoire d'Informatique de Grenoble (LIG), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS), Modélisation et Recherche d’Information Multimédia [Grenoble] (MRIM), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS), Institute for Infocomm Research - I²R [Singapore], Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF), and National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore]
Subjects: Computer Science::Machine Learning, Jaccard index, business.industry, kNN, Pattern recognition, 02 engineering and technology, Perceptron, Similarity Learning, Classification, Class (biology), k-nearest neighbors algorithm, Euclidean distance, Similarity (network science), 020204 information systems, [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], 0202 electrical engineering, electronic engineering, information engineering, Symmetric matrix, 020201 artificial intelligence & image processing, Artificial intelligence, business, Similarity learning, Metric Learning, Mathematics
Abstract: International audience; In this paper, we propose an algorithm for learning a general class of similarity measures for kNN classification. This class encompasses, among others, the standard cosine measure, as well as the Dice and Jaccard coefficients. The algorithm we propose is an extension of the voted perceptron algorithm and allows one to learn different types of similarity functions (either based on diagonal, symmetric or asymmetric similarity matrices). The results we obtained show that learning similarity measures yields significant improvements on several collections, for two prediction rules: the standard kNN rule, which was our primary goal, and a symmetric version of it.
Published: 2008

85. Rich representation and ranking for photographic image retrieval in ImageCLEF 2007

Author: Joo-Hwee Lim, Sheng Gao, Jean-Pierre Chevallet, Image Perception, Access and Language (IPAAL), Université Joseph Fourier - Grenoble 1 (UJF)-École Nationale Supérieure de Physique de Grenoble (ENSPG)-UNIV NATIONALE DE SINGAPOUR-AGENCY FOR SCIENCE TECHNOLOGY AND RESEAR-Centre National de la Recherche Scientifique (CNRS), Modélisation et Recherche d’Information Multimédia [Grenoble] (MRIM), Laboratoire d'Informatique de Grenoble (LIG), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF), Institute for Infocomm Research - I²R [Singapore], Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], Université Joseph Fourier - Grenoble 1 (UJF)-École Nationale Supérieure de Physique de Grenoble (ENSPG)-AGENCY FOR SCIENCE TECHNOLOGY AND RESEAR-National University of Singapore (NUS)-Centre National de la Recherche Scientifique (CNRS), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS), National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], and Fauvet, Marie-Christine
Subjects: Modality (human–computer interaction), Information retrieval, Computer science, Feature extraction, Search engine indexing, 02 engineering and technology, Ranking (information retrieval), Visualization, 020204 information systems, Histogram, [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, [INFO.INFO-IR] Computer Science [cs]/Information Retrieval [cs.IR], Representation (mathematics), Image retrieval
Abstract: International audience; The task of ad-hoc photographic image retrieval in ImageCLEF 2007 international benchmark is to retrieve relevant images in the database to the user query formulated as keywords and image examples. This paper presents rich representation and indexing technologies exploited in our system that participated in ImageCLEF 2007. It uses diverse visual content representation, text representation, pseudo-relevance feedback and fusion, which make our system, with mean average precision 0.2833, in the 4th place among 457 automatic runs submitted from 20 participants to photographic ImageCLEF 2007 and in the 2nd place in terms of participants. Our systematic analysis in the paper demonstrates that 1) combing diverse low-level visual features and ranking technologies significantly improves the content-based image retrieval (CBIR) system; 2) cross-modality pseudo-relevance feedback improves the system performance; and 3) fusion of CBIR and TBIR outperforms individual modality based system.
Published: 2008

86. Domain knowledge conceptual inter-media indexing

Author: Joo-Hwee Lim, Jean-Pierre Chevallet, Diem Thi Hoang Le, Laboratoire d'Informatique de Grenoble (LIG), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF), Institute for Infocomm Research - I²R [Singapore], Image & Pervasive Access Lab (IPAL), and National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore]
Subjects: Information retrieval, Point (typography), Computer science, business.industry, InformationSystems_INFORMATIONSTORAGEANDRETRIEVAL, Search engine indexing, computer.software_genre, Image (mathematics), Index (publishing), [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], ComputingMethodologies_DOCUMENTANDTEXTPROCESSING, Domain knowledge, Artificial intelligence, business, computer, ComputingMilieux_MISCELLANEOUS, Natural language processing
Abstract: Conceptual Indexing is a way to produce only one index for many multilingual documents. Inter-Media conceptual indexing promotes the use of common concepts between two media in order to use a single index for several media. In this paper we explore such an advance indexing point of view. We show the benefit of an automatic conceptual indexing for texts and its extension for text and image documents. Tests are conducted on the multilingual image and text medical document corpus of the CLEF initiative, where we obtain best results on text in 2005 and 2006, and show promising results on images, and best results for the combination of image and text.
Published: 2007
Full Text: View/download PDF

87. Knowledge-Assisted Medical Image Retrieval

Author: Jean-Pierre Chevallet, Joo-Hwee Lim, Caroline Lacoste, Diem Thi Hoang He, Institute for Infocomm Research - I²R [Singapore], Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], Laboratoire d'Informatique de Grenoble (LIG), and Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)
Subjects: Modality (human–computer interaction), Information retrieval, 020205 medical informatics, Computer science, InformationSystems_INFORMATIONSTORAGEANDRETRIEVAL, Search engine indexing, Unified Medical Language System, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Semantics, 03 medical and health sciences, 0302 clinical medicine, Ranking, [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], 0202 electrical engineering, electronic engineering, information engineering, Medical imaging, 030212 general & internal medicine, Visual Word, Structured prediction, Image retrieval, ComputingMilieux_MISCELLANEOUS
Abstract: In this paper, we present a knowledge-assisted approach to index and retrieve large volume of medical images. Both images and associated texts are indexed using medical concepts from the Unified Medical Language System (UMLS) meta-thesaurus. We propose a structured learning framework for modular acquisition of medical semantics from images with complementary global and local image indexing schemes. Two fusion approaches are also developed to improve text retrieval using the UMLS-based image indexing: a simple post-query fusion and a visual modality filtering to remove visually aberrant images according to the query modality concepts. On the ImageCLEFmed 2005 database, our framework outperformed our previous result which ranked top in the ImageCLEFmed 2005 Medical Image Retrieval task benchmark.
Published: 2007

88. Scene Recognition with Camere Phones for Tourist Information Access

Author: Lim, Joo-Hwee, Li, Yiqun, You, Yilun, Chevallet, Jean-Pierre, Institute for Infocomm Research - I²R [Singapore], Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], Laboratoire d'Informatique de Grenoble (LIG), and Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)
Subjects: [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Abstract: International audience; Camera phones present new opportunities and challenges for mobile information association and retrieval. The visual input in the real environment is a new and rich interaction modality between a mobile user and vast information base connected to a userâï¿½ï¿½s device via rapidly advancing communication infrastructure. We have developed a system for tourist information access to provide scene description based on an image taken of the scene. In this paper, we describe the working system, the STOIC 101 database, and a new pattern discovery algorithm to learn image patches that are recurrent within a scene class and discriminative across others. We report preliminary scene recognition results on 90 scenes, trained on 5 images per scene, with an accuracy of 92% and 88% on a test set of 110 images, with and without location priming.
Published: 2007

89. Object Identification and Retrieval from Efficient Image Matching Snap2Tell with the STOIC dataset

Author: Jean-Pierre Chevallet, Mun-Kew Leong, Joo-Hwee Lim, Laboratoire d'Informatique de Grenoble (LIG), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF), Institute for Infocomm Research - I²R [Singapore], Image & Pervasive Access Lab (IPAL), and National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore]
Subjects: Computer science, InformationSystems_INFORMATIONSTORAGEANDRETRIEVAL, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Mobile Information Retrieval, Library and Information Sciences, Management Science and Operations Research, Content-based image retrieval, Test collection building, Image texture, 0202 electrical engineering, electronic engineering, information engineering, Media Technology, Relevance (information retrieval), Visual Word, Image retrieval, Feature detection (computer vision), Information retrieval, 020207 software engineering, Computer Science Applications, Automatic image annotation, Feature (computer vision), [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], 020201 artificial intelligence & image processing, Object identification, Information Systems
Abstract: International audience; Traditional content based image retrieval attempts to retrieve images using syntactic features for a query image. Annotated image banks and Google allow the use of text to retrieve images. In this paper, we studied the task of using the content of an image to retrieve information in general. We describe the significance of object identification in an information retrieval paradigm that uses image set as intermediate means in indexing and matching. We also describe a unique Singapore Tourist Object Identification Collection with associated queries and relevance judgments for evaluating the new task and the need for efficient image matching using simple image features. We present comprehensive experimental evaluation on the effects of feature dimensions, context, spatial weightings, coverage of image indexes, and query devices on task performance. Lastly we describe the current system developed to support mobile image-based tourist information retrieval.
Published: 2007

90. Latent Semantic Fusion Model for Image Retrieval and Annotation

Author: Nicolas Maillot, Joo-Hwee Lim, Jean-Pierre Chevallet, Trong-Ton Pham, Modélisation et Recherche d’Information Multimédia [Grenoble] (MRIM), Laboratoire d'Informatique de Grenoble (LIG), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF), Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS), National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], and Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)
Subjects: Information retrieval, Computer science, Latent semantic analysis, InformationSystems_INFORMATIONSTORAGEANDRETRIEVAL, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 020207 software engineering, 02 engineering and technology, Annotation, Multimedia document, Automatic image annotation, [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Visual Word, Image retrieval, ComputingMilieux_MISCELLANEOUS, Latent semantic indexing
Abstract: This paper studies the effect of Latent Semantic Analysis (LSA) on two different tasks: multimedia document retrieval (MDR) and automatic image annotation (AIA). The contributions of this paper are twofold. First, to the best of our knowledge, this work is the first study of the influence of LSA on the retrieval of a significant number of multimedia documents (i.e. collection of 20000 tourist images). Second, it shows how different image representations (region-based and keypoint-based) can be combined by LSA to improve automatic image annotation. The document collections used for these experiments are the Corel photo collection and ImageCLEF 2006 collection.
Published: 2007

91. Medical Image Retrieval based on Knowledge-Assisted Text and Image Indexing

Author: Lacoste, Caroline, Lim, Joo-Hwee, Chevallet, Jean-Pierre, Le, Thi Hoang Diem, Institute for Infocomm Research - I²R [Singapore], Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], Laboratoire d'Informatique de Grenoble (LIG), and Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)
Subjects: Knowledge-based image indexing, Unified Medical Language System, content-based image retrieval, [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], InformationSystems_INFORMATIONSTORAGEANDRETRIEVAL, visual ontology
Abstract: International audience; Voluminous medical images are generated daily. They are critical assets for medical diagnosis, research, and teaching. To facilitate automatic indexing and retrieval of large medical image databases, both images and associated texts are indexed using medical concepts from the Unified Medical Language System (UMLS) meta-thesaurus. We propose a structured learning framework based on Support Vector Machines to facilitate modular design and learning of medical semantics from images. We present two complementary visual indexing approaches within this framework: a global indexing to access image modality, and a local indexing to access semantic local features. Two fusion approaches are developed to improve textual retrieval using the UMLS-based image indexing. First, a simple fusion of the textual and visual retrieval approaches is proposed, improving significantly the retrieval results of both text and image retrieval. Second, a visual modality filtering is designed to remove visually aberrant images according to the query modality concept(s). Using the ImageCLEFmed database, we demonstrate the effectiveness of our framework that is superior when compared to the automatic runs evaluated in 2005 on the same Medical Image Retrieval task.
Published: 2007

92. Towards Automatic Mobile Blogging

Author: Pujianto Cemerlang, Jun Zhang, Yilun You, Joo-Hwee Lim, Jean-Pierre Chevallet, Institute for Infocomm Research - I²R [Singapore], Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], Department of Physics [New York], New York University [New York] (NYU), NYU System (NYU)-NYU System (NYU), Applied Math Laboratory Courant Institute of Mathematical Sciences (AML - COURANT INSTITUTE), Modélisation et Recherche d’Information Multimédia [Grenoble] (MRIM), Laboratoire d'Informatique de Grenoble (LIG), and Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)
Subjects: Mobile radio, Multimedia, business.industry, Computer science, 05 social sciences, Mobile computing, 02 engineering and technology, Mobile blogging, computer.software_genre, Popularity, Camera phone, World Wide Web, [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], 0202 electrical engineering, electronic engineering, information engineering, Information system, 020201 artificial intelligence & image processing, 0501 psychology and cognitive sciences, Electronic publishing, The Internet, business, computer, 050107 human factors, Tourism, ComputingMilieux_MISCELLANEOUS
Abstract: International audience; Weblog (usually shortened as blog) has gained its popularity lately. There are about 70,000 new blogs a day and about 29,100 blog updates an hour. As an emerging blogging phenomenon, with the proliferation of camera phones, mobile bloggers can write their blogs almost instantaneously. But how much further can current mobile blogging tools enhance the experience? In this paper, we propose a Mobilog framework to automate context-relevant annotation and synthesise personalised content for mobile blogging. In particular, we describe a system implementation of the framework, Travelog, adapted for tourism applications. Finally, we discuss the challenges and future possibilities for mobile blogging.
Published: 2006

93. Concept Propagation Based on Visual Similarity. Application to Medical Image Annotation

Author: Chevallet, Jean-Pierre, Maillot, Nicolas, Lim, Joo-Hwee, Modélisation et Recherche d’Information Multimédia [Grenoble] (MRIM), Laboratoire d'Informatique de Grenoble (LIG), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF), Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], and Institute for Infocomm Research - I²R [Singapore]
Subjects: Annotation Propagation, [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Conceptual Indexing, Visual Similarity
Abstract: International audience; This paper presents an approach for image annotation propagation to images which have no annotations. In some specific domains, the assumption that visual similarity implies (partial) semantic similarity can be made. For instance, in medical imaging, two images of the same anatomic part in a given modality have a very similar appearance. In the proposed approach, a conceptual indexing phase extracts concepts from texts; a visual similarity between images is computed and then combined with conceptual text indexing. Annotation propagation driven by prior knowledge on the domain is finally performed. Domain knowledge used is a meta-thesaurus for both indexing and annotations propagation. The proposed approach has been applied on the imageCLEF medical image collection.
Published: 2006

94. Scene Identification using Discriminative Patterns

Author: Joo-Hwee Lim, Sheng Gao, Jean-Pierre Chevallet, Institute for Infocomm Research - I²R [Singapore], Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], Modélisation et Recherche d’Information Multimédia [Grenoble] (MRIM), Laboratoire d'Informatique de Grenoble (LIG), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF), Image Perception, Access and Language (IPAAL), Université Joseph Fourier - Grenoble 1 (UJF)-École Nationale Supérieure de Physique de Grenoble (ENSPG)-UNIV NATIONALE DE SINGAPOUR-AGENCY FOR SCIENCE TECHNOLOGY AND RESEAR-Centre National de la Recherche Scientifique (CNRS), and Fauvet, Marie-Christine
Subjects: Contextual image classification, Computer science, business.industry, Rank (computer programming), ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 020207 software engineering, Pattern recognition, 02 engineering and technology, Information retrieval applications, Camera phone, Image (mathematics), Support vector machine, Identification (information), Discriminative model, [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Computer vision, [INFO.INFO-IR] Computer Science [cs]/Information Retrieval [cs.IR], Artificial intelligence, business
Abstract: International audience; With the proliferation of camera phones, new information retrieval applications will emerge. The image of a scene captured by a camera phone can be a query to a remote server to identify the scene and return relevant information. But unconstrained scene identification is an open problem. In this paper, we propose a discriminative measure to rank image patterns sampled from target scene classes. Support vector classifiers are then trained using top discriminative patterns for scene identification using voting. We demonstrate our generic approach on two scene databases (ZuBuD and STOIC) with promising results.
Published: 2006
Full Text: View/download PDF

95. SnapToTell : Accès ubiquitaire à de l'information multimédia à partir d'un téléphone portable. Application sur une base d'images de Singapour

Author: Chevallet, Jean-Pierre, Lim, Joo-Hwee, Modélisation et Recherche d’Information Multimédia [Grenoble] (MRIM), Laboratoire d'Informatique de Grenoble (LIG), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF), Institute for Infocomm Research - I²R [Singapore], Image & Pervasive Access Lab (IPAL), and National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore]
Subjects: using context for IR, Recherche d'Information (RI) par l'image, ubiquitous Information Retrieval, [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], Terminaux mobile de RI. KEYWORDS: image Information Retrieval (IR), utilisation du contexte en RI, mobile device for IR, RI ubiquitaire
Abstract: International audience; Avec la prolifération des téléphones portables munis dï¿½appareils photo, beaucoup de nouvelles applications et services vont émerger : nous présentons le système SnapToTell, qui permet de fournir de l'information à partir de requêtes images prises dï¿½un téléphone portable. Nous présentons également des résultats expérimentaux sur lï¿½identification de scènes basée une collection de test d'images originales et réalistes de scènes à Singapour. ABSTRACT. With the proliferation of camera phones, many novel applications and services will emerge. In this paper, we present the SnapToTell system, which provides information directory service to tourists based on pictures taken by the camera phones and location information. Next we present experimental results on scene recognition based on a realistic data set of scenes and locations in Singapore which form a new original application oriented image test bed freely available.
Published: 2005

96. VisMed: A Visual Vocabulary Approach for Medical Image Indexing and Retrieval

Author: Jean-Pierre Chevallet, Joo-Hwee Lim, Institute for Infocomm Research - I²R [Singapore], Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], Modélisation et Recherche d’Information Multimédia [Grenoble] (MRIM), Laboratoire d'Informatique de Grenoble (LIG), and Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)
Subjects: Information retrieval, Computer science, Feature vector, Search engine indexing, 02 engineering and technology, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, Automatic image annotation, Automatic indexing, [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Visual Word, Medical diagnosis, Image retrieval
Abstract: Voluminous medical images are generated daily. They are critical assets for medical diagnosis, research, and teaching. To facilitate automatic indexing and retrieval of large medical image databases, we propose a structured framework for designing and learning vocabularies of meaningful medical terms associated with visual appearance from image samples. These VisMed terms span a new feature space to represent medical image contents. After a multi-scale detection process, a medical image is indexed as compact spatial distributions of VisMed terms. A flexible tiling (FlexiTile) matching scheme is proposed to compare the similarity between two medical images of arbitrary aspect ratios. We evaluate the VisMed approach on the medical retrieval task of the ImageCLEF 2004 benchmark. Based on 2% of the 8725 CasImage collection, we cropped 1170 image regions to train and validate 40 VisMed terms using support vector machines. The Mean Average Precision (MAP) over 26 query topics is 0.4156, an improvement over all the automatic runs in ImageCLEF 2004.
Published: 2005

97. Advances in Digital Home Image Albums

Author: Mulhem, Philippe, Lim, Joo-Hwee, Leow, Wee-Kheng, Kankanhalli, Mohan, Fauvet, Marie-Christine, Modélisation et Recherche d’Information Multimédia [Grenoble] (MRIM), Laboratoire d'Informatique de Grenoble (LIG), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF), Institute for Infocomm Research - I²R [Singapore], Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], Image Perception, Access and Language (IPAAL), Université Joseph Fourier - Grenoble 1 (UJF)-École Nationale Supérieure de Physique de Grenoble (ENSPG)-UNIV NATIONALE DE SINGAPOUR-AGENCY FOR SCIENCE TECHNOLOGY AND RESEAR-Centre National de la Recherche Scientifique (CNRS), National University of Singapore (NUS), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS), National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], and Université Joseph Fourier - Grenoble 1 (UJF)-École Nationale Supérieure de Physique de Grenoble (ENSPG)-AGENCY FOR SCIENCE TECHNOLOGY AND RESEAR-National University of Singapore (NUS)-Centre National de la Recherche Scientifique (CNRS)
Subjects: [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], [INFO.INFO-IR] Computer Science [cs]/Information Retrieval [cs.IR], ComputingMilieux_MISCELLANEOUS
Abstract: International audience; no abstract
Published: 2003

98. Mining evolutions of complex spatial objects using a single-attributed Directed Acyclic Graph

Author: Jean-François Boulicaut, Jérémy Sanhes, Claude Pasquier, Frédéric Flouvat, Nazha Selmaoui-Folcher, Chengcheng Mu, Institut de sciences exactes et appliquées (ISEA), Université de la Nouvelle-Calédonie (UNC), Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS)-MATHEMATIQUES, SCIENCES ET TECHNOLOGIES DE L'INFORMATION ET DE LA COMMUNICATION (UJF)-Agency for science, technology and research [Singapore] (A*STAR)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], Scalable and Pervasive softwARe and Knowledge Systems (Laboratoire I3S - SPARKS), Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S), Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA), Data Mining and Machine Learning (DM2L), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-École Centrale de Lyon (ECL), Université de Lyon-Université Lumière - Lyon 2 (UL2)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), and Université de Lyon-Université Lumière - Lyon 2 (UL2)
Subjects: Theoretical computer science, Computer science, Ranging, 02 engineering and technology, Directed acyclic graph, Data structure, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Human-Computer Interaction, Compact space, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Artificial Intelligence, Hardware and Architecture, [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], 020204 information systems, Scalability, 0202 electrical engineering, electronic engineering, information engineering, Information system, Graph (abstract data type), ComputingMilieux_MISCELLANEOUS, Software, Information Systems
Abstract: Directed acyclic graphs (DAGs) are used in many domains ranging from computer science to bioinformatics, including industry and geoscience. They enable to model complex evolutions where spatial objects (e.g., soil erosion) may move, (dis)appear, merge or split. We study a new graph-based representation, called attributed DAG (a-DAG). It enables to capture interactions between objects as well as information on objects (e.g., characteristics or events). In this paper, we focus on pattern mining in such data. Our patterns, called weighted paths, offer a good trade-off between expressiveness and complexity. Frequency and compactness constraints are used to filter out uninteresting patterns. These constraints lead to an exact condensed representation (without loss of information) in the single-graph setting. A depth-first search strategy and an optimized data structure are proposed to achieve the efficiency of weighted path discovery. It does a progressive extension of patterns based on database projections. Relevance, scalability and genericity are illustrated by means of qualitative and quantitative results when mining various real and synthetic datasets. In particular, we show how such an approach can be used to monitor soil erosion using remote sensing and geographical information system (GIS) data.
Published: 2020
Full Text: View/download PDF

99. Contextual Bandits for Advertising Campaigns: A Diffusion-Model Independent Approach

Author: Alexandra Iacob, Bogdan Cautis, Silviu Maniu, Centre National de la Recherche Scientifique (CNRS), Université Paris-Sud - Paris 11 (UP11), Université Paris-Saclay, Image & Pervasive Access Lab (IPAL), National University of Singapore (NUS)-Agency for science, technology and research [Singapore] (A*STAR)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], Laboratoire Interdisciplinaire des Sciences du Numérique (LISN), Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS), and SIAM
Subjects: [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract: International audience; Motivated by scenarios of information diffusion and advertising in social media, we study an influence maximization problem in which little is assumed to be known about the diffusion network or about the model that determines how information may propagate. In such a highly uncertain environment, one can focus on multiround diffusion campaigns, with the objective to maximize the number of distinct users that are influenced or activated, starting from a known base of few influential nodes. During a campaign, spread seeds are selected sequentially at consecutive rounds, and feedback is collected in the form of the activated nodes at each round. A round's impact (reward) is then quantified as the number of newly activated nodes. Overall, one must maximize the campaign's total spread, as the sum of rounds' rewards. In this setting, an exploreexploit approach could be used to learn the key underlying diffusion parameters, while running the campaign. We describe and compare two methods of contextual multi-armed bandits, with upper-confidence bounds on the remaining potential of influencers, one using a generalized linear model and the Good-Turing estimator for remaining potential (GLM-GT-UCB), and another one that directly adapts the LinUCB algorithm to our setting (LogNorm-LinUCB). We show that they outperform baseline methods using state-of-the-art ideas, on synthetic and real-world data, while at the same time exhibiting different and complementary behavior, depending on the scenarios in which they are deployed.
Published: 2022
Full Text: View/download PDF

100. Multitask Prompted Training Enables Zero-Shot Task Generalization

Author: Sanh, Victor, Webson, Albert, Raffel, Colin, Bach, Stephen, Sutawika, Lintang, Alyafeai, Zaid, Chaffin, Antoine, Stiegler, Arnaud, Le Scao, Teven, Raja, Arun, Dey, Manan, Bari, M Saiful, Xu, Canwen, Thakker, Urmish, Sharma, Shanya, Szczechla, Eliza, Kim, Taewoon, Chhablani, Gunjan, V. Nayak, Nihal, Datta, Debajyoti, Chang, Jonathan, Jiang, Mike, Wang, Han, Manica, Matteo, Shen, Sheng, Yong, Zheng-Xin, Pandey, Harshit, Mckenna, Michael, Bawden, Rachel, Wang, Thomas, Neeraj, Trishala, Rozen, Jos, Sharma, Abheesht, Santilli, Andrea, Fevry, Thibault, Fries, Jason, Teehan, Ryan, Bers, Tali, Biderman, Stella, Gao, Leo, Wolf, Thomas, Rush, Alexander, Hugging Face, Department of Computer Science (Brown University), Brown University, Konvergen AI, King Fahd University of Petroleum and Minerals (KFUPM), 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)-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), IMATAG [Rennes], Hyperscience, Institute for Infocomm Research - I²R [Singapore], SAP AI Research (SAP AI ), School of Computer Engineering [Singapore] (NTU), Nanyang Technological University [Singapour], Department of Computer Science and Engineering [Univ California San Diego] (CSE - UC San Diego), University of California [San Diego] (UC San Diego), University of California (UC)-University of California (UC), SambaNova Systems, Walmart Labs, Scott Tiger S.A., Vrije Universiteit Amsterdam [Amsterdam] (VU), Oracle, University of Virginia, AsusTeK Computer (ASUS), ZEALS, New York University [New York] (NYU), NYU System (NYU), IBM Research [Zurich], University of California [Berkeley] (UC Berkeley), University of California (UC), Sans affiliation, Parity, Automatic Language Modelling and ANAlysis & Computational Humanities (ALMAnaCH), Inria de Paris, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), CyberCube, Naver Labs Europe [Meylan], Birla Institute of Technology and Science (BITS Pilani), Università degli Studi di Roma 'La Sapienza' = Sapienza University [Rome] (UNIROMA), Point72, Stanford University, Charles River Analytics, EleutherAI, Booz Hallen Hamilton Inc, and ANR-19-P3IA-0001,PRAIRIE,PaRis Artificial Intelligence Research InstitutE(2019)
Subjects: [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
Abstract: International audience; Large language models have recently been shown to attain reasonable zero-shot generalization on a diverse set of tasks (Brown et al., 2020). It has been hypothesized that this is a consequence of implicit multitask learning in language models’ pretraining (Radford et al., 2019). Can zero-shot generalization instead be directly induced by explicit multitask learning? To test this question at scale, we develop a system for easily mapping any natural language tasks into a human-readable prompted form. We convert a large set of supervised datasets, each with multiple prompts with diverse wording. These prompted datasets allow for benchmarking the ability of a model to perform completely held-out tasks. We fine-tune a pre-trained encoder-decoder model (Raffel et al., 2020; Lester et al., 2021) on this multitask mixture covering a wide variety of tasks. The model attains strong zero-shot performance on several standard datasets, often outperforming models up to 16x its size. Further, our approach attains strong performance on a subset of tasks from the BIG-bench benchmark, outperforming models up to 6x its size. All trained models are available at https://github.com/bigscience-workshop/t-zero, and all prompts are available at https://github.com/bigscience-workshop/promptsource.
Published: 2022

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

Search

Search Constraints

Refine your results

Search Limiters

Topic

Publication Year Range

Language

Publication Type

Journal

Database

Publisher

294 results on '"Institute for Infocomm Research (I2R)"'

Search Results

Catalog

Select search scope, currently: Articles

Catalog

books, media & more in Jio Institute collections

Articles

journal articles & other e-resources