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

Your search keyword '"Institute for Infocomm Research (I2R)"' showing total 293 results

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

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

1. Comparative Study of Band-Power Extraction Techniques for Motor Imagery Classification

Author: Laboratoire Traitement du Signal et de l'Image (LTSI) ; INSERM - Université de Rennes 1, IPARLA (INRIA Bordeaux - Sud-Ouest) ; CNRS - INRIA - Université Sciences et Technologies - Bordeaux I - École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB), Laboratoire Bordelais de Recherche en Informatique (LaBRI) ; CNRS - Université Sciences et Technologies - Bordeaux I - Université Victor Segalen - Bordeaux II - École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB), Brain-Computer Interface Laboratory - Singapore (BCI) ; Institute for Infocomm Research (I2R), VR4I (INRIA - IRISA) ; INRIA - École normale supérieure (ENS) - Cachan - Université de Rennes 1 - Institut National des Sciences Appliquées (INSA) - Rennes, Brodu, Nicolas, Lotte, Fabien, Lécuyer, Anatole, Laboratoire Traitement du Signal et de l'Image (LTSI) ; INSERM - Université de Rennes 1, IPARLA (INRIA Bordeaux - Sud-Ouest) ; CNRS - INRIA - Université Sciences et Technologies - Bordeaux I - École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB), Laboratoire Bordelais de Recherche en Informatique (LaBRI) ; CNRS - Université Sciences et Technologies - Bordeaux I - Université Victor Segalen - Bordeaux II - École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB), Brain-Computer Interface Laboratory - Singapore (BCI) ; Institute for Infocomm Research (I2R), VR4I (INRIA - IRISA) ; INRIA - École normale supérieure (ENS) - Cachan - Université de Rennes 1 - Institut National des Sciences Appliquées (INSA) - Rennes, Brodu, Nicolas, Lotte, Fabien, and Lécuyer, Anatole
Abstract: International audience, We review different techniques for extracting the power information contained in frequency bands in the context of electroencephalography (EEG) based Brain-Computer Interfaces (BCI). In this domain it is common to apply only one algorithm for extracting the power information. However previous work and our current study confirm that one may indeed expect varying degrees of success by choosing inadequate algorithms for the power extraction. Our results suggest that on average one algorithm seems superior for extracting the power information for Motor Imagery tasks : the application of a Morlet wavelet on the raw EEG signals, with the time-frequency resolution tradeoff selected by cross-validation.

2. Potential contamination of stream waters by ultramafic mining sediments: Identification of geochemical makers (New Caledonia)

Author: Nazha Selmaoui-Folcher, Aurélie Boula, Christine Laporte-Magoni, Olivier Bour, Peggy Gunkel-Grillon, Université de la Nouvelle-Calédonie (UNC), Institut de sciences exactes et appliquées (ISEA), Géosciences Rennes (GR), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire des Sciences de l'Univers de Rennes (OSUR)-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)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore], CNRT (Centre National de Recherche Technologique) Nickel & Environment in New Caledonia, Université de Rennes (UR)-Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire des Sciences de l'Univers de Rennes (OSUR), Université de Rennes (UR)-Institut national des sciences de l'Univers (INSU - CNRS)-Université de Rennes 2 (UR2)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)-Institut national des sciences de l'Univers (INSU - CNRS)-Université de Rennes 2 (UR2)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)-Centre National de la Recherche Scientifique (CNRS), 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], Centre National de la Recherche Scientifique (CNRS)-Observatoire des Sciences de l'Univers de Rennes (OSUR)-Institut national des sciences de l'Univers (INSU - CNRS)-Université de Rennes 1 (UR1), and Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)
Subjects: Geochemistry, ultramafic complexes, STREAMS, 010501 environmental sciences, 01 natural sciences, surface waters, Geochemistry and Petrology, Ultramafic rock, [SDU.STU.GC]Sciences of the Universe [physics]/Earth Sciences/Geochemistry, [SDU.STU.HY]Sciences of the Universe [physics]/Earth Sciences/Hydrology, 0105 earth and related environmental sciences, geography, geography.geographical_feature_category, dissolved metal concentration, 04 agricultural and veterinary sciences, Massif, total metal concentration, 6. Clean water, hydrogeochemical background, machine learning, Soil water, [SDE]Environmental Sciences, 040103 agronomy & agriculture, Erosion, 0401 agriculture, forestry, and fisheries, Environmental science, Economic Geology, Metalloid, Surface runoff, Sediment transport
Abstract: International audience; The ultramafic massifs of New Caledonia are mainly composed of regolites with lateritic soils rich in metals such as Co, Fe, Mg and Ni. The nickeliferous ore is exploited by opencast mines. After rainfalls, erosion and particle runoff cause the mobilization of metals and metalloids in surface waters. The objective of this study is (i) to determine the geochemical background of metals and metalloids in surface waters draining a mining ultramafic massif, (ii) to identify the geochemical markers influenced by the mining of nickeliferous ore (iii) and to define discriminant values of the mining impact. Hydrochemical monitoring was carried out on five streams draining the Koniambo massif over a 15-years period. Twenty-four elements were analyzed for their total concentration and 18 for their dissolved concentration (
Published: 2022
Full Text: View/download PDF

3. Inclusive Adaptation of Existing Board Games for Gamers with and without Visual Impairments using a Spatial Augmented Reality Framework for Touch Detection and Audio Feedback

Author: Lauren Thévin, Christophe Jouffrais, Bernard Oriola, Anke Brock, Nicolas Rodier, Martin Hachet, Université Catholique de l'Ouest (UCO), Institut für Informatik [München/Munich] (LMU), Ludwig-Maximilians-Universität München (LMU), 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 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), Popular interaction with 3d content (Potioc), Laboratoire Bordelais de Recherche en Informatique (LaBRI), Université de Bordeaux (UB)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)-Centre National de la Recherche Scientifique (CNRS)-Université de Bordeaux (UB)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)-Centre National de la Recherche Scientifique (CNRS)-Inria Bordeaux - Sud-Ouest, 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)-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], ENAC - Equipe Informatique Interactive (LII), Ecole Nationale de l'Aviation Civile (ENAC), 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, Université de Bordeaux (UB)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)-Université de Bordeaux (UB)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)-Inria Bordeaux - Sud-Ouest, 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)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore]
Subjects: Attractiveness, Computer Networks and Communications, Computer science, 05 social sciences, ComputingMilieux_PERSONALCOMPUTING, 020207 software engineering, Special needs, 02 engineering and technology, Braille, Human-Computer Interaction, Entertainment, Interactivity, Human–computer interaction, 0202 electrical engineering, electronic engineering, information engineering, 0501 psychology and cognitive sciences, Augmented reality, Audio feedback, [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], Adaptation (computer science), 050107 human factors, Social Sciences (miscellaneous), ComputingMilieux_MISCELLANEOUS
Abstract: International audience; Board games allow us to share collective entertainment experiences. They entertain because of the interactions between players, physical manipulation of tokens and decision making. Unfortunately, most board games exclude people with visual impairments as they were not initially designed for players with special needs. Through a user-centered design process with an accessible game library and visually impaired players, we observed challenges and solutions in making existing board games accessible through handcrafted solutions (tactile stickers, braille labels, etc.). In a second step, we used Spatial Augmented Reality (SAR), to make existing board games inclusive by adding interactivity (GameARt). In a case study with an existing board game considered as not accessible (Jamaica), we designed an interactive SAR version with touch detection (JamaicAR). We evaluated this prototype in a user study with 5 groups of 3 players each, including sighted, low vision and blind players. All players, independent of visual status, were able to play the Augmented Reality game. Moreover, the game was rated positively by all players regarding attractiveness, play engrossment, enjoyment and social connectivity. Our work shows that Spatial Augmented Reality has the potential to make board games accessible to people with visual impairments when handcrafted adaptations fall short.
Published: 2021
Full Text: View/download PDF

4. Nonintrusive Vital Signs Monitoring for Sleep Apnea Patients: A Preliminary Study

Author: Jit Biswas, Bessam Abdulrazak, Ibrahim Sadek, Edwin Seet, Mounir Mokhtari, 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 ), Department of Visual computing, Institute for Infocomm Research, Institute for Infocomm Research - I²R [Singapore], Institut for Infocomm Research, Agency for science, technology and research [Singapore] ( A*STAR ), Université de Sherbrooke [Sherbrooke], Département Réseaux et Services de Télécommunications ( RST ), Institut Mines-Télécom [Paris]-Télécom SudParis ( TSP ), 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], Département Informatique et Réseaux (INFRES), Télécom ParisTech, Khoo Teck Puat Hospital (KTPH), Alexandra Health, Singapore University of Technology and Design (SUTD), Département d'informatique [Sherbrooke] (UdeS), Faculté des sciences [Sherbrooke] (UdeS), Université de Sherbrooke (UdeS)-Université de Sherbrooke (UdeS), Département Réseaux et Services de Télécommunications (RST), and Institut Mines-Télécom [Paris] (IMT)-Télécom SudParis (TSP)
Subjects: medicine.medical_specialty, [ INFO.INFO-TS ] Computer Science [cs]/Signal and Image Processing, General Computer Science, Respiratory rate, 0206 medical engineering, Vital signs, 02 engineering and technology, vital signs, Ballistocardiography, 03 medical and health sciences, 0302 clinical medicine, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Internal medicine, Heart rate, medicine, General Materials Science, ComputingMilieux_MISCELLANEOUS, Shallow breathing, business.industry, General Engineering, Sleep apnea, medicine.disease, sleep apnea, 020601 biomedical engineering, technology and services for home care, 3. Good health, Obstructive sleep apnea, Breathing, Cardiology, e-health, Sleep (system call), lcsh:Electrical engineering. Electronics. Nuclear engineering, medicine.symptom, business, lcsh:TK1-9971, 030217 neurology & neurosurgery
Abstract: Sleep is a fundamental and vital physiological function. Getting enough quality sleep is necessary to a person's mental health, physiological well-being, quality of life, and safety. Sleep-disordered breathing, specifically obstructive sleep apnea can result in serious health issues, including hypertension and stroke. The current approaches for diagnosing sleep disorders are burdensome, intrusive, and can affect the patient's sleep quality. As a result, there is a crucial need for less cumbersome systems to diagnose sleep-related problems. In this paper, we evaluated the capacity of the microbend fiber optic sensor to monitor heart rate and respiration in a nonintrusive manner. In addition, we tested the capacity of the sensor in discriminating between shallow breathing and no breathing. The proposed sensor was compared with the three-channel portable monitoring device (ApneaLink) in a clinical setting during a drug-induced sleep endoscopy. Across all ten patients recruited for our study, the system achieved satisfactory results in the mean heart rate and the mean respiratory rate with an error of 0.55 ± 0.59 beats/minute and 0.38 ± 0.32 breaths/minute, respectively. Besides, the Pearson correlation coefficient between the proposed sensor and the reference device was 0.96 and 0.78 for heart rate and respiration, respectively. On the contrary, the proposed sensor provided a very low sensitivity (24.24 ± 12.81%) and a relatively high specificity (85.88 ± 6.01%) for sleep apnea detection. It is expected that this preliminary research will pave the way toward unobtrusive detection of vital signs in real time.
Published: 2018
Full Text: View/download PDF

5. Creating Accessible Interactive Audio-Tactile Drawings Using Spatial Augmented Reality

Author: Nicolas Rodier, Martin Hachet, Nicolas Palard, Anke Brock, Lauren Thévin, Christophe Jouffrais, Popular interaction with 3d content (Potioc), Laboratoire Bordelais de Recherche en Informatique (LaBRI), Université de Bordeaux (UB)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)-Université de Bordeaux (UB)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)-Inria Bordeaux - Sud-Ouest, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Ludwig Maximilian University [Munich] (LMU), 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), 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], RealityTech, Ecole Nationale de l'Aviation Civile (ENAC), ENAC - Equipe Informatique Interactive (LII), Université de Bordeaux (UB)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)-Centre National de la Recherche Scientifique (CNRS)-Université de Bordeaux (UB)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)-Centre National de la Recherche Scientifique (CNRS)-Inria Bordeaux - Sud-Ouest, 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), and 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]
Subjects: Computer science, Visual impairment, 02 engineering and technology, Special education, Content creation, Software, Accessible graphics, Human–computer interaction, Participatory design, 0202 electrical engineering, electronic engineering, information engineering, medicine, Audio-tactile drawings, 0501 psychology and cognitive sciences, [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], Graphics, 050107 human factors, Social work, business.industry, Accessible maps, 05 social sciences, Spatial augmented reality, 020207 software engineering, Accessibility, Augmented reality, medicine.symptom, business
Abstract: International audience; Interactive tactile graphics have shown a true potential for people with visual impairments, for instance for acquiring spatial knowledge. Until today, however, they are not well adopted in real-life settings (e.g. special education schools). One obstacle consists in the creation of these media, which requires specific skills, such as the use of vector-graphic software for drawing and inserting interactive zones, which is challenging for stakeholders (social workers, teachers, families of people with visual impairments, etc.). We explored how a Spatial Augmented Reality approach can enhance the creation of interactive tactile graphics by sighted users. We developed the system using a participatory design method. A user study showed that the augmented reality device allowed stakeholders (N=28) to create interactive tactile graphics more efficiently than with a regular vector-drawing software (baseline), independently of their technical background.
Published: 2019
Full Text: View/download PDF

6. Comparing Interaction Techniques to Help Blind People Explore Maps on Small Tactile Devices

Author: Anke Brock, Mathieu Simonnet, Bernard Oriola, Antonio Serpa, Christophe Jouffrais, Laboratoire d'Economie et de Gestion de l'Ouest (LEGO), Université de Bretagne Sud (UBS)-Université de Brest (UBO)-Institut Mines-Télécom [Paris] (IMT)-Institut Brestois des Sciences de l'Homme et de la Société (IBSHS), Université de Brest (UBO)-Université Bretagne Loire (UBL)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT), Département Logique des Usages, Sciences sociales et Sciences de l'Information (IMT Atlantique - LUSSI), IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Ecole Nationale de l'Aviation Civile (ENAC), Popular interaction with 3d content (Potioc), Laboratoire Bordelais de Recherche en Informatique (LaBRI), Université de Bordeaux (UB)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)-Centre National de la Recherche Scientifique (CNRS)-Université de Bordeaux (UB)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)-Centre National de la Recherche Scientifique (CNRS)-Inria Bordeaux - Sud-Ouest, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), 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 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), Centre National de la Recherche Scientifique (CNRS), 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], ANR-14-CE17-0018,AccessiMap,Les cartographies (Open Data) interactives, collaboratives et accessibles pour les déficients visuels(2014), Université de Brest (UBO)-Université Bretagne Loire (UBL)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Université de Bordeaux (UB)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)-Université de Bordeaux (UB)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)-Inria Bordeaux - Sud-Ouest, 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, 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)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Institute for Infocomm Research - I²R [Singapore]
Subjects: Touchscreen, Interaction, Computer Networks and Communications, Computer science, Visual impairment, Neuroscience (miscellaneous), Tactile device, lcsh:Technology, 050105 experimental psychology, Memorization, Task (project management), law.invention, Human–computer interaction, law, medicine, 0501 psychology and cognitive sciences, [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], lcsh:Science, Sensory cue, 050107 human factors, Screen reader, lcsh:T, 05 social sciences, Spatial cognition, Accessibility, Computer Science Applications, Human-Computer Interaction, lcsh:Q, medicine.symptom
Abstract: International audience; Exploring geographic maps on touchscreens is a difficult task in the absence of vision as those devices miss tactile cues. Prior research has therefore introduced non-visual interaction techniques designed to allow visually impaired people to explore spatial configurations on tactile devices. In this paper, we present a study in which six blind and six blindfolded sighted participants evaluated three of those interaction techniques compared to a screen reader condition. We observed that techniques providing guidance result in a higher user satisfaction and more efficient exploration. Adding a grid-like structure improved the estimation of distances. None of the interaction techniques improved the reconstruction of the spatial configurations. The results of this study allow improving the design of non-visual interaction techniques that support a better exploration and memorization of maps in the absence of vision.
Published: 2019
Full Text: View/download PDF

7. A novel generic dictionary-based denoising method for improving noisy and densely packed nuclei segmentation in 3D time-lapse fluorescence microscopy images

Author: Thomas Boudier, Lamees Nasser, 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 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: 0301 basic medicine, Computer science, Noise reduction, lcsh:Medicine, Boundary (topology), Context (language use), Tracking (particle physics), Article, 030218 nuclear medicine & medical imaging, Image (mathematics), 03 medical and health sciences, 0302 clinical medicine, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Position (vector), Microscopy, [INFO]Computer Science [cs], Segmentation, lcsh:Science, ComputingMilieux_MISCELLANEOUS, 030304 developmental biology, 0303 health sciences, Multidisciplinary, business.industry, lcsh:R, Pattern recognition, Sparse approximation, 030104 developmental biology, 13. Climate action, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], lcsh:Q, Noise (video), Artificial intelligence, business, 030217 neurology & neurosurgery
Abstract: Time-lapse fluorescence microscopy is an essential technique for quantifying various characteristics of cellular processes, i.e. cell survival, migration, and differentiation. To perform high-throughput quantification of cellular processes, nuclei segmentation and tracking should be performed in an automated manner. Nevertheless, nuclei segmentation and tracking are challenging tasks due to embedded noise, intensity inhomogeneity, shape variation as well as a weak boundary of nuclei. Although several nuclei segmentation approaches have been reported in the literature, dealing with embedded noise remains the most challenging part of any segmentation algorithm. We propose a novel denoising algorithm, based on sparse coding, that can both enhance very faint and noisy nuclei signal but simultaneously detect nuclei position accurately. Furthermore our method is based on a limited number of parameters, with only one being critical, which is the approximate size of the objects of interest. We also show that our denoising method coupled with classical segmentation method works properly in the context of the most challenging cases. To evaluate the performance of the proposed method, we tested our method on two datasets from the cell tracking challenge. Across all datasets, the proposed method achieved satisfactory results with 96:96% recall for the C. elegans dataset. Besides, in the Drosophila dataset, our method achieved very high recall (99:3%).
Published: 2019
Full Text: View/download PDF

8. Nonintrusive heart rate measurement using ballistocardiogram signals: a comparative study

Author: Ibrahim Sadek, Jit Biswas, 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), and Institute for Infocomm Research - I²R [Singapore]
Subjects: Discrete wavelet transform, Artifact (error), Computer science, business.industry, Multiresolution analysis, Fast Fourier transform, Autocorrelation, 020206 networking & telecommunications, 02 engineering and technology, Signal, Wavelet, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Signal Processing, Cepstrum, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Computer vision, Artificial intelligence, Electrical and Electronic Engineering, business, ComputingMilieux_MISCELLANEOUS
Abstract: Nonintrusive monitoring and long-term monitoring of vital signs are essential requirements for early diagnosis and prevention due to many reasons, one of the most important being improving the quality of life. In this paper, we present a comparative study using various algorithms, i.e., wavelet analysis, cepstrum, fast Fourier transform, and autocorrelation function for heart rate measurement. The heart rate was measured from noisy ballistocardiogram signals acquired from 50 subjects in a sitting position using a massage chair. The signals were unobtrusively collected from a microbend fiber-optic sensor embedded within the headrest of the chair and then transmitted to a computer through a Bluetooth connection. The multiresolution analysis of the maximal overlap discrete wavelet transform was implemented for heart rate measurement. The error between the proposed method and the reference electrocardiogram is estimated in beats per minute using the mean absolute error in which the system achieved relatively good results ( $$10.12\pm 4.69$$ ) despite the remarkable amount of motion artifact produced owing to the frequent body movements and/or vibrations of the massage chair during stress relief massage. In contrast, the error between the proposed method and the reference signal was very large when other algorithms, i.e., cepstrum, fast Fourier transform, and autocorrelation function, were implemented for heart rate measurement.
Published: 2018
Full Text: View/download PDF

9. Uncertainty handling in semantic reasoning for accurate context understanding

Author: Hamdi Aloulou, Jit Biswas, Thibaut Tiberghien, Mounir Mokhtari, Romain Endelin, Institut Mines-Télécom [Paris] (IMT), Interactive Digital Humans (IDH), Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier (LIRMM), Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-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], Institute for Infocomm Research - I²R [Singapore], 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: Decision support system, Information Systems and Management, Uncertainty handling, Computer science, Semantic modeling, Context (language use), Machine learning, computer.software_genre, Reasoning under uncertainty, Management Information Systems, [INFO.INFO-IU]Computer Science [cs]/Ubiquitous Computing, Activity recognition, Artificial Intelligence, Order (exchange), Context awareness, Focus (computing), business.industry, [INFO.INFO-IT]Computer Science [cs]/Information Theory [cs.IT], [INFO.INFO-ES]Computer Science [cs]/Embedded Systems, Artificial intelligence, business, Decision making, computer, Software
Abstract: International audience; Context aware systems are using various sensing technologies in order to recognize end-users situations; however these technologies are vulnerable to hardware failures, energy depletion, communication problems and multiple other issues. This generates an uncertainty about the events received from the sensors, which is translated into a confidence given to these events. This confidence is used in the context-aware reasoning through a fusion of sensor data to make more accurate decisions. In this paper, we focus on handling uncertainty in sensor-based context aware applications and we propose a method for the measurement of uncertainty based on both physical and operational behaviors of the sensors. We describe how the level of uncertainty is incorporated into different layers of a semantically driven context aware system and how it is transferred to a decision engine in order to perform more accurate decisions in ambiguous observations.
Published: 2015
Full Text: View/download PDF

10. Preserving privacy in distributed system (PPDS) protocol: Security analysis

Author: Talel Abdessalem, Sihem Mesnager, Stéphane Bressan, Mounira Msahli, Ashref Aloui, Cybersecurity for Communication and Networking (CCN), Laboratoire Traitement et Communication de l'Information (LTCI), Institut Mines-Télécom [Paris] (IMT)-Télécom Paris-Institut Mines-Télécom [Paris] (IMT)-Télécom Paris, Département Informatique et Réseaux (INFRES), Télécom ParisTech, 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), Laboratoire Analyse, Géométrie et Applications (LAGA), Université Paris 8 Vincennes-Saint-Denis (UP8)-Centre National de la Recherche Scientifique (CNRS)-Institut Galilée-Université Paris 13 (UP13), 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], Université Paris 8 Vincennes-Saint-Denis (UP8)-Université Paris 13 (UP13)-Institut Galilée-Centre National de la Recherche Scientifique (CNRS), and 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]
Subjects: Information privacy, Authentication, Security analysis, business.industry, Computer science, Node (networking), Distributed computing, Big data, 02 engineering and technology, Encryption, Proof of concept, 020204 information systems, 0202 electrical engineering, electronic engineering, information engineering, [INFO]Computer Science [cs], business, Protocol (object-oriented programming), ComputingMilieux_MISCELLANEOUS
Abstract: Within the diversity of existing Big Data and data processing solutions, meeting the requirements of privacy and security is becoming a real need. In this paper we tackle the security analysis of a new protocol of data processing in distributed system (PPDS). This protocol is composed of three phases: authentication, node head selection and data linking. This paper deals with its formal validation done using HLPSL language via AVISPA. We provide also its security analysis. Some performance analysis based on its proof of concept are also given in this paper.
Published: 2017
Full Text: View/download PDF

11. A dictionary-based approach to reduce noise in fluorescent microscopy images

Author: Paula Coronado, Etienne David, Thomas Boudier, Lamees Nasser, 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), 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: 0301 basic medicine, Computer science, business.industry, Noise reduction, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Pattern recognition, 03 medical and health sciences, Noise, 030104 developmental biology, Live cell imaging, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Microscopy, Preprocessor, Segmentation, [INFO]Computer Science [cs], Sensitivity (control systems), Artificial intelligence, Neural coding, business, ComputingMilieux_MISCELLANEOUS
Abstract: Live imaging of cells and small organisms is an important step for understanding and analyzing biological functions via studying cellular dynamics. Cell segmentation and tracking in microscopy images are challenging tasks due mainly to embedded noise. We proposed to use an adaptive dictionary learning approach for filtering and reducing noise in fluorescent microscopy images. We applied our method to detect nuclei in noisy images from different types of datasets and the results demonstrated that our proposed algorithm had a satisfactory performance with an average sensitivity of 99.1%, precision of 92.4% and f-measure of 95.6%. As a result, this method is a promising preprocessing tool for detecting nuclei in noisy microscopy images.
Published: 2017
Full Text: View/download PDF

12. NucleiNet: A convolutional encoder-decoder network for bio-image denoising

Author: Lamees Nasser, Yifei Hu, Hao Yu, Thomas Boudier, Philippe Coquet, Hang Xu, Zichuan Liu, Biologie du Développement et Reproduction (BDR), Institut National de la Recherche Agronomique (INRA), CINTRA / SEEE Nanyang Technological University, Nanyang Technological University [Singapour], 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], School of Electrical and Electronic Engineering (EEE), 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 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: Cell Nucleus, 0301 basic medicine, Computer science, business.industry, Noise reduction, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Machine Learning, 03 medical and health sciences, 030104 developmental biology, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Animals, [INFO]Computer Science [cs], Video denoising, Computer vision, Artificial intelligence, Encoder decoder, Noise (video), Image denoising, Caenorhabditis elegans, business, ComputingMilieux_MISCELLANEOUS
Abstract: Generic and scalable data analysis procedures are highly demanded by the increasing number of multi-dimensional biomedical data. However, especially for time-lapse biological data, the high level of noise prevents for automated high-throughput analysis methods. The rapid developing of machine-learning methods and particularly deep-learning methods provide new tools and methodologies that can help in the denoising of such data. Using a convolutional encoder-decoder network, one can provide a scalable bio-image platform, called NucleiNet, to automatically segment, classify and track cell nuclei. The proposed method can achieve 0.99 F-score and 0.99 pixel-wise accuracy on C. elegans dataset, which means that over 99% of nuclei can be successfully detected with no merging nuclei found.
Published: 2017
Full Text: View/download PDF

13. Protocol for preserving privacy in distributed system (PPDS)

Author: Talel Abdessalem, Stéphane Bressan, Mounira Msahli, Sihem Mesnager, Ashref Aloui, Cybersecurity for Communication and Networking (CCN), Laboratoire Traitement et Communication de l'Information (LTCI), Institut Mines-Télécom [Paris] (IMT)-Télécom Paris-Institut Mines-Télécom [Paris] (IMT)-Télécom Paris, Département Informatique et Réseaux (INFRES), Télécom ParisTech, 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], School of computing [Singapore] (NUS), National University of Singapore (NUS), Laboratoire Analyse, Géométrie et Applications (LAGA), Université Paris 8 Vincennes-Saint-Denis (UP8)-Université Paris 13 (UP13)-Institut Galilée-Centre National de la Recherche Scientifique (CNRS), 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], Université Paris 8 Vincennes-Saint-Denis (UP8)-Centre National de la Recherche Scientifique (CNRS)-Institut Galilée-Université Paris 13 (UP13), 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: Information privacy, Authentication, Privacy by Design, business.industry, Computer science, Node (networking), Internet privacy, Big data, Data security, 020206 networking & telecommunications, Cryptography, 02 engineering and technology, Computer security, computer.software_genre, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, [INFO]Computer Science [cs], business, Protocol (object-oriented programming), computer, ComputingMilieux_MISCELLANEOUS
Abstract: Preserving privacy in Big data is one of the most debated topics of computer security. The fast growing volume of data and the need of companies to extract value from that data creates new complicated and serious security challenges. Despite its wide spread, the common use and the popularity of Big data paradigm, significant risks and challenges are inherent to this new concept, especially when we talk about externalized treatment of sensitive data via insecure network. In this paper we tackle the privacy challenge in Big Data. We focus in special case of data processing. Several Bank agencies want to share data processing while protecting the privacy. We propose a new protocol of communication between agencies. This protocol is composed of three phases: authentication, node head selection and data linking. Some proof of concept are also given in this paper.
Published: 2017
Full Text: View/download PDF

14. Map Learning with a 3D Printed Interactive Small-Scale Model: Improvement of Space and Text Memorization in Visually Impaired Students

Author: Giraud, Stéphanie, Brock, Anke, Macé, Marc J.-M., Jouffrais, Christophe, Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Institut National de la Recherche en Informatique et en Automatique - INRIA (FRANCE), Institut Mines-Télécom (FRANCE), Université Paris 1 Panthéon-Sorbonne (FRANCE), Université Grenoble Alpes - UGA (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), National University of Singapore - NUS (REPUBLIC OF SINGAPORE), Université de Bordeaux (FRANCE), Institut National Polytechnique de Toulouse - INPT (FRANCE), Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées, Centre National de la Recherche Scientifique (CNRS), 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), Laboratoire Bordelais de Recherche en Informatique (LaBRI), Université de Bordeaux (UB)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB), Popular interaction with 3d content (Potioc), Université de Bordeaux (UB)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)-Université de Bordeaux (UB)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)-Inria Bordeaux - Sud-Ouest, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Etude de L’Interaction Personne SystèmE (IRIT-ELIPSE), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), 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], 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), 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 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 Bordeaux (UB)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)-Centre National de la Recherche Scientifique (CNRS), Université de Bordeaux (UB)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)-Centre National de la Recherche Scientifique (CNRS)-Université de Bordeaux (UB)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)-Centre National de la Recherche Scientifique (CNRS)-Inria Bordeaux - Sud-Ouest, 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: education technology, Low-cost prototyping, Interactive maps, low-cost prototyping, interactive maps, visual impairment, Visual impairment, Interface homme-machine, Tangible user interfaces, spatial cognition, ComputingMilieux_COMPUTERSANDEDUCATION, Psychology, [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], special needs, Education technology, Special needs, General Psychology, Spatial cognition, tangible user interfaces
Abstract: International audience; Special education teachers for visually impaired students rely on tools such as raised-line maps (RLMs) to teach spatial knowledge. These tools do not fully and adequately meet the needs of the teachers because they are long to produce, expensive, and not versatile enough to provide rapid updating of the content. For instance, the same RLM can barely be used during different lessons. In addition, those maps do not provide any interactivity, which reduces students' autonomy. With the emergence of 3D printing and low-cost microcontrollers, it is now easy to design affordable interactive small-scale models (SSMs) which are adapted to the needs of special education teachers. However, no study has previously been conducted to evaluate non-visual learning using interactive SSMs. In collaboration with a specialized teacher, we designed a SSM and a RLM representing the evolution of the geography and history of a fictitious kingdom. The two conditions were compared in a study with 24 visually impaired students regarding the memorization of the spatial layout and historical contents. The study showed that the interactive SSM improved both space and text memorization as compared to the RLM with braille legend. In conclusion, we argue that affordable home-made interactive small scale models can improve learning for visually impaired students. Interestingly, they are adaptable to any teaching situation including students with specific needs.
Published: 2017
Full Text: View/download PDF

15. Text-Edge-Box: An Object Proposal Approach for Scene Texts Localization

Author: Mounir Mokhtari, Dinh Nguyen, Lu Shijian, Nizar Ouarti, Télécom ParisTech, 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 d'Informatique de Robotique et de Microélectronique de Montpellier (LIRMM), Université de Montpellier (UM)-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 Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)
Subjects: Connected component, Computer science, Orientation (computer vision), business.industry, Distortion (optics), Feature extraction, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Pattern recognition, 02 engineering and technology, 010501 environmental sciences, Object (computer science), 01 natural sciences, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Image (mathematics), Bounding overwatch, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Computer vision, Enhanced Data Rates for GSM Evolution, Artificial intelligence, business, 0105 earth and related environmental sciences
Abstract: International audience; Text proposal has been gaining interest in recent years due to the great success of object proposal in categories-independent object localization. In this paper, we present a novel text-specific proposal technique that provides superior bounding boxes for accurate text localization in scenes. The proposed technique, which we call Text Edge Box (TEB), uses a binary edge map, a gradient map and an orientation map of an image as inputs. Connected components are first found within the binary edge map, which are scored by two proposed low-cue text features that are extracted in the gradient map and the orientation map, respectively. These scores present text probability of connected components and are aggregated in a text edge image. Scene texts proposals are finally generated by grouping the connected components and estimating their likelihood of being words. The proposed TEB has been evaluated on the two public scene text datasets: the Robust Reading Competition 2013 dataset (ICDAR 2013) dataset and the Street View Text (SVT) dataset. Experiments show that the proposed TEB outperforms the state-of-the-art techniques greatly.
Published: 2017
Full Text: View/download PDF

16. Confidential Truth Finding with Multi-Party Computation

Author: Saadeh, Angelo, Senellart, Pierre, Bressan, Stéphane, Laboratoire Traitement et Communication de l'Information (LTCI), Institut Mines-Télécom [Paris] (IMT)-Télécom Paris, CNRS@CREATE Ltd., Département d'informatique - ENS Paris (DI-ENS), École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS), Value from Data (VALDA ), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-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)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria de Paris, Institut National de Recherche en Informatique et en Automatique (Inria), Institut Universitaire de France (IUF), Ministère de l'Education nationale, de l’Enseignement supérieur et de la Recherche (M.E.N.E.S.R.), 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], School of computing [Singapore] (NUS), and National University of Singapore (NUS)
Subjects: Secret-sharing, [INFO.INFO-CR]Computer Science [cs]/Cryptography and Security [cs.CR], Uncertain data, Privacy, Truth finding, Secure multi-party computation
Abstract: International audience; Federated knowledge discovery and data mining are challenged to assess the trustworthiness of data originating from autonomous sources while protecting confidentiality and privacy. Truth-finding algorithms help corroborate data from disagreeing sources. For each query it receives, a truth-finding algorithm predicts a truth value of the answer, possibly updating the trustworthiness factor of each source. Few works, however, address the issues of confidentiality and privacy. We devise and present a secure secret-sharing-based multi-party computation protocol for pseudo-equality tests that are used in truth-finding algorithms to compute additions depending on a condition. The protocol guarantees confidentiality of the data and privacy of the sources. We also present a variants of a truth-finding algorithm that would make the computation faster when executed using secure multi-party computation. We empirically evaluate the performance of the proposed protocol on a state-of-the-art truth-finding algorithm, 3-Estimates, and compare it with that of the baseline plain algorithm. The results confirm that the secret-sharing-based secure multi-party algorithms are as accurate as the corresponding baselines but for proposed numerical approximations that significantly reduce the efficiency loss incurred.
Published: 2023

17. Continuous and unconstrained vital signs monitoring with ballistocardiogram sensors in headrest position

Author: Jit Biswas, Ibrahim Sadek, Zhang Haihong, Bessam Abdulrazak, Mounir Mokhtari, 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 Mines-Télécom [Paris] (IMT), Institute for Infocomm Research - I²R [Singapore], Département Réseaux et Services de Télécommunications (RST), Institut Mines-Télécom [Paris] (IMT)-Télécom SudParis (TSP), Université de Sherbrooke (UdeS), 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 Département Réseaux et Services de Télécommunications (TSP - RST)
Subjects: Discrete wavelet transform, Massage, 020205 medical informatics, medicine.diagnostic_test, Technology and services for home care, business.industry, Multiresolution analysis, 0206 medical engineering, Vital signs, 02 engineering and technology, Sitting, 020601 biomedical engineering, law.invention, Bluetooth, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, law, Fiber optic sensor, Technology and services for assisted-living and elderly, 0202 electrical engineering, electronic engineering, information engineering, medicine, Computer vision, Artificial intelligence, Telecommunications, business, Electrocardiography
Abstract: International audience; Unobtrusive and long-term monitoring of human vital signs are essential requirements for early diagnosis and prophylaxis due to many reasons, one of the most important being improving the quality of life. Currently, vital signs are continuously monitored through sensors attached to the body, such as multiple electrodes for measuring electrical activity of the heart. Such methods may be undesirable, especially for elderly, infants and other groups of people. In this paper, we introduce an improved technique for measuring heart rate from noisy ballistocardiogram signals acquired from 50 human volunteers in a sitting position using a massage chair. The signals are unobtrusively collected from a microbend fiber optic sensor embedded within the headrest of the chair, and then transmitted to a computer through a Bluetooth connection. The heart rate is computed using the multiresolution analysis of the maximal overlap discrete wavelet transform. The error between the proposed method and the reference ECG is estimated in beats per minute using the mean absolute error, where the system achieved relatively good results (7.31 ± 1.60) despite the large amount of motion artifacts produced owing to the frequent body movements and/or vibrations of the massage chair during stress relief massage. Unlike the complete ensemble empirical mode decomposition algorithm, previously employed for heart rate estimation, the suggested system is much faster. Hence, it can be used in real-time applications.
Published: 2017
Full Text: View/download PDF

18. 'DIY' Prototyping of Teaching Materials for Visually Impaired Children: Usage and Satisfaction of Professionals

Author: Christophe Jouffrais, Philippe Truillet, Véronique Gaildrat, Stéphanie Giraud, Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Institut Mines-Télécom (FRANCE), Université Pierre et Marie Curie, Paris 6 - UPMC (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), Agency for Science, Technology and Research - A*STAR (SINGAPORE), National University of Singapore - NUS (REPUBLIC OF SINGAPORE), Université Joseph Fourier Grenoble 1 - UJF (FRANCE), 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, Real Expression Artificial Life (IRIT-REVA), 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 National de la Recherche Scientifique (CNRS), 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], Institut de recherche en informatique de Toulouse ( IRIT ), Institut National Polytechnique [Toulouse] ( INP ) -Université Toulouse 1 Capitole ( UT1 ) -Université Toulouse - Jean Jaurès ( UT2J ) -Université Paul Sabatier - Toulouse 3 ( UPS ) -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 Institut National Polytechnique de Toulouse - INPT (FRANCE)
Subjects: Fablab, Rapid prototyping, Visually impaired, Computer science, Visual impairment, New materials, 02 engineering and technology, [ INFO.INFO-LG ] Computer Science [cs]/Machine Learning [cs.LG], Blind, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], ComputingMilieux_COMPUTERSANDEDUCATION, 0202 electrical engineering, electronic engineering, information engineering, medicine, 0501 psychology and cognitive sciences, [ INFO.INFO-AI ] Computer Science [cs]/Artificial Intelligence [cs.AI], Education technology, Set (psychology), 050107 human factors, Medical education, 4. Education, 05 social sciences, Orientation and Mobility, 020207 software engineering, Intelligence artificielle, Apprentissage, medicine.symptom
Abstract: International audience; Professionals working with visually impaired children (i.e. specialist teachers and educators, Orientation and Mobility trainers, psychologists, etc.) have to create their own teaching materials. Indeed, only few adapted materials exist, and do not fully meet their needs. Thus, rapid prototyping tools and methods could help them to design and make materials adapted to teaching to visually impaired students. In this study, we first designed a blog enabling professionals to create their own teaching materials. Then, we set up a challenge with five teams including one professional of visual impairment and students in computer science. The aim of each team was to design and make a teaching material, based on handcrafting, 3D printing tools and cheap micro-controllers, fitting the needs of the professional. After they have used their material with visually impaired students, we interviewed the professionals in order to evaluate usage and satisfaction. The professionals reported that the materials were easy to make, and valuable for teaching to visually impaired students. They also reported that DIY prototyping, based on 3D printing and cheap microcontrollers, enables them to create their own teaching materials, and hence accurately meet unanswered needs. Importantly, they would advise their colleagues to use this method and new tools. However, they consider that they would need assistance to create new materials on their own.
Published: 2017
Full Text: View/download PDF

19. A novel toolbox to investigate tissue spatial organization applied to the study of the islets of Langerhans

Author: Hoa Tran Thi Nhu, Per Olof Berggren, Rafael Arrojo e Drigo, Thomas Boudier, 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], 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], 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 Lee Kong Chian School of Medicine (LKCMedicine)
Subjects: 0301 basic medicine, Cell type, Cell signaling, [SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging, Gene Expression, Image processing, Cell Communication, Computational biology, Biology, Bioinformatics, Cellular Interactions, Article, Islets of Langerhans, Mice, 03 medical and health sciences, Imaging, Three-Dimensional, 0302 clinical medicine, Image Processing, Computer-Assisted, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, [SDV.MHEP.AHA]Life Sciences [q-bio]/Human health and pathology/Tissues and Organs [q-bio.TO], Animals, Insulin, Spatial Statistic, Islet of Langerhans, Spatial organization, Cell Nucleus, geography, Multidisciplinary, geography.geographical_feature_category, Volumetric data, Nuclei Segmentation, Optical Imaging, Diabetes, 3d image processing, 3D Tissue Spatial Organization, Haplorhini, Glucagon, Islet, [INFO.INFO-MO]Computer Science [cs]/Modeling and Simulation, Toolbox, Mice, Inbred C57BL, 030104 developmental biology, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Single-Cell Analysis, 3D image processing, Somatostatin, Algorithms, 030217 neurology & neurosurgery
Abstract: Thanks to the development of new 3D Imaging techniques, volumetric data of thick samples, especially tissues, are commonly available. Several algorithms were proposed to analyze cells or nuclei in tissues, however these tools are limited to two dimensions. Within any given tissue, cells are not likely to be organized randomly and as such have specific patterns of cell-cell interaction forming complex communication networks. In this paper, we propose a new set of tools as an approach to segment and analyze tissues in 3D with single cell resolution. This new tool box can identify and compute the geographical location of single cells and analyze the potential physical interactions between different cell types and in 3D. As a proof-of-principle, we applied our methodology to investigation of the cyto-architecture of the islets of Langerhans in mice and monkeys. The results obtained here are a significant improvement in current methodologies and provides new insight into the organization of alpha cells and their cellular interactions within the islet’s cellular framework. ASTAR (Agency for Sci., Tech. and Research, S’pore) Published version
Published: 2017
Full Text: View/download PDF

20. Rapid synaptogenesis in the Nucleus Accumbens is induced by a single cocaine administration and stabilized by MAP Kinase interacting kinase 1 activity

Author: Dos Santos, Marc, Salery, Marine, Forget, Benoit, Garcia Perez, Maria Alexandra, Betuing, Sandrine, Boudier, Thomas, Vanhoutte, Peter, Caboche, Jocelyne, Heck, Nicolas, Signalisation Neuronale et Régulations Géniques = Neuronal Signaling and Gene Regulation (NPS-02), Neuroscience Paris Seine (NPS), Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut de Biologie Paris Seine (IBPS), Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut de Biologie Paris Seine (IBPS), Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Agency for science, technology and research [Singapore] (A*STAR), 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], Neurosciences Paris Seine (NPS), 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), Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut de Biologie Paris Seine (IBPS), Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-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 HAL-UPMC, Gestionnaire
Subjects: synaptogenesis, dendritic spine, Cocaine, [SDV.NEU.NB]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]/Neurobiology, [SDV.NEU.NB] Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]/Neurobiology, Biological Psychiatry, MAP Kinase Interacting Kinase (MNK)
Abstract: International audience; Background: Repeated cocaine exposure produces new spine formation in Striatal Projection Neurons (SPNs) of the Nucleus Accumbens (NAc). However, an acute exposure to cocaine can trigger long-lasting synaptic plasticity in SPN leading to behavioral alterations. This raises the intriguing question as to whether acute cocaine could modify enduringly striatal connectivity.Methods: A 3D morphometric analysis of presynaptic glutamatergic boutons and dendritic spines was performed on SPN one hour and one week after a single cocaine administration. Time-lapse two-photon microscopy in adult slices was used to determine the precise molecular events sequence responsible for the rapid spine formation.Results: A single injection triggered a rapid synaptogenesis and persistent increase in glutamatergic connectivity in SPN from the shell part of the NAc, specifically. Synapse formation occurred through clustered growth of active spines contacting pre-existing axonal boutons. Spine growth required ERK activation, while spine stabilization involved transcription-independent protein synthesis driven by MAP kinase interacting kinase-1 (MNK-1), downstream from ERK. The maintenance of new spines driven by MNK-1 was essential for long-term connectivity changes induced by cocaine in vivo.Conclusions: Our study originally demonstrates that an acute administration of cocaine is able to induce stable synaptic rewiring in the NAc, which will likely influence responses to subsequent drug exposure. It also unravels a new functional role for cocaine-induced ERK pathway independently of nuclear targets. Finally, it reveals that MNK-1 has a pivotal role in cocaine-induced connectivity.
Published: 2017
Full Text: View/download PDF

21. Tumor angiogenesis assessment using multi-fluorescent scans on murine slices by Markov Random Field framework

Author: Oumeima Laifa, Daniel Racoceanu, Delphine Le Guillou-Buffello, Université Pierre et Marie Curie - Paris 6 (UPMC), 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: Tumor angiogenesis, Markov random field, Angiogenesis, VEGF receptors, Anti-angiogenic, multi-fluorescence images, apoptosis, Biology, Bioinformatics, Fluorescence, ACM: G.: Mathematics of Computing, Vascular endothelial growth factor, Pazopanib, chemistry.chemical_compound, chemistry, Apoptosis, medicine, Cancer research, biology.protein, pazopanib, [INFO]Computer Science [cs], MRF, ACM: I.: Computing Methodologies, medicine.drug, watershed
Abstract: International audience; The fundamental role of vascular supply in tumor growth makes the evaluation of the angiogenesis crucial in assessing effect of anti-angiogenic therapies. Since many years, such therapies are designed to inhibit the vascular endothelial growth factor (VEGF). To contribute to the assessment of anti-angiogenic agent (Pazopanib) effect on vascular and cellular structures, we acquired data from tumors extracted from a murine tumor model using Multi-Fluorescence Scanning. In this paper, we implemented an unsupervised algorithm combining the Watershed segmentation and Markov Random Field model (MRF). This algorithm allowed us to quantify the proportion of apoptotic endothelial cells and to generate maps according to cell density. Stronger association between apoptosis and endothelial cells was revealed in the tumors receiving anti-angiogenic therapy (n = 4) as compared to those receiving placebo (n = 4). The percentage of apoptotic cells on tumor area is mostly endothelial. Lower density cells were detected in tumor slices presenting higher apoptotic endothelial areas.
Published: 2017

22. Sensor Data Quality Processing for Vital Signs with Opportunistic Ambient Sensing

Author: Zhu Yongwei, Jayachandran Maniyeri, Mounir Mokhtari, Ibrahim Sadek, Jit Biswas, Teo Ju Teng, Chen Zhihao, Zhang Haihong, Ng Soon Huat, 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 Mines-Télécom [Paris] (IMT), Institute for Infocomm Research - I²R [Singapore], 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: Engineering, Support Vector Machine, Feature extraction, 02 engineering and technology, computer.software_genre, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Robustness (computer science), Heart Rate, 0202 electrical engineering, electronic engineering, information engineering, Humans, business.industry, Decision Trees, Discriminant Analysis, 020206 networking & telecommunications, Pattern recognition, Linear discriminant analysis, Random forest, Data Accuracy, Support vector machine, Fiber optic sensor, Data quality, Feedforward neural network, 020201 artificial intelligence & image processing, [SDV.IB]Life Sciences [q-bio]/Bioengineering, Artificial intelligence, Data mining, Neural Networks, Computer, business, computer
Abstract: International audience; Opportunistic ambient sensing involves placement of sensors appropriately so that intermittent contact can be made unobtrusively for gathering physiological signals for vital signs. In this paper, we discuss the results of our quality processing system used to extract heart rate from ballistocardiogram signals obtained from a micro-bending fiber optic sensor pressure mat. Visual inspection is used to label data into informative and non-informative classes based on their heart rate information. Five classifiers are employed for the classification process, i.e., random forest, support vector machine, multilayer, feedforward neural network, linear discriminant analysis, and decision tree. To compute the overall effectiveness of quality processing, the informative signals are processed to estimate interbeat intervals. The system was used to process, data collected from 50 human subjects sitting in a massage chair while performing different activities. Opportunistically collected data was obtained from the fiber optic sensor mat placed on the headrest of the massage chair. Using our classification approach, 57.37% of the dataset was able to provide informative signals. On the informative signals, random forest classifier achieves the best classification accuracy with a mean accuracy of 98.99%. The average of the mean absolute error between the estimated heart rate and the reference ECG is reduced from 13.2 to 8.47. Therefore, the proposed system shows a good robustness for opportunistic ambient sensing.
Published: 2016
Full Text: View/download PDF

23. Automatic Nonlinear Filtering and Segmentation for Breast Ultrasound Images

Author: Sergi Ganau, Ibrahim Sadek, Mohamed Elawady, Abd El Rahman Shabayek, Gerard Pons, Laboratoire Hubert Curien (LHC), Institut d'Optique Graduate School (IOGS)-Université Jean Monnet - Saint-Étienne (UJM)-Centre National de la Recherche Scientifique (CNRS), Institute for Infocomm Research - I²R [Singapore], Institut Mines-Télécom [Paris] (IMT), 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], Interdisciplinary Centre for Security, Reliability and Trust [Luxembourg] (SnT), Université du Luxembourg (Uni.lu), Universitat de Girona (UdG), Department of Pathology, UDIAT Centre Diagnòstic, Corporació Sanitària Parc Taulí, Laboratoire Hubert Curien [Saint Etienne] (LHC), Université Jean Monnet [Saint-Étienne] (UJM)-Centre National de la Recherche Scientifique (CNRS)-Institut d'Optique Graduate School (IOGS), 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), Campilho, Aurélio, and Karray, Fakhri
Subjects: Computer science, Anisotropic diffusion, 02 engineering and technology, Image (mathematics), 03 medical and health sciences, 0302 clinical medicine, Breast Cancer, Ultrasound Imaging, 0202 electrical engineering, electronic engineering, information engineering, medicine, Lesion Segmentation, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Segmentation, Computer vision, Breast ultrasound, Nonlinear Filtering, Ground truth, medicine.diagnostic_test, business.industry, Probabilistic logic, Speckle noise, Filter (signal processing), 3. Good health, 030220 oncology & carcinogenesis, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Speckle Noise Removal, 020201 artificial intelligence & image processing, Artificial intelligence, business
Abstract: International audience; Breast cancer is one of the leading causes of cancer death among women worldwide. The proposed approach comprises three steps as follows. Firstly, the image is preprocessed to remove speckle noise while preserving important features of the image. Three methods are investigated, i.e., Frost Filter, Detail Preserving Anisotropic Diffusion, and Probabilistic Patch-Based Filter. Secondly, Normalized Cut or Quick Shift is used to provide an initial segmentation map for breast lesions. Thirdly, a postprocessing step is proposed to select the correct region from a set of candidate regions. This approach is implemented on a dataset containing 20 B-mode ultrasound images, acquired from UDIAT Diagnostic Center of Sabadell, Spain. The overall system performance is determined against the ground truth images. The best system performance is achieved through the following combinations: Frost Filter with Quick Shift, Detail Preserving Anisotropic Diffusion with Normalized Cut and Probabilistic Patch-Based with Normalized Cut.
Published: 2016
Full Text: View/download PDF

24. Social media marketing analytics : a multicultural approach applied to the beauty & cosmetic sector

Author: Kefi, Hajer, Indra, Sitesh, Abdessalem, Talel, Dauphine Recherches en Management (DRM), Université Paris Dauphine-PSL, Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS), School of computing [Singapore] (NUS), National University of Singapore (NUS), Centre de droit des affaires et de gestion (CEDAG - EA 1516), Université Paris Descartes - Paris 5 (UPD5), Laboratoire Traitement et Communication de l'Information (LTCI), Télécom ParisTech-Institut Mines-Télécom [Paris] (IMT)-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), Dauphine Recherches en Management ( DRM ), Université Paris-Dauphine-Centre National de la Recherche Scientifique ( CNRS ), School of computing [Singapore] ( NUS ), National University of Singapore ( NUS ), Centre de droit des affaires et de gestion ( CEDAG - EA 1516 ), Université Paris Descartes - Paris 5 ( UPD5 ), Laboratoire Traitement et Communication de l'Information ( LTCI ), Télécom ParisTech-Institut Mines-Télécom [Paris]-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 National de la Recherche Scientifique (CNRS)-Université Paris Dauphine-PSL, 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-SI ] Computer Science [cs]/Social and Information Networks [cs.SI], Social Media marketing, Social Network analysis, [SHS.INFO]Humanities and Social Sciences/Library and information sciences, [INFO.INFO-WB]Computer Science [cs]/Web, [ SHS.INFO ] Humanities and Social Sciences/Library and information sciences, [ INFO.INFO-WB ] Computer Science [cs]/Web, Multicultural differences, Facebook, [SHS.GESTION]Humanities and Social Sciences/Business administration, Computer Science - Social and Information Networks, [ SHS.GESTION ] Humanities and Social Sciences/Business administration, [INFO.INFO-SI]Computer Science [cs]/Social and Information Networks [cs.SI]
Abstract: We present in this paper a multicultural approach to social media marketing analytics, applied in two Facebook brand pages: French (individualistic culture, the country home of the brand) versus Saudi Arabian (collectivistic culture, one of its country hosts), which are published by an internationalbeauty \& cosmetics firm. Using social network analysis and content analysis, we identify the most popular posts and the most influential users within these two brand pages and highlight the different communities emerging from brand and users interactions. These communities seem to be culture oriented when they are constructed around socialization branded posts and product-line oriented when advertising branded posts are concerned., Comment: 20th Pacific Asia Conference on Information Systems, PACIS 2016, Jun 2016, Chiayi, Taiwan. 2016
Published: 2016

25. Biomineralization Patterns of Intracellular Carbonatogenesis in Cyanobacteria: Molecular Hypotheses

Author: Thomas Boudier, Fériel Skouri-Panet, Julie Cosmidis, Corinne Cassier-Chauvat, Jinhua Li, Mélanie Poinsot, Marine Blondeau, Jean Michel Guigner, Franck Chauvat, David Moreira, Purificación López-García, Isabel Margaret Oliver, Céline Férard, Karim Benzerara, Nithavong Cam, Eric Leroy, Institut de minéralogie, de physique des matériaux et de cosmochimie (IMPMC), Muséum national d'Histoire naturelle (MNHN)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut de recherche pour le développement [IRD] : UR206-Centre National de la Recherche Scientifique (CNRS), Chinese Academy of Sciences [Changchun Branch] (CAS), Laboratoire de Réactivité de Surface (LRS), Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut de Chimie du CNRS (INC)-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], Agency for science, technology and research [Singapore] (A*STAR), Institut de Chimie et des Matériaux Paris-Est (ICMPE), Institut de Chimie du CNRS (INC)-Université Paris-Est Créteil Val-de-Marne - Paris 12 (UPEC UP12)-Centre National de la Recherche Scientifique (CNRS), University of Colorado [Boulder], Ecologie Systématique et Evolution (ESE), Université Paris-Sud - Paris 11 (UP11)-AgroParisTech-Centre National de la Recherche Scientifique (CNRS), Institut de Biologie Intégrative de la Cellule (I2BC), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS), Institut de minéralogie, de physique des matériaux et de cosmochimie ( IMPMC ), Muséum National d'Histoire Naturelle ( MNHN ) -Université Pierre et Marie Curie - Paris 6 ( UPMC ) -Institut de recherche pour le développement [IRD] : UR206-Centre National de la Recherche Scientifique ( CNRS ), Chinese Academy of Sciences [Changchun Branch] ( CAS ), Laboratoire de Réactivité de Surface ( LRS ), Université Pierre et Marie Curie - Paris 6 ( UPMC ) -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], Agency for science, technology and research [Singapore] ( A*STAR ), Institut de Chimie et des Matériaux Paris-Est ( ICMPE ), Université Paris-Est Créteil Val-de-Marne - Paris 12 ( UPEC UP12 ) -Centre National de la Recherche Scientifique ( CNRS ), University of Colorado Boulder [Boulder], Ecologie Systématique et Evolution ( ESE ), Université Paris-Sud - Paris 11 ( UP11 ) -AgroParisTech-Centre National de la Recherche Scientifique ( CNRS ), Institut de Biologie Intégrative de la Cellule ( I2BC ), Université Paris-Saclay-Centre National de la Recherche Scientifique ( CNRS ) -Commissariat à l'énergie atomique et aux énergies alternatives ( CEA ) -Université Paris-Sud - Paris 11 ( UP11 ), 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 Paris-Est Créteil Val-de-Marne - Paris 12 (UPEC UP12)-Centre National de la Recherche Scientifique (CNRS)-Institut de Chimie du CNRS (INC)
Subjects: 0301 basic medicine, Cyanobacteria, lcsh:QE351-399.2, Cell division, Biology, tomography, 010502 geochemistry & geophysics, 01 natural sciences, cyanobacteria, carboxysome, FtsZ, calcification, 03 medical and health sciences, ACC, STXM, particle size distribution, polyphosphate, biomineralization, Botany, Extracellular, Cytoskeleton, [ SDU.STU.MI ] Sciences of the Universe [physics]/Earth Sciences/Mineralogy, 0105 earth and related environmental sciences, Ultramicrotomy, lcsh:Mineralogy, Geology, Geotechnical Engineering and Engineering Geology, biology.organism_classification, Carboxysome, 030104 developmental biology, Biophysics, Intracellular, Biomineralization, [SDU.STU.MI]Sciences of the Universe [physics]/Earth Sciences/Mineralogy
Abstract: International audience; The recent discovery of intracellular carbonatogenesis in several cyanobacteria species has challenged the traditional view that this process was extracellular and not controlled. However, a detailed analysis of the size distribution, chemical composition and 3-D-arrangement of carbonates in these cyanobacteria is lacking. Here, we characterized these features in Candidatus Gloeomargarita lithophora C7 and Candidatus Synechococcus calcipolaris G9 by conventional transmission electron microscopy, tomography, ultramicrotomy, and scanning transmission X-ray microscopy (STXM). Both Ca. G. lithophora C7 and Ca. S. calcipolaris G9 formed numerous polyphosphate granules adjacent or engulfing Ca-carbonate inclusions when grown in phosphate-rich solutions. Ca-carbonates were scattered within Ca. G. lithophora C7 cells under these conditions, but sometimes arranged in one or several chains. In contrast, Ca-carbonates formed at cell septa in Ca. S. calcipolaris G9 and were segregated equally between daughter cells after cell division, arranging as distorted disks at cell poles. The size distribution of carbonates evolved from a positively to a negatively skewed distribution as particles grew. Conventional ultramicrotomy did not preserve Ca-carbonates explaining partly why intracellular calcification has been overlooked in the past. All these new observations allow discussing with unprecedented insight some nucleation and growth processes occurring in intracellularly calcifying cyanobacteria with a particular emphasis on the possible involvement of intracellular compartments and cytoskeleton.
Published: 2016
Full Text: View/download PDF

26. Haptic Recognition of Emotions in Raised-Line Drawings by Congenitally Blind and Sighted Adults

Author: Christophe Jouffrais, Samuel Lebaz, Delphine Picard, Centre de Recherche en Psychologie de la Connaissance, du Langage et de l'Émotion (PsyCLÉ), Aix Marseille Université (AMU), 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 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), 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), Octogone Unité de Recherche Interdisciplinaire (Octogone), Université de Toulouse (UT)-Université de Toulouse (UT), 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: Visual perception, media_common.quotation_subject, [SCCO.COMP]Cognitive science/Computer science, Facial recognition system, 050105 experimental psychology, Task (project management), [SCCO]Cognitive science, 03 medical and health sciences, 0302 clinical medicine, Perception, 0501 psychology and cognitive sciences, Computer vision, [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], Emotion recognition, media_common, Haptic technology, business.industry, 05 social sciences, Line drawings, Computer Science Applications, Visualization, Human-Computer Interaction, [SCCO.PSYC]Cognitive science/Psychology, [INFO.INFO-ET]Computer Science [cs]/Emerging Technologies [cs.ET], Artificial intelligence, Psychology, business, 030217 neurology & neurosurgery, Cognitive psychology
Abstract: International audience; 15 sighted and 15 congenitally blind adults were to classify raised-line pictures of emotional faces through haptics. Whereas accuracy did not vary significantly between the two groups, the blind adults were faster at the task. These results suggest that raised-line pictures of emotional faces are intelligible to blind adults.
Published: 2011
Full Text: View/download PDF

27. Quasi-static scheduling of communicating tasks

Author: Shaofa Yang, Blaise Genest, P. S. Thiagarajan, Philippe Darondeau, System synthesis and supervision, scenarios (S4), 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], School of computing [Singapore] (NUS), National University of Singapore (NUS), International Institute for Software Technology [Macao] (UNU-IIST), United Nations University (UNU), Distributed and Iterative Algorithms for the Management of Telecommunications Systems (DISTRIBCOM), equipe associée DST, AND DOTS, 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: Quasi-static scheduling, Computer science, Distributed computing, [INFO.INFO-OH]Computer Science [cs]/Other [cs.OH], 0102 computer and information sciences, 02 engineering and technology, Dynamic priority scheduling, 01 natural sciences, Fair-share scheduling, Theoretical Computer Science, Scheduling (computing), [INFO.INFO-NI]Computer Science [cs]/Networking and Internet Architecture [cs.NI], Fixed-priority pre-emptive scheduling, [INFO.INFO-FL]Computer Science [cs]/Formal Languages and Automata Theory [cs.FL], 0202 electrical engineering, electronic engineering, information engineering, Job shop scheduling, Channel bound, Communicating machines, Petri net, C.: Computer Systems Organization/C.2: COMPUTER-COMMUNICATION NETWORKS, Computer Science Applications, Computational Theory and Mathematics, 010201 computation theory & mathematics, [INFO.INFO-ES]Computer Science [cs]/Embedded Systems, 020201 artificial intelligence & image processing, Information Systems
Abstract: Good scheduling policies for distributed embedded applications are required for meeting hard real time constraints and for optimizing the use of computational resources. We study the \emph{quasi-static scheduling} problem in which (uncontrollable) control flow branchings can influence scheduling decisions at run time. Our abstracted distributed task model consists of a network of sequential processes that communicate via point-to-point buffers. In each round, the task gets activated by a request from the environment. When the task has finished computing the required responses, it reaches a pre-determined configuration and is ready to receive a new request from the environment. For such systems, we prove that determining the existence of a scheduling policy that guarantees %blaise uniform upper bounds on buffer capacities is undecidable. However, we show that the problem is decidable for the important subclass of ``data-branching'' systems in which control flow branchings are exclusively due to data-dependent internal choices made by the sequential components. This decidability result exploits ideas derived from the Karp and Miller coverability tree for Petri nets as well as the existential boundedness notion of languages of message sequence charts.
Published: 2010
Full Text: View/download PDF

28. Visual graph modeling for scene recognition and mobile robot localization

Author: Loïc Maisonnasse, Eric Gaussier, Philippe Mulhem, Trong-Ton Pham, 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), Modélisation et Recherche d’Information Multimédia [Grenoble] (MRIM), 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), Analyse de données, Modélisation et Apprentissage automatique [Grenoble] (AMA), 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)-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: Matching (graph theory), Computer Networks and Communications, Computer science, 02 engineering and technology, computer.software_genre, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], 020204 information systems, 0202 electrical engineering, electronic engineering, information engineering, Media Technology, Information retrieval, Computer vision, Visual Word, Spatial analysis, Image retrieval, Scene Recognition, Graph database, business.industry, Robot localization, Mobile robot, Graph theory, Pattern recognition, Language model, Graph, Support vector machine, Categorization, Hardware and Architecture, [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], 020201 artificial intelligence & image processing, Artificial intelligence, business, computer, Software
Abstract: From the issue entitled "Content-based Multimedia Indexing"; International audience; Image retrieval and categorization may need to consider several types of visual features and spatial information between them (e.g., different point of views of an image). This paper presents a novel approach that exploits an extension of the language modeling approach from information retrieval to the problem of graph-based image retrieval and categorization. Such versatile graph model is needed to represent the multiple points of views of images. A language model is defined on such graphs to handle a fast graph matching. We present the experiments achieved with several instances of the proposed model on two collections of images: one composed of 3,849 touristic images and another composed of 3,633 images captured by a mobile robot. Experimental results show that using visual graph model (VGM) improves the accuracies of the results of the standard language model (LM) and outperforms the Support Vector Machine (SVM) method.
Published: 2010
Full Text: View/download PDF

29. Tangible Maps for Visually Impaired Users: Shape-Changing Perspectives

Author: Julie Ducasse, M Macé, Marc J., Marcos Serrano, Christophe Jouffrais, Jouffrais, Christophe, Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Centre National de la Recherche Scientifique - CNRS (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), 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 de Toulouse (UT)-Institut des Jeunes Aveugles [Toulouse] (IJA)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), and 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]
Subjects: InformationSystems_INFORMATIONINTERFACESANDPRESENTATION(e.g.,HCI), [SCCO.COMP]Cognitive science/Computer science, Actuated tangibles, [SCCO] Cognitive science, Intelligence artificielle, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Interactive graphics, [SCCO]Cognitive science, [SCCO.COMP] Cognitive science/Computer science, [SCCO.PSYC]Cognitive science/Psychology, [INFO.INFO-ET] Computer Science [cs]/Emerging Technologies [cs.ET], [SCCO.PSYC] Cognitive science/Psychology, [INFO.INFO-ET]Computer Science [cs]/Emerging Technologies [cs.ET], [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], [INFO.INFO-HC] Computer Science [cs]/Human-Computer Interaction [cs.HC], Non-visual tangible interfaces
Abstract: International audience; Interactive maps for visually impaired people are rarely dynamic and if so, very expensive. We developed a low-cost tangible tabletop interface that enables visually impaired users to dynamically construct maps. To do so, we designed a novel type of physical icons, called Tangible Reels. In this paper, we discuss how actuated Tangible Reels could be used to provide visually impaired users with an access to dynamic tangible maps and advanced functionalities (zoom, pan and exploration of geostatistical data). The three design ideas that we propose open new avenues for shape-changing interfaces for visually impaired users
Published: 2016

30. From Tactile to Virtual: Using a Smartwatch to Improve Spatial Map Exploration for Visually Impaired Users

Author: Christophe Jouffrais, Sandra Bardot, Marcos Serrano, Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Centre National de la Recherche Scientifique - CNRS (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), 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), 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: Geospatial analysis, Computer science, [SCCO.COMP]Cognitive science/Computer science, 02 engineering and technology, computer.software_genre, Interface homme-machine, Smartwatch, [SCCO]Cognitive science, Human–computer interaction, Visually impaired users, Map exploration, 0202 electrical engineering, electronic engineering, information engineering, 0501 psychology and cognitive sciences, Computer vision, [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], 050107 human factors, Wearable technology, business.industry, 05 social sciences, SwIPe, 020207 software engineering, Usability, Filter (signal processing), Grid, Wearable devices, Geospatial data, [SCCO.PSYC]Cognitive science/Psychology, [INFO.INFO-ET]Computer Science [cs]/Emerging Technologies [cs.ET], Artificial intelligence, business, computer, Gesture
Abstract: International audience; Tactile raised-line maps are paper maps widely used by visually impaired people. We designed a mobile technique, based on hand tracking and a smartwatch, in order to leverage pervasive access to virtual maps. We use the smartwatch to render localized text-to-speech and vibratory feedback during hand exploration, but also to provide filtering functions activated by swipe gestures. We conducted a first study to compare the usability of a raised-line map with three virtual maps (plain, with filter, with filter and grid). The results show that virtual maps are usable, and that adding a filter, or a filter and a grid, significantly speeds up data exploration and selection. The results of a following case study showed that visually impaired users were able to achieve a complex task with the device, i.e. finding spatial correlations between two sets of data.
Published: 2016
Full Text: View/download PDF

31. Intégration des Influences Géographique et Temporelle pour la Recommandation de Points d'Intérêt

Author: Griesner, Jean-Benoît, Abdessalem, Talel, Naacke, Hubert, 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], School of computing [Singapore] (NUS), National University of Singapore (NUS), 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), 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-DB]Computer Science [cs]/Databases [cs.DB], [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [INFO]Computer Science [cs]
Abstract: National audience; La recommandation de points d'intérêts (ou POI), est devenue un problème majeur avec l'émergence des réseaux sociaux (ou LBSN). À la différence des approches de recommandation traditionnelles, les données des LBSN présentent des caractéristiques géographique et temporelle importantes qui limitent les performances des algorithmes traditionnels existant. L'intégration de ces caractéristiques dans un unique modèle de factorisation pour augmenter la qualité de la recommandation n'a pas été un problème très étudié jusqu'à présent. Dans ce papier nous présentons GeoMF-TD, une extension d'un modèle de factorisation géographique avec des dépendances temporelles. Nos expérimentations sur un jeu de données réel montre jusqu'à 20% de gain sur la précision de la recommandation.
Published: 2016

32. DiAna, an ImageJ tool for object-based 3D co-localization and distance analysis

Author: Nicolas Heck, Susanne Bolte, Thomas Boudier, Jean-François Gilles, Marc Dos Santos, Neuroscience Paris Seine (NPS), Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut de Biologie Paris Seine (IBPS), Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Signalisation Neuronale et Régulations Géniques = Neuronal Signaling and Gene Regulation (NPS-02), Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut de Biologie Paris Seine (IBPS), 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], Bioinformatics Institute [Singapore], Agency for science, technology and research [Singapore] (A*STAR), Imagerie Cellulaire et Cytométrie de Flux [IBPS] (IBPS-IP), Institut de Biologie Paris Seine (IBPS), Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS), Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut de Biologie Paris Seine (IBPS), 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], Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Sorbonne Université (SU)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université (SU)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), HAL-UPMC, Gestionnaire, Neurosciences Paris Seine (NPS), Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut de Biologie Paris Seine (IBPS), Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS), Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut de Biologie Paris Seine (IBPS), 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), Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS), and Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut de Biologie Paris Seine (IBPS)
Subjects: 0301 basic medicine, Male, Computer science, Interface (Java), Gene Expression, Deconvolution, computer.software_genre, Mice, Co localization, Image Processing, Computer-Assisted, Computer vision, Gene Knock-In Techniques, ComputingMilieux_MISCELLANEOUS, [INFO.INFO-BI] Computer Science [cs]/Bioinformatics [q-bio.QM], Image co-localization, Fluorescence microscopy, Image segmentation, Microscopy, Confocal, Brain, Algorithms, [SDV.OT]Life Sciences [q-bio]/Other [q-bio.OT], Tyrosine 3-Monooxygenase, Recombinant Fusion Proteins, Synaptophysin, Mice, Transgenic, Nerve Tissue Proteins, General Biochemistry, Genetics and Molecular Biology, Antibodies, 03 medical and health sciences, Bacterial Proteins, 3D imaging, Animals, Plug-in, Molecular Biology, Fluorescent Dyes, business.industry, Object based, Spatial analysis, Microtomy, Object (computer science), Luminescent Proteins, 030104 developmental biology, Microscopy, Fluorescence, Vesicular Glutamate Transport Protein 1, Distance analysis, Artificial intelligence, [INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM], business, computer, Software
Abstract: International audience; We present a new plugin for ImageJ called DiAna, for Distance Analysis, which comes with a user-friendly interface. DiAna proposes robust and accurate 3D segmentation for object extraction. The plugin performs automated object-based co-localization and distance analysis. DiAna offers an in-depth analysis of co-localization between objects and retrieves 3D measurements including co-localizing volumes and surfaces of contact. It also computes the distribution of distances between objects in 3D. With DiAna, we furthermore introduce an original method, which allows for estimating the statistical significance of object co-localization. DiAna offers a complete and intuitive 3D image analysis tool for biologists.
Published: 2016
Full Text: View/download PDF

33. Automatic heart rate detection from FBG sensors using sensor fusion and enhanced empirical mode decomposition

Author: Victor Foo Siang Fook, Mounir Mokhtari, Jit Biswas, Ibrahim Sadek, 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], Institute for Infocomm Research - I²R [Singapore], Institut Mines-Télécom [Paris] (IMT), 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: business.industry, Noise (signal processing), Computer science, Process (computing), Sensor fusion, Standard deviation, Hilbert–Huang transform, 3. Good health, Fiber Bragg grating, Sensor array, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Computer vision, Artificial intelligence, Time domain, business, Telecommunications
Abstract: International audience; Cardiovascular diseases are the world's top leading causes of death. Real time monitoring of patients who have cardiovascular abnormalities can provide comprehensive and preventative health care. We investigate the role of the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and sensor fusion for automatic heart rate detection from a mat with embedded Fiber Bragg Grating (FBG) sensor arrays. The fusion process is performed in the time domain by averaging the readings of the sensors for each sensor array. Subsequently, the CEEMDAN is applied to obtain the interbeat intervals. Experiments are performed with 10 human subjects (males and females) lying on two different positions on a bed for a period of 20 minutes. The overall system performance is assessed against the reference ECG signals. The average and standard deviation of the mean relative absolute error are 0.049, 0.019 and 0.047, 0.038 for fused and best sensors respectively. Sensor fusion together with CEEMDAN proved to be robust against motion artifacts caused by body movements.
Published: 2015
Full Text: View/download PDF

34. A new automated 3D detection of synaptic contacts reveals the formation of cortico-striatal synapses upon cocaine treatment in vivo

Author: Jocelyne Caboche, Nicolas Heck, Marine Salery, Antoine Besnard, Peter Vanhoutte, Brahim Amairi, Marc Dos Santos, Thomas Boudier, Etienne Herzog, Université Pierre et Marie Curie - Paris 6 (UPMC), Neuroscience Paris Seine (NPS), Centre National de la Recherche Scientifique (CNRS)-Institut de Biologie Paris Seine (IBPS), Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Pierre et Marie Curie - Paris 6 (UPMC), Physiopathologie des Maladies du Système Nerveux Central, Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Harvard Medical School [Boston] (HMS), Interdisciplinary Institute for Neuroscience (IINS), Université de Bordeaux (UB)-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), Neurobiologie des processus adaptatifs (NPA), Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC), Signalisation Neuronale et Régulations Géniques = Neuronal Signaling and Gene Regulation (NPS-02), Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Institut de Biologie Paris Seine (IBPS), Centre National pour la Recherche Scientifique (CNRS), Institut National de la Sante et de la Recherche Medicale (INSERM), University Pierre and Marie Curie (UPMC), Agence Nationale pour la Recherche (ANR) [ANR-08-BLAN-0287], Fondation Jerome Lejeune, Labex Bio-Psy cluster of excellence, Neurosciences Paris Seine (NPS), Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut de Biologie Paris Seine (IBPS), Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS), Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Pierre et Marie Curie - Paris 6 (UPMC), Centre National de la Recherche Scientifique (CNRS)-Université de Bordeaux (UB), Sorbonne Université (SU)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut de Biologie Paris Seine (IBPS), Sorbonne Université (SU)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université (SU)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS), Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut de Biologie Paris Seine (IBPS), Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut de Biologie Paris Seine (IBPS), Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-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], Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Institut de Biologie Paris Seine (IBPS), Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), and Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut de Biologie Paris Seine (IBPS)
Subjects: Histology, Dendritic spine, Axonal bouton, VGLUT1, Dendritic Spines, Striatum, Biology, Medium spiny neuron, 03 medical and health sciences, Glutamatergic, Mice, 0302 clinical medicine, Cocaine, Neuroplasticity, Image Processing, Computer-Assisted, Animals, ComputingMilieux_MISCELLANEOUS, 030304 developmental biology, Neurons, 0303 health sciences, Neuronal Plasticity, 3D segmentation, General Neuroscience, Glutamate receptor, Axons, Corpus Striatum, Spine (zoology), Neostriatum, nervous system, Synaptic plasticity, Synapses, [SDV.NEU]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC], Anatomy, Neuroscience, 030217 neurology & neurosurgery
Abstract: International audience; Addiction can be considered as a form of neuronal adaptation within the reward circuitry. Upon psychostimulant administration, long-term behavioral adaptations are associated with synaptic plasticity and morphological changes of medium spiny neurons (MSN) from the striatum. Increased spine density onto MSN in response to chronic cocaine exposure in mice has been described for more than a decade, but no evidence indicates that these newly formed spines establish connections. We developed a method for labeling, automated detection and morphological analysis of synaptic contacts. Individual labeling of neurons in mice that express the Vesicular GLUtamate Transporter-1 fused to Venus allows visualization of both dendritic spines and axonal boutons. Automated three-dimensional segmentation and morphometric analysis retrieve information on thousands of synapses at high resolution. We used this method to demonstrate that new cortico-striatal connections are formed in the striatum upon chronic cocaine. We also show that the cortical input weight is preserved over other cerebral inputs and that the newly formed spines contact pre-existing axonal boutons. Our results pave the way for other studies, since our method can be applied to any other neuronal type as demonstrated herein for glutamatergic connections on pyramidal neurons and Purkinje cells.
Published: 2015
Full Text: View/download PDF

35. POI Recommendation: Towards Fused Matrix Factorization with Geographical and Temporal Influences

Author: Jean-Benoît Griesner, Hubert Naacke, Talel Abdessalem, 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), 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), 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: Information retrieval, accuracy measures, Computer science, Kernel density estimation, Information Search and Retrieval, 02 engineering and technology, Extension (predicate logic), POI recommendation, Recommender system, computer.software_genre, Matrix decomposition, Application domain, 020204 information systems, [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, [INFO]Computer Science [cs], Data mining, computer
Abstract: International audience; Providing personalized point-of-interest (POI) recommendation has become a major issue with the rapid emergence of location-based social networks (LBSNs). Unlike traditional recommendation approaches, the LBSNs application domain comes with significant geographical and temporal dimensions. Moreover most of traditional recommendation algorithms fail to cope with the specific challenges implied by these two dimensions. Fusing geographical and temporal influences for better recommendation accuracy in LBSNs remains unexplored, as far as we know. We depict how matrix factorization can serve POI recommendation, and propose a novel attempt to integrate both geographical and temporal influences into matrix factorization. Specifically we present GeoMF-TD, an extension of geographical matrix factorization with temporal dependencies. Our experiments on a real dataset shows up to 20% benefit on recommendation precision.
Published: 2015
Full Text: View/download PDF

36. Measuring the Impact of ICTs on the Quality of Life of Ageing People with Mild Dementia

Author: Mounir Mokhtari, Thibaut Tiberghien, Hamdi Aloulou, Romain Endelin, Institut Mines-Télécom [Paris] (IMT), Interactive Digital Humans (IDH), Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier (LIRMM), Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM), 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), Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS), 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: Population ageing, Activities of daily living, Ageing people, business.industry, ADL, Internet privacy, Ambient Assisted Living, Cognition, Gateway (computer program), Activities of Daily Living (ADL), 3. Good health, Outsourcing, [INFO.INFO-IU]Computer Science [cs]/Ubiquitous Computing, Quality of life, Software deployment, Activities of Daily Living, Business, Dependant, Ambient Assisted Living (AAL), Simulation
Abstract: International audience; The growing of ageing population worldwide and the need to focus research efforts on a specific target group motivate our research to focus on frail ageing people with chronic disease and physical/cognitive deficiencies. The primary goal is to enable the frail and dependant persons, through reliable assistive technologies, to maximize their physical and mental functions, and to continue to engage them in social networks, so that he can continue to lead an independent and purposeful life. Our target is to analyze the users’ habits at home through an extensive survey performed in France recently, and to design a suitable assistive system, which is mainly composed of devices available in the market. This research activity led to the deployment of a simplified hardware infrastructure (gateway, sensors, actuators) in the home of end-users with a limited number of wireless sensors, and to the outsourcing of all the software for data analysis in a framework running on a distant server. The research focuses on the quality of life of ageing people having cognitive and functional limitations, and on recent achievements realised in France and Singapore through several European and national projects, and through Quality of Life Chair (QoL) directed by Mounir Mokhtari and supported by two major health insurance companies in France, namely la Mutuelle Generale and REUNICA.
Published: 2014
Full Text: View/download PDF

37. méthodologie de modélisation de la croissance de neurosphères sous microscope à contraste de phase

Author: Rigaud, Stephane Ulysse, 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], Université Pierre et Marie Curie - Paris VI, Daniel Racoceanu, and 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]
Subjects: Recalage 3d-2d, Cellule souche neuronale, Neural stem cell, Detection de cellule, [INFO.INFO-OH]Computer Science [cs]/Other [cs.OH], Maillage, Microscope à contraste de phase, Meshing, Algorithm evolutionaire
Abstract: The study of stem cells is one of the most important fields of research in the biomedical field. Computer vision and image processing have been greatly emphasized in this area for the development of automated solutions for culture and observation of cells. This work proposes a new methodology for observing and modelling the proliferation of neural stem cell under a phase contrast microscope. At each time lapse observation performed by the microscope during the proliferation, the system determines a three-dimensional model of the structure formed by the observed cells. This is achieved by a framework combining analysis, synthesis and selection process. First, an analysis of the images from the microscope segments the neurosphere and the constituent cells. With this analysis, combined with prior knowledge about the cells and their culture protocol, several 3-D possible models are generated through a synthesis process. These models are finally selected and evaluated according to their likelihood with the microscope image using a 3-D to 2-D registration method. Through this approach, we present an automatic visualisation tool and observation of the proliferation of neural stem cell under a phase contrast microscope.; L'étude des cellules souches est l'un des champs de recherches les plus importants dans le domaine biomédical. La vision par ordinateur et le traitement d'images ont été fortement mis en avant dans ce domaine pour le développement de solutions automatiques de culture et d'observation de cellules. Ce travail de thèse propose une nouvelle méthodologie pour l'observation et la modélisation de la prolifération de cellule souche neuronale sous microscope à contraste de phase. À chaque observation réalisée par le microscope durant la prolifération, notre système extrait un modèle en trois dimensions de la structure de cellules observées. Cela est réalisé par une suite de processus d'analyse, synthèse et sélection. Premièrement, une analyse de la séquence d'images de contraste de phase permet la segmentation de la neurosphère et des cellules la constituant. À partir de ces informations, combinées avec des connaissances a priori sur les cellules et le protocole de culture, plusieurs modèles 3-D possibles sont générés. Ces modèles sont finalement évalués et sélectionnés par rapport à l¿image d¿observation, grâce à une méthode de recalage 3-D vers 2-D. A travers cette approche, nous présentons un outil automatique de visualisation et d'observation de la prolifération de cellule souche neuronale sous microscope à contraste de phase.
Published: 2014

38. Support Exploration Algorithm for Sparse Support Recovery

Author: Mohamed, Mimoun, Malgouyres, François, Emiya, Valentin, Chaux, Caroline, Institut de Mathématiques de Marseille (I2M), Aix Marseille Université (AMU)-École Centrale de Marseille (ECM)-Centre National de la Recherche Scientifique (CNRS), éQuipe d'AppRentissage de MArseille (QARMA), Laboratoire d'Informatique et Systèmes (LIS), Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS)-Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS), Institut de Mathématiques de Toulouse UMR5219 (IMT), Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-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), 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], Région Sud - Provence-Alpes-Côte d’Azur et Euranova France, and ANR-19-P3IA-0004,ANITI,Artificial and Natural Intelligence Toulouse Institute(2019)
Subjects: FOS: Computer and information sciences, Computer Science - Machine Learning, model selection, sparsity, Mathematics - Statistics Theory, Statistics Theory (math.ST), restricted isometry property, Machine Learning (cs.LG), greedy algorithm, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Optimization and Control (math.OC), [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST], FOS: Mathematics, [MATH.MATH-OC]Mathematics [math]/Optimization and Control [math.OC], straight-through estimator, Mathematics - Optimization and Control, support recovery
Abstract: We introduce a new algorithm promoting sparsity called {\it Support Exploration Algorithm (SEA)} and analyze it in the context of support recovery/model selection problems.The algorithm can be interpreted as an instance of the {\it straight-through estimator (STE)} applied to the resolution of a sparse linear inverse problem. SEA uses a non-sparse exploratory vector and makes it evolve in the input space to select the sparse support. We put to evidence an oracle update rule for the exploratory vector and consider the STE update. The theoretical analysis establishes general sufficient conditions of support recovery. The general conditions are specialized to the case where the matrix $A$ performing the linear measurements satisfies the {\it Restricted Isometry Property (RIP)}.Experiments show that SEA can efficiently improve the results of any algorithm. Because of its exploratory nature, SEA also performs remarkably well when the columns of $A$ are strongly coherent.
Published: 2023

39. Confidential Truth Finding with Multi-Party Computation (Extended Version)

Author: Saadeh, Angelo, Senellart, Pierre, Bressan, Stéphane, CNRS@CREATE Ltd., Laboratoire Traitement et Communication de l'Information (LTCI), Institut Mines-Télécom [Paris] (IMT)-Télécom Paris, Value from Data (VALDA ), Département d'informatique - ENS Paris (DI-ENS), École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-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)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria de Paris, Institut National de Recherche en Informatique et en Automatique (Inria), Institut Universitaire de France (IUF), Ministère de l'Education nationale, de l’Enseignement supérieur et de la Recherche (M.E.N.E.S.R.), 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], School of computing [Singapore] (NUS), National University of Singapore (NUS), and This research is part of the program DesCartes and issupported by the National Research Foundation, Prime Minister’s Office, Sin-gapore under its Campus for Research Excellence and Technological Enterprise(CREATE) program.
Subjects: Secret-sharing, FOS: Computer and information sciences, [INFO.INFO-CR]Computer Science [cs]/Cryptography and Security [cs.CR], Computer Science - Cryptography and Security, Computer Science - Databases, Uncertain data, Privacy, Truth finding, Databases (cs.DB), Secure multi-party computation, Cryptography and Security (cs.CR)
Abstract: Federated knowledge discovery and data mining are challenged to assess the trustworthiness of data originating from autonomous sources while protecting confidentiality and privacy. Truth-finding algorithms help corroborate data from disagreeing sources. For each query it receives, a truth-finding algorithm predicts a truth value of the answer, possibly updating the trustworthiness factor of each source. Few works, however, address the issues of confidentiality and privacy. We devise and present a secure secret-sharing-based multi-party computation protocol for pseudo-equality tests that are used in truth-finding algorithms to compute additions depending on a condition. The protocol guarantees confidentiality of the data and privacy of the sources. We also present variants of truth-finding algorithms that would make the computation faster when executed using secure multi-party computation. We empirically evaluate the performance of the proposed protocol on two state-of-the-art truth-finding algorithms, Cosine, and 3-Estimates, and compare them with that of the baseline plain algorithms. The results confirm that the secret-sharing-based secure multi-party algorithms are as accurate as the corresponding baselines but for proposed numerical approximations that significantly reduce the efficiency loss incurred., Comment: 15-page extended version of a paper published at DEXA 2023
Published: 2023
Full Text: View/download PDF

40. Inhibitory neurons control the consolidation of neural assemblies via adaptation to selective stimuli

Author: Raphaël Bergoin, Alessandro Torcini, Gustavo Deco, Mathias Quoy, Gorka Zamora-López, 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), Laboratoire de Physique Théorique et Modélisation (LPTM - UMR 8089), Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), Universitat Pompeu Fabra [Barcelona] (UPF), 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], CNRS, Labex MME-DII, Spanish national research project, Organization for Computational Neurosciences, 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), European Project, Bergoin, Raphaël, APPEL À PROJETS GÉNÉRIQUE 2018 - Réduction exacte de la dynamique neuronale multi-échelle - - ERMUNDY2018 - ANR-18-CE37-0014 - AAPG2018 - VALID, Human Brain Project Specific Grant Agreement 3 - HBP SGA3 - - H20202020-01-01 - 2023-09-30 - 945539 - VALID, and EUTOPIA-PhD-2020-0000000066 - NEUROAI - INCOMING
Subjects: Multidisciplinary, Mathematics and computing, [SCCO.NEUR]Cognitive science/Neuroscience, [SCCO.NEUR] Cognitive science/Neuroscience, Computational science, Complex networks, Statistical physics, thermodynamics and nonlinear dynamics, Computer science, Neuroscience
Abstract: Brain circuits display modular architecture at different scales of organization. Such neural assemblies are typically associated to functional specialization but the mechanisms leading to their emergence and consolidation still remain elusive. In this paper we investigate the role of inhibition in structuring new neural assemblies driven by the entrainment to various inputs. In particular, we focus on the role of partially synchronized dynamics for the creation and maintenance of structural modules in neural circuits by considering a network of excitatory and inhibitory θ -neurons with plastic Hebbian synapses. The learning process consists of an entrainment to temporally alternating stimuli that are applied to separate regions of the network. This entrainment leads to the emergence of modular structures. Contrary to common practice in artificial neural networks—where the acquired weights are typically frozen after the learning session—we allow for synaptic adaptation even after the learning phase. We find that the presence of inhibitory neurons in the network is crucial for the emergence and the post-learning consolidation of the modular structures. Indeed networks made of purely excitatory neurons or of neurons not respecting Dale’s principle are unable to form or to maintain the modular architecture induced by the stimuli. We also demonstrate that the number of inhibitory neurons in the network is directly related to the maximal number of neural assemblies that can be consolidated, supporting the idea that inhibition has a direct impact on the memory capacity of the neural network. This work was supported (R.B., G.D. and G.Z.L.) by the European Union’s Horizon 2020 Framework Programme for Research and Innovation under the Specific [Grant Agreement No. 945539 (Human Brain Project SGA3)] and by an EUTOPIA funding [EUTOPIA-PhD-2020-0000000066 - NEUROAI]. A.T. received financial support by the Labex MME-DII [Grant No. ANR-11-LBX-0023-01] (together with M.Q.), and by the ANR Project ERMUNDY [Grant No. ANR-18-CE37-0014] all part of the French program “Investissements d’Avenir”. G.D. is supported by the Spanish national research project [ref. PID2019-105772GB-I00/AEI/10.13039/501100011033] funded by the Spanish Ministry of Science, Innovation, and Universities (MCIU). M.Q. is also partially supported by CNRS through the IPAL lab in Singapore.
Published: 2023

41. IGNiteR: News Recommendation in Microblogging Applications

Author: Yuting Feng, Bogdan Cautis, Université Paris-Saclay, 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), 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], CNRS CREATE, National University of Singapore (NUS), Données et Connaissances Massives et Hétérogènes (LaHDAK), Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-Science des Données (SDD), Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS), and IEEE
Subjects: diffusion, deep learning, [INFO]Computer Science [cs], News recommendation deep learning diffusion, News recommendation
Abstract: International audience; As social media, and particularly microblogging applications like Twitter or Weibo, gains popularity as platforms for news dissemination, personalized news recommendation in this context becomes a significant challenge. We propose a diffusion and influence-aware approach, Influence-Graph News Recommender (IGNiteR), which is a content-based deep recommendation model that jointly exploits all the data facets that may impact adoption decisions, namely semantics, diffusion-related features pertaining to local and global influence among users, temporal attractiveness, and timeliness, as well as dynamic user preferences. We perform extensive experiments on two real-world datasets, showing that IGNiteR outperforms the state-of-the-art deep-learning based news recommendation methods.
Published: 2022
Full Text: View/download PDF

42. Détection automatique de Mitoses dans des images Histopathologiques haut-contenu, couleur multispectrales : application à la gradation du cancer du sein en pathologie numérique

Author: Irshad, Humayun, 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), Université de Grenoble, Daniel Racoceanu, Ludovic Roux, 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: Détection de mitoses, Breast Cancer, Digital Pathology, Histopathology, Multispectral Imaging, Segmentation et classification de noyaux, Histopathologie, Mitosis Detection, Images multispectrales, Pathologie numérique, Cancer du sein, [SDV.MHEP]Life Sciences [q-bio]/Human health and pathology, Nuclei Segmentation and Classification
Abstract: Digital pathology represents one of the major and challenging evolutions in modernmedicine. Pathological exams constitute not only the gold standard in most of medicalprotocols, but also play a critical and legal role in the diagnosis process. Diagnosing adisease after manually analyzing numerous biopsy slides represents a labor-intensive workfor pathologists. Thanks to the recent advances in digital histopathology, the recognitionof histological tissue patterns in a high-content Whole Slide Image (WSI) has the potentialto provide valuable assistance to the pathologist in his daily practice. Histopathologicalclassification and grading of biopsy samples provide valuable prognostic information thatcould be used for diagnosis and treatment support. Nottingham grading system is thestandard for breast cancer grading. It combines three criteria, namely tubule formation(also referenced as glandular architecture), nuclear atypia and mitosis count. Manualdetection and counting of mitosis is tedious and subject to considerable inter- and intrareadervariations. The main goal of this dissertation is the development of a framework ableto provide detection of mitosis on different types of scanners and multispectral microscope.The main contributions of this work are eight fold. First, we present a comprehensivereview on state-of-the-art methodologies in nuclei detection, segmentation and classificationrestricted to two widely available types of image modalities: H&E (HematoxylinEosin) and IHC (Immunohistochemical). Second, we analyse the statistical and morphologicalinformation concerning mitotic cells on different color channels of various colormodels that improve the mitosis detection in color datasets (Aperio and Hamamatsu scanners).Third, we study oversampling methods to increase the number of instances of theminority class (mitosis) by interpolating between several minority class examples that lietogether, which make classification more robust. Fourth, we propose three different methodsfor spectral bands selection including relative spectral absorption of different tissuecomponents, spectral absorption of H&E stains and mRMR (minimum Redundancy MaximumRelevance) technique. Fifth, we compute multispectral spatial features containingpixel, texture and morphological information on selected spectral bands, which leveragediscriminant information for mitosis classification on multispectral dataset. Sixth, we performa comprehensive study on region and patch based features for mitosis classification.Seven, we perform an extensive investigation of classifiers and inference of the best one formitosis classification. Eight, we propose an efficient and generic strategy to explore largeimages like WSI by combining computational geometry tools with a local signal measureof relevance in a dynamic sampling framework.The evaluation of these frameworks is done in MICO (COgnitive MIcroscopy, ANRTecSan project) platform prototyping initiative. We thus tested our proposed frameworks on MITOS international contest dataset initiated by this project. For the color framework,we manage to rank second during the contest. Furthermore, our multispectral frameworkoutperforms significantly the top methods presented during the contest. Finally, ourframeworks allow us reaching the same level of accuracy in mitosis detection on brightlightas multispectral datasets, a promising result on the way to clinical evaluation and routine.; La gradation de lames de biopsie fournit des informations pronostiques essentielles pour le diagnostic et le traitement. La détection et le comptage manuel des mitoses est un travail fastidieux, sujet à des variations inter-et intra- observateur considérables. L'objectif principal de cette thèse de doctorat est le développement d'un système capable de fournir une détection des mitoses sur des images provenant de différents types de scanners rapides automatiques, ainsi que d'un microscope multispectral. L'évaluation des différents systèmes proposés est effectuée dans le cadre du projet MICO (MIcroscopie COgnitive, projet ANR TecSan piloté par notre équipe). Dans ce contexte, les systèmes proposés ont été testés sur les données du benchmark MITOS. En ce qui concerne les images couleur, notre système s'est ainsi classé en deuxième position de ce concours international, selon la valeur du critère F-mesure. Par ailleurs, notre système de détection de mitoses sur images multispectrales surpasse largement les meilleurs résultats obtenus durant le concours.
Published: 2014

43. An Adaptable and Flexible Framework for Assistive Living of Cognitively Impaired People

Author: Hamdi Aloulou, Jit Biswas, Mounir Mokhtari, Philip Yap, Thibaut Tiberghien, Institut Mines-Télécom [Paris] (IMT), Interactive Digital Humans (IDH), Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier (LIRMM), Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-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], Institute for Infocomm Research - I²R [Singapore], Khoo Teck Puat Hospital (KTPH), Alexandra Health, Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-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: Process management, Computer science, media_common.quotation_subject, 02 engineering and technology, computer.software_genre, Adaptability, [INFO.INFO-IU]Computer Science [cs]/Ubiquitous Computing, Computer Communication Networks, Health Information Management, 0202 electrical engineering, electronic engineering, information engineering, Humans, Electrical and Electronic Engineering, context aware services, Monitoring, Physiologic, media_common, cognitive impairment, 020203 distributed computing, Multimedia, Ambient assistive living (AAL), Cognition, dynamic and extendible frameworks, Self-Help Devices, Computer Science Applications, Work (electrical), Software deployment, 020201 artificial intelligence & image processing, Cognitively impaired, User interface, Cognition Disorders, Neurocognitive, computer, Medical Informatics, Autonomy, Biotechnology
Abstract: International audience; On account of chronic neurocognitive disorders, many people progressively lose their autonomy and become more dependent on others, finally reaching the stage when they need round-the-clock care from caregivers. Over time, as patients' needs increase with the evolution of their diseases, caregivers experience increasing levels of stress and burden. Therefore, an assistive solution that is able to adapt to the changing needs of the end-users is needed. This need was considered as a major requirement that emerged from our field work and deployment experience in Singapore. In this paper, we focus on the technical aspects of our deployment, where we were interested in solving the technical requirement of adaptability and extendibility of the framework that has emerged from our predeployment analysis and discussions with professional caregivers. We expose our approach for dynamic integration of assistive services with their related sensing technologies and interaction devices and provide the technical results of the deployment of this solution. We also provide guidelines for real-world deployment of assistive solutions.
Published: 2014
Full Text: View/download PDF

44. Top-Down Regularization of Deep Belief Networks

Author: Goh, Hanlin, Thome, Nicolas, Cord, Matthieu, Lim, Joo-Hwee, 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 Access (MLIA), 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), C.J.C. Burges, L. Bottou, M. Welling, Z. Ghahramani, K.Q. Weinberger, 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-LG]Computer Science [cs]/Machine Learning [cs.LG]
Abstract: International audience; Designing a principled and effective algorithm for learning deep architectures is a challenging problem. The current approach involves two training phases: a fully unsupervised learning followed by a strongly discriminative optimization. We suggest a deep learning strategy that bridges the gap between the two phases, resulting in a three-phase learning procedure. We propose to implement the scheme using a method to regularize deep belief networks with top-down information. The network is constructed from building blocks of restricted Boltzmann machines learned by combining bottom-up and top-down sampled signals. A global optimization procedure that merges samples from a forward bottom-up pass and a top-down pass is used. Experiments on the MNIST dataset show improvements over the existing algorithms for deep belief networks. Object recognition results on the Caltech-101 dataset also yield competitive results.
Published: 2013

45. Implementation of Allen’s interval logic with the semantic web

Author: Endelin, Romain, Aloulou, Hamdi, de Roo, Jos, Renouard, Stéphane, Tiberghien, Thibaut, Mokhtari, Mounir, Interactive Digital Humans (IDH), Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier (LIRMM), Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM), 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), AGFA HealthCare, UNIV DE GAND, HANDCO, Handco, Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM), Aloulou, Hamdi, Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-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], Universiteit Gent = Ghent University (UGENT), and Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)
Subjects: [INFO.INFO-IU]Computer Science [cs]/Ubiquitous Computing, [INFO.INFO-IU] Computer Science [cs]/Ubiquitous Computing
Abstract: International audience; In this paper, we describe the implementation of a qualitative temporal reasoning. We will discuss the challenges and benefits of using the Semantic Web and Allen's Interval Logic for such reasoning.
Published: 2013

46. Tree Species Classification Based on 3D Bark Texture Analysis

Author: Lew F.C. Lew Yan Voon, Alexandre Piboule, Nicolas Loménie, Oscar Dalmau, Said Mokrani, Ahlem Othmani, Laboratoire Electronique, Informatique et Image [UMR6303] ( Le2i ), 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 ), 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], Office National des Forêts - ONF (FRANCE), Centro de Investigación en Matemáticas ( CIMAT ), Consejo Nacional de Ciencia y Tecnología [Mexico] ( CONACYT ), Centre de Recherche en Informatique de Paris 5 ( CRIP5 - EA 2517 ), Université Paris Descartes - Paris 5 ( UPD5 ), 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 ), 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 Science for Interventional Techniques (ISIT), Université d'Auvergne - Clermont-Ferrand I (UdA)-Centre National de la Recherche Scientifique (CNRS)-Clermont Université, 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), Office National des Forêts (ONF), Centro de Investigación en Matemáticas (CIMAT), Consejo Nacional de Ciencia y Tecnología [Mexico] (CONACYT), Centre de Recherche en Informatique de Paris 5 (CRIP5 - EA 2517), Université Paris Descartes - Paris 5 (UPD5), Université de Bourgogne (UB)-École Nationale Supérieure d'Arts et Métiers (ENSAM), 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), Université d'Auvergne - Clermont-Ferrand I (UdA)-Clermont Université-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], Office national des forêts (ONF), and Clermont Université-Centre National de la Recherche Scientifique (CNRS)-Université d'Auvergne - Clermont-Ferrand I (UdA)
Subjects: [ INFO.INFO-TS ] Computer Science [cs]/Signal and Image Processing, Computer science, Point cloud, 02 engineering and technology, computer.software_genre, [ INFO.INFO-CV ] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Texture (geology), 3D pattern recognition, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [ INFO.INFO-TI ] Computer Science [cs]/Image Processing, 0202 electrical engineering, electronic engineering, information engineering, forest inventory, [STAT.AP]Statistics [stat]/Applications [stat.AP], Forest inventory, Trees pecies classification, [ STAT.AP ] Statistics [stat]/Applications [stat.AP], [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 3D bark texture analysis, 020206 networking & telecommunications, Terrestrial laser scanning, 15. Life on land, Random forest, visual_art, Test set, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], visual_art.visual_art_medium, 020201 artificial intelligence & image processing, Bark, Data mining, computer, Tree species
Abstract: Terrestrial Laser Scanning (TLS) technique is today widely used in ground plots to acquire 3D point clouds from which forest inventory attributes are calculated. In the case of mixed plantings where the 3D point clouds contain data from several different tree species, it is important to be able to automatically recognize the tree species in order to analyze the data of each of the species separately. Although automatic tree species recognition from TLS data is an important problem, it has received very little attention from the scientific community. In this paper we propose a method for classifying five different tree species using TLS data. Our method is based on the analysis of the 3D geometric texture of the bark in order to compute roughness measures and shape characteristics that are fed as input to a Random Forest classifier to classify the tree species. The method has been evaluated on a test set composed of 265 samples (53 samples of each of the 5 species) and the results obtained are very encouraging.
Published: 2013
Full Text: View/download PDF

47. Unsupervised dense crowd detection by multiscale texture analysis

Author: Jean-Yves Dufour, Daniel Racoceanu, Nicolas Courty, Antoine Fagette, Thalès Solution Asia, THALES, Environment observation with complex imagery (OBELIX), Université de Bretagne Sud (UBS)-SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), CentraleSupélec-Télécom Bretagne-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Université de Bretagne Sud (UBS)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-CentraleSupélec-Télécom Bretagne-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA), 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], Thales Services, THALES [France], Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), and 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: Multiscale, Computer science, Feature vector, Feature extraction, Diffusion map, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Crowds, Segmentation, Artificial Intelligence, Quadtree, Computer vision, Cluster analysis, business.industry, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Pattern recognition, Real image, Diffusion maps, Binary classification, Dense crowd, Computer Science::Computer Vision and Pattern Recognition, Signal Processing, Computer Vision and Pattern Recognition, Artificial intelligence, business, Software
Abstract: We propose a fully unsupervised method for the detection of dense crowds in images.We build multiscale texture-based feature vectors over the image.We use the diffusion maps algorithm to perform the clustering of our data.We propose the use of a quadtree for the coarse-graining of the diffusion map.We prove the efficiency of our method on synthetic and real images. This study introduces a totally unsupervised method for the detection and location of dense crowds in images without context-awareness. With the perspective of setting up fully autonomous video-surveillance systems, automatic detection and location of crowds is a crucial step that is going to point which areas of the image have to be analyzed. After retrieving multiscale texture-related feature vectors from the image, a binary classification is conducted to determine which parts of the image belong to the crowd and which to the background. The algorithm presented can be operated on images without any prior knowledge of any kind and is totally unsupervised.
Published: 2013

48. Apprentissage de Représentations Visuelles Profondes

Author: Goh, Hanlin, 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 Access (MLIA), 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), Université Pierre et Marie Curie - Paris VI, Matthieu Cord(matthieu.cord@lip6.fr), 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: apprentissage profond, représentations visuelles hierarchiques, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], deep learning, hierarchical visual representations, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], classification d'images, image classification
Abstract: Recent advancements in the areas of deep learning and visual information processing have presented an opportunity to unite both fields. These complementary fields combine to tackle the problem of classifying images into their semantic categories. Deep learning brings learning and representational capabilities to a visual processing model that is adapted for image classification. This thesis addresses problems that lead to the proposal of learning deep visual representations for image classification. The problem of deep learning is tackled on two fronts. The first aspect is the problem of unsupervised learning of latent representations from input data. The main focus is the integration of prior knowledge into the learning of restricted Boltzmann machines (RBM) through regularization. Regularizers are proposed to induce sparsity, selectivity and topographic organization in the coding to improve discrimination and invariance. The second direction introduces the notion of gradually transiting from unsupervised layer-wise learning to supervised deep learning. This is done through the integration of bottom-up information with top-down signals. Two novel implementations supporting this notion are explored. The first method uses top-down regularization to train a deep network of RBMs. The second method combines predictive and reconstructive loss functions to optimize a stack of encoder-decoder networks. The proposed deep learning techniques are applied to tackle the image classification problem. The bag-of-words model is adopted due to its strengths in image modeling through the use of local image descriptors and spatial pooling schemes. Deep learning with spatial aggregation is used to learn a hierarchical visual dictionary for encoding the image descriptors into mid-level representations. This method achieves leading image classification performances for object and scene images. The learned dictionaries are diverse and non-redundant. The speed of inference is also high. From this, a further optimization is performed for the subsequent pooling step. This is done by introducing a differentiable pooling parameterization and applying the error backpropagation algorithm. This thesis represents one of the first attempts to synthesize deep learning and the bag-of-words model. This union results in many challenging research problems, leaving much room for further study in this area.; Les avancées récentes en apprentissage profond et en traitement d'image présentent l'opportunité d'unifier ces deux champs de recherche complémentaires pour une meilleure résolution du problème de classification d'images dans des catégories sémantiques. L'apprentissage profond apporte au traitement d'image le pouvoir de représentation nécessaire à l'amélioration des performances des méthodes de classification d'images. Cette thèse propose de nouvelles méthodes d'apprentissage de représentations visuelles profondes pour la résolution de cette tache. L'apprentissage profond a été abordé sous deux angles. D'abord nous nous sommes intéressés à l'apprentissage non supervisé de représentations latentes ayant certaines propriétés à partir de données en entrée. Il s'agit ici d'intégrer une connaissance à priori, à travers un terme de régularisation, dans l'apprentissage d'une machine de Boltzmann restreinte. Nous proposons plusieurs formes de régularisation qui induisent différentes propriétés telles que la parcimonie, la sélectivité et l'organisation en structure topographique. Le second aspect consiste au passage graduel de l'apprentissage non supervisé à l'apprentissage supervisé de réseaux profonds. Ce but est réalisé par l'introduction sous forme de supervision, d'une information relative à la catégorie sémantique. Deux nouvelles méthodes sont proposées. Le premier est basé sur une régularisation top-down de réseaux de croyance profonds à base de machines des Boltzmann restreintes. Le second optimise un cout intégrant un critère de reconstruction et un critère de supervision pour l'entrainement d'autoencodeurs profonds. Les méthodes proposées ont été appliquées au problème de classification d'images. Nous avons adopté le modèle sac-de-mots comme modèle de base parce qu'il offre d'importantes possibilités grâce à l'utilisation de descripteurs locaux robustes et de pooling par pyramides spatiales qui prennent en compte l'information spatiale de l'image. L'apprentissage profonds avec agrégation spatiale est utilisé pour apprendre un dictionnaire hiérarchique pour l'encodage de représentations visuelles de niveau intermédiaire. Cette méthode donne des résultats très compétitifs en classification de scènes et d'images. Les dictionnaires visuels appris contiennent diverses informations non-redondantes ayant une structure spatiale cohérente. L'inférence est aussi très rapide. Nous avons par la suite optimisé l'étape de pooling sur la base du codage produit par le dictionnaire hiérarchique précédemment appris en introduisant introduit une nouvelle paramétrisation dérivable de l'opération de pooling qui permet un apprentissage par descente de gradient utilisant l'algorithme de rétro-propagation. Ceci est la première tentative d'unification de l'apprentissage profond et du modèle de sac de mots. Bien que cette fusion puisse sembler évidente, l'union de plusieurs aspects de l'apprentissage profond de représentations visuelles demeure une tache complexe à bien des égards et requiert encore un effort de recherche important.
Published: 2013

49. Learning Deep Visual Representations

Author: Goh, Hanlin, 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 Access (MLIA), 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), Université Pierre et Marie Curie - Paris VI, and Matthieu Cord(matthieu.cord@lip6.fr)
Subjects: apprentissage profond, représentations visuelles hierarchiques, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], deep learning, hierarchical visual representations, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], classification d'images, image classification
Abstract: Recent advancements in the areas of deep learning and visual information processing have presented an opportunity to unite both fields. These complementary fields combine to tackle the problem of classifying images into their semantic categories. Deep learning brings learning and representational capabilities to a visual processing model that is adapted for image classification. This thesis addresses problems that lead to the proposal of learning deep visual representations for image classification. The problem of deep learning is tackled on two fronts. The first aspect is the problem of unsupervised learning of latent representations from input data. The main focus is the integration of prior knowledge into the learning of restricted Boltzmann machines (RBM) through regularization. Regularizers are proposed to induce sparsity, selectivity and topographic organization in the coding to improve discrimination and invariance. The second direction introduces the notion of gradually transiting from unsupervised layer-wise learning to supervised deep learning. This is done through the integration of bottom-up information with top-down signals. Two novel implementations supporting this notion are explored. The first method uses top-down regularization to train a deep network of RBMs. The second method combines predictive and reconstructive loss functions to optimize a stack of encoder-decoder networks. The proposed deep learning techniques are applied to tackle the image classification problem. The bag-of-words model is adopted due to its strengths in image modeling through the use of local image descriptors and spatial pooling schemes. Deep learning with spatial aggregation is used to learn a hierarchical visual dictionary for encoding the image descriptors into mid-level representations. This method achieves leading image classification performances for object and scene images. The learned dictionaries are diverse and non-redundant. The speed of inference is also high. From this, a further optimization is performed for the subsequent pooling step. This is done by introducing a differentiable pooling parameterization and applying the error backpropagation algorithm. This thesis represents one of the first attempts to synthesize deep learning and the bag-of-words model. This union results in many challenging research problems, leaving much room for further study in this area.; Les avancées récentes en apprentissage profond et en traitement d'image présentent l'opportunité d'unifier ces deux champs de recherche complémentaires pour une meilleure résolution du problème de classification d'images dans des catégories sémantiques. L'apprentissage profond apporte au traitement d'image le pouvoir de représentation nécessaire à l'amélioration des performances des méthodes de classification d'images. Cette thèse propose de nouvelles méthodes d'apprentissage de représentations visuelles profondes pour la résolution de cette tache. L'apprentissage profond a été abordé sous deux angles. D'abord nous nous sommes intéressés à l'apprentissage non supervisé de représentations latentes ayant certaines propriétés à partir de données en entrée. Il s'agit ici d'intégrer une connaissance à priori, à travers un terme de régularisation, dans l'apprentissage d'une machine de Boltzmann restreinte. Nous proposons plusieurs formes de régularisation qui induisent différentes propriétés telles que la parcimonie, la sélectivité et l'organisation en structure topographique. Le second aspect consiste au passage graduel de l'apprentissage non supervisé à l'apprentissage supervisé de réseaux profonds. Ce but est réalisé par l'introduction sous forme de supervision, d'une information relative à la catégorie sémantique. Deux nouvelles méthodes sont proposées. Le premier est basé sur une régularisation top-down de réseaux de croyance profonds à base de machines des Boltzmann restreintes. Le second optimise un cout intégrant un critère de reconstruction et un critère de supervision pour l'entrainement d'autoencodeurs profonds. Les méthodes proposées ont été appliquées au problème de classification d'images. Nous avons adopté le modèle sac-de-mots comme modèle de base parce qu'il offre d'importantes possibilités grâce à l'utilisation de descripteurs locaux robustes et de pooling par pyramides spatiales qui prennent en compte l'information spatiale de l'image. L'apprentissage profonds avec agrégation spatiale est utilisé pour apprendre un dictionnaire hiérarchique pour l'encodage de représentations visuelles de niveau intermédiaire. Cette méthode donne des résultats très compétitifs en classification de scènes et d'images. Les dictionnaires visuels appris contiennent diverses informations non-redondantes ayant une structure spatiale cohérente. L'inférence est aussi très rapide. Nous avons par la suite optimisé l'étape de pooling sur la base du codage produit par le dictionnaire hiérarchique précédemment appris en introduisant introduit une nouvelle paramétrisation dérivable de l'opération de pooling qui permet un apprentissage par descente de gradient utilisant l'algorithme de rétro-propagation. Ceci est la première tentative d'unification de l'apprentissage profond et du modèle de sac de mots. Bien que cette fusion puisse sembler évidente, l'union de plusieurs aspects de l'apprentissage profond de représentations visuelles demeure une tache complexe à bien des égards et requiert encore un effort de recherche important.
Published: 2013

50. Behavior Recognition for Elderly People in Large-Scale Deployment

Author: Endelin, Romain, Renouard, Stéphane, Tiberghien, Thibaut, Aloulou, Hamdi, Mokhtari, Mounir, Interactive Digital Humans (IDH), Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier (LIRMM), Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM), Département Réseaux et Services de Télécommunications (RST), Institut Mines-Télécom [Paris] (IMT)-Télécom SudParis (TSP), Services répartis, Architectures, MOdélisation, Validation, Administration des Réseaux (SAMOVAR), 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), Télécom ParisTech, Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM), Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS), Département Réseaux et Services de Télécommunications (TSP - RST), 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], Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS), and Aloulou, Hamdi
Subjects: [INFO.INFO-IU]Computer Science [cs]/Ubiquitous Computing, Human Abnormal Activity Detection, Sensor Deployment, Actimetry, [INFO.INFO-IU] Computer Science [cs]/Ubiquitous Computing, Ambient Assisted Living, Context Awareness
Abstract: International audience; Behavior recognition through ambient assisted living solutions for elderly people, represents an ambitious challenge for actimetry. Numerous and versatile solutions have been deployed. However, a commercial adoption is still pending, due to scalability and acceptability constraints. Most researches in ambient assisted living appear to have an heavy design, where precise features are first selected, and hardware architecture is designed accordingly. Although it may provide interesting results, such approach leads to a lack of scalability. This is why we experimented a lighter approach for a real deployment. The complexity is shifted from hardware to software, and we aim to make meaningful informations emerge from simple and generic sensor data, in order to recognize abnormal and dangerous situations. In this paper, we will describe how to retrieve consistent informations, so that resident's behavior may be observed, and that a light and generic approach fits in large scale deployments, with acceptable cost and scalability.
Published: 2013

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

293 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