Éditeur(s) : HAL CCSD
Résumé : Document soutenu à l'atelier Fouille de Données Complexes de la conférence EGC2017
International audience
"L'informatique affective est l'informatique qui se réfère à, résulte de, ou influence délibérément les émotions" (Picard (1997)). Singulièrement, l'équi-libre psychosocial est désormais considéré comme une préoccupation majeure pour la santé, tant sur le plan individuel que public. Prédire les émotions hu-maines via des méthodes non-invasives est un challenge propulsé notamment par le développement des systèmes d'accompagnement intelligents. Afin de dé-terminer l'état émotionel d'un individu, ayant potentiellement un trouble psy-chosocial, il convient de traiter tant les émotions expressives que neutres. Une approche originale de classification de l'information émotionelle à partir de vi-déos est proposée.
Extraction et Gestion des Connaissances
Grenoble, France

Droits : http://creativecommons.org/licenses/by-nc-sa/
hal-01513329
https://hal.archives-ouvertes.fr/hal-01513329
https://hal.archives-ouvertes.fr/hal-01513329/document
https://hal.archives-ouvertes.fr/hal-01513329/file/egcArticle%20scholet.pdf

Éditeur(s) : HAL CCSD
Résumé : International audience
Extract the features for a multi-touch gesture is difficult due to the complex temporal and motion relations between multiple trajectories. In this paper we present a new generic graph model to quantify the shape, temporal and motion information from multi-touch gesture. To make a comparison between graph, we also propose a specific graph matching method based on graph edit distance. Results prove that our graph model can be fruitfully used for multi-touch gesture pattern recognition purpose with the classifier of graph embedding and SVM.
17th Biennial Conference of the International Graphonomics Society
Pointe-à-Pitre, Guadeloupe

hal-01165768
https://hal.univ-antilles.fr/hal-01165768
https://hal.univ-antilles.fr/hal-01165768/document
https://hal.univ-antilles.fr/hal-01165768/file/IGS_2015_submission_6.pdf

Éditeur(s) : HAL CCSD
Résumé : Best paper for innovative research
International audience
This paper investigates the interest of using the Kinematic Theory of rapid human movements to analyseand evaluate the handwriting produced by young kindergarten children in typical classroom environment. A total of66 children participated in this trial. For the preliminary results reported herein, movements from 15 children, takenevenly from three different levels (3, 4, and 5 years old), were analyzed. Our results confirm that 1) the sigmalognormalequation can model accurately childen’s movement and 2) that this modeling can differentiate betweenchildren of different school levels, hence supporting the relevance of pursuing along this original pathway.
Recent Progress in Graphonomics: Learn from the Past. IGS 2013
Nara, Japan

hal-01098125
https://hal.archives-ouvertes.fr/hal-01098125

Éditeur(s) : HAL CCSD
Résumé : International audience
It is an admitted fact that mainstream boosting algorithms like AdaBoost do not perform well to estimate class conditional probabilities. In this paper, we analyze, in the light of this problem, a recent algorithm, unn, which leverages nearest neighbors while minimizing a convex loss. Our contribution is threefold. First, we show that there exists a subclass of surrogate losses, elsewhere called balanced, whose minimization brings simple and statistically efficient estimators for Bayes posteriors. Second, we show explicit convergence rates towards these estimators for unn, for any such surrogate loss, under a Weak Learning Assumption which parallels that of classical boosting results. Third and last, we provide experiments and comparisons on synthetic and real datasets, including the challenging SUN computer vision database. Results clearly display that boosting nearest neighbors may provide highly accurate estimators, sometimes more than a hundred times more accurate than those of other contenders like support vector machines.
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)
Bristol, United Kingdom

hal-00702771
https://hal.archives-ouvertes.fr/hal-00702771
https://hal.archives-ouvertes.fr/hal-00702771/document
https://hal.archives-ouvertes.fr/hal-00702771/file/ecml12-dnbnb-sub.pdf

Éditeur(s) : HAL CCSD
Résumé : International audience
Antiviral proteins that recognize pathogen-specific or aberrantly located molecular motifs are perfectly positioned to act as pattern-recognition receptors and signal to the immune system. Here we investigated whether the interferon-induced viral restriction factor tetherin (CD317/BST2), which is known to inhibit HIV-1 particle release by physically tethering virions to the cell surface, has such a signaling role. We find that upon restriction of Vpu-defective HIV-1, tetherin acts as a virus sensor to induce NFκB-dependent proinflammatory gene expression. Signaling requires both tetherin's extracellular domain involved in virion retention and determinants in the cytoplasmic tail, including an endocytic motif, although signaling is independent of virion endocytosis. Furthermore, recruitment of the TNF-receptor-associated factor TRAF6 and activation of the mitogen-activated protein kinase TAK1 are critical for signaling. Human tetherin's ability to mediate efficient signaling may have arisen as a result of a five amino acid deletion that occurred in hominids after their divergence from chimpanzees.
ISSN: 1934-6069

hal-01121777
https://hal-univ-rennes1.archives-ouvertes.fr/hal-01121777
PUBMED : 23159053
DOI : 10.1016/j.chom.2012.10.007
PUBMEDCENTRAL : PMC3556742

Éditeur(s) : HAL CCSD Springer Verlag
Résumé : under revision for IJCV
International audience
The k-nearest neighbors (k-NN) classification rule has proven extremely successful in countless many computer vision applications. For example, image categorization often relies on uniform voting among the nearest prototypes in the space of descriptors. In spite of its good properties, the classic k-NN rule suffers from high variance when dealing with sparse prototype datasets in high dimensions. A few techniques have been proposed to improve k-NN classification, which rely on either deforming the nearest neighborhood relationship or modifying the input space. In this paper, we propose a novel boosting algorithm, called UNN (Universal Nearest Neighbors), which induces leveraged k-NN, thus generalizing the classic k-NN rule. We redefine the voting rule as a strong classifier that linearly combines predictions from the k closest prototypes. Weak classifiers are learned by UNN so as to minimize a surrogate risk. A major feature of UNN is the ability to learn which prototypes are the most relevant for a given class, thus allowing one for effective data reduction. Experimental results on the synthetic two-class dataset of Ripley show that such a filtering strategy is able to reject "noisy" prototypes. We carried out image categorization experiments on a database containing eight classes of natural scenes. We show that our method outperforms significantly the classic k-NN classification, while enabling significant reduction of the computational cost by means of data filtering.
ISSN: 0920-5691

hal-00481712
https://hal.archives-ouvertes.fr/hal-00481712
DOI : 10.1007/s11263-012-0539-2
ARXIV : 1001.1221

Éditeur(s) : HAL CCSD
Résumé : International audience
The goal of our experiment is to develop a useful and accessible tool that can be used to evaluate a patient's health by analyzing handwritten strokes. We use a cloud computing approach to analyze stroke data sampled on a commercial tablet working on the Android platform and a distant server to perform complex calculations using the Delta and Sigma lognormal algorithms. A Google Drive account is used to store the data and to ease the development of the project. The communication between the tablet, the cloud and the server is encrypted to ensure biomedical information confidentiality. Highly parameterized biomedical tests are implemented on the tablet as well as a free drawing test to evaluate the validity of the data acquired by the first test compared to the second one. A blurred shape model descriptor pattern recognition algorithm is used to classify the data obtained by the free drawing test. The functions presented in this paper are still currently under development and other improvements are needed before launching the application in the public domain.
17th Biennial Conference of the International Graphonomics Society
Pointe-à-Pitre, Guadeloupe

hal-01165890
https://hal.univ-antilles.fr/hal-01165890
https://hal.univ-antilles.fr/hal-01165890/document
https://hal.univ-antilles.fr/hal-01165890/file/IGS_2015_submission_20.pdf

Éditeur(s) : HAL CCSD
Résumé : International audience
Drawing and handwriting are communicational skills that are fundamental in geopolitical, ideological and technological evolutions of all time. drawingand handwriting are still useful in defining innovative applications in numerous fields. In this regard, researchers have to solve new problems like those related to the manner in which drawing and handwriting become an efficient way to command various connected objects; or to validate graphomotor skills as evident and objective sources of data useful in the study of human beings, their capabilities and their limits from birth to decline.
17th Biennial Conference of the International Graphonomics Society
Pointe-à-Pitre, Guadeloupe

Droits : http://creativecommons.org/licenses/by-nc-nd/
ISBN : 979-10-95177-01-2
hal-01166509
https://hal.univ-antilles.fr/hal-01166509
https://hal.univ-antilles.fr/hal-01166509/document
https://hal.univ-antilles.fr/hal-01166509/file/IGS2015proceedingsvHal-1.pdf

Éditeur(s) : HAL CCSD IEEE
Résumé : Object classification is a challenging task in computer vision. Many approaches have been proposed to extract meaningful descriptors from images and classifying them in a supervised learning framework. In this paper, we revisit the classic k-nearest neighbors (k-NN) classification rule, which has shown to be very effective when dealing with local image descriptors. However, k-NN still features some major drawbacks, mainly due to the uniform voting among the nearest prototypes in the feature space. In this paper, we propose a generalization of the classic k-NN rule in a supervised learning (boosting) framework. Namely, we redefine the voting rule as a strong classifier that linearly combines predictions from the k closest prototypes. To induce this classifier, we propose a novel learning algorithm, MLNN (Multiclass Leveraged Nearest Neighbors), which gives a simple procedure for performing prototype selection very efficiently. We tested our method on 12 categories of objects, and observed significant improvement over classic k-NN in terms of classification performances.
International Workshop on Image Analysis for Multimedia Interactive Services
Desenzano del Garda, Italy

hal-00481725
https://hal.archives-ouvertes.fr/hal-00481725
https://hal.archives-ouvertes.fr/hal-00481725/document
https://hal.archives-ouvertes.fr/hal-00481725/file/pbnn_wiamis_10.pdf

Éditeur(s) : HAL CCSD
Résumé : International audience
Half away between edge detection and pattern recognition this study aim to characterize singularities in order to build closed edges and to classify object within an image.
IGARSS
Toulouse, France

hal-00602262
https://hal.archives-ouvertes.fr/hal-00602262

Éditeur(s) : HAL CCSD
Résumé : International audience
Pattern Recognition, Applications and Methods

hal-01279723
https://hal.archives-ouvertes.fr/hal-01279723

Éditeur(s) : HAL CCSD
Résumé : International audience
Here, we synthesize conceptual frameworks, applied modeling approaches, and as case studies to highlight complex social-ecological system (SES) dynamics that inform environmental policy, conservation and management. Although a set of “good practices” about what constitutes a good SES study are emerging, there is still a disconnection between generating SES scientific studies and providing decision-relevant information to policy makers. Classical single variable/hypothesis studies rooted in one or two disciplines are still most common, leading to incremental growth in knowledge about the natural or social system, but rarely both. The recognition of human dimensions is a key aspect of successful planning and implementation in natural resource management, ecosystem-based management, fisheries management, and marine conservation. The lack of social data relating to human-nature interactions in this particular context is now seen as an omission, which can often erode the efficacy of any resource management or conservation action. There have been repeated calls for a transdisciplinary approach to complex SESs that incorporates resilience, complexity science characterized by intricate feedback interactions, emergent processes, non-linear dynamics and uncertainty. To achieve this vision, we need to embrace diverse research methodologies that incorporate ecology, sociology, anthropology, political science, economics and other disciplines that are anchored in empirical data. We conclude that to make SES research most useful in adding practical value to conservation planning, marine resource management planning processes and implementation, and the integration of resilience thinking into adaptation strategies, more research is needed on (1) understanding social-ecological landscapes and seascapes and patterns that would ensure planning process legitimacy, (2) costs of transformation (financial, social, environmental) to a stable resilient social-ecological system, (3) overcoming place-based data collection challenges as well as modeling challenges.
Ocean and Coastal Management

Droits : http://creativecommons.org/licenses/by-nc-nd/
hal-01224152
https://hal-univ-perp.archives-ouvertes.fr/hal-01224152
https://hal-univ-perp.archives-ouvertes.fr/hal-01224152/document
https://hal-univ-perp.archives-ouvertes.fr/hal-01224152/file/1-s2.0-S096456911500126X-main.pdf
DOI : 10.1016/j.ocecoaman.2015.04.018

Éditeur(s) : HAL CCSD
Résumé : National audience
Dans cet article nous présentons les résultats opérationnels obtenus pour la pré-détection de bateaux de pêche dans des images satellites optiques haute résolution. Les images utilisées sont de type SPOT 5 panchromatique de résolution 5m. La méthode utilisée s'appuie sur les techniques Bayésiennes classiques de détection, et ne comporte aucun pré-traitement. Au cours de cet article, nous décrivons précisément la méthode utilisée, ainsi que le réglage des deux seuls paramètres de la méthode qui sont le seuil de détection et la taille de la fenêtre d'analyse. Ces paramètres sont fixés à partir des courbes ROC (Receiver Operating Characteristic) obtenues sur les jeux de tests dont nous disposons. La méthode est enfin testée sur un jeu complet et réaliste d'images. La méthode doit être à terme intégrée dans une application industrielle.
ORASIS'09 - Congrès des jeunes chercheurs en vision par ordinateur
Trégastel, France, France

Droits : info:eu-repo/semantics/OpenAccess
inria-00404625
https://hal.inria.fr/inria-00404625
https://hal.inria.fr/inria-00404625/document
https://hal.inria.fr/inria-00404625/file/23.pdf