Éditeur(s) : HAL CCSD Elsevier
Résumé : International audience
Voting rules relying on k-nearest neighbors (k-NN) are an effective tool in countless many machine learning techniques. Thanks to its simplicity, k-NN classification is very attractive to practitioners, as it enables very good performances in several practical applications. However, it suffers from various drawbacks, like sensitivity to "noisy" instances and poor generalization properties when dealing with sparse high-dimensional data. In this paper, we tackle the k-NN classification problem at its core by providing a novel k-NN boosting approach. Namely, we propose a supervised learning algorithm, called Universal Nearest Neighbors (UNN), that induces a leveraged k-NN rule by globally minimizing a surrogate risk upper bounding the empirical misclassification rate over training data. Interestingly, this surrogate risk can be arbitrary chosen from a class of Bregman loss functions, including the familiar exponential, logistic and squared losses. Furthermore, we show that UNN allows to efficiently filter a dataset of instances by keeping only a small fraction of data. Experimental results on the synthetic Ripley's dataset show that such a filtering strategy is able to reject "noisy" examples, and yields a classification error close to the optimal Bayes error. Experiments on standard UCI datasets show significant improvements over the current state of the art.
ISSN: 0925-2312

hal-00664462
https://hal.inria.fr/hal-00664462

Éditeur(s) : HAL CCSD IEEE
Résumé : International audience
This paper proposes a novel automated approach for the categorization of cells in fluorescence microscopy images. Our supervised classification method aims at recognizing patterns of unlabeled cells based on an annotated dataset. First, the cell images need to be indexed by encoding them in a feature space. For this purpose, we propose tailored bio-inspired features relying on the distribution of contrast information. Then, a supervised learning algorithm is proposed for classifying the cells. We carried out experiments on cellular images related to the diagnosis of autoimmune diseases, testing our classification method on the HEp-2 Cells dataset of Foggia et al (CBMS 2010). Results show classification precision larger than 96% on average, thus confirming promising application of our approach to the challenging application of cellular image classification for computer-aided diagnosis.
ICPR 2012
Tsukuba, Japan

hal-00958856
https://hal.archives-ouvertes.fr/hal-00958856
https://hal.archives-ouvertes.fr/hal-00958856/document
https://hal.archives-ouvertes.fr/hal-00958856/file/icpr_2012.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

Résumé : Les méthodes classiques d'analyse d'images satellites sont inadaptées au volume actuel du flux de données. L'automatisation de l'interprétation de ces images devient donc cruciale pour l'analyse et la gestion des phénomènes observables par satellite et évoluant dans le temps et l'espace. Ce travail vise à automatiser la cartographie dynamique de l'occupation du sol à partir d'images satellites, par des mécanismes expressifs, facilement interprétables en prenant en compte les aspects structurels de l'information géographique. Il s'inscrit dans le cadre de l'analyse d'images basée objet. Ainsi, un paramétrage supervisé d'un algorithme de segmentation d'images est proposé. Dans un deuxième temps, une méthode de classification supervisée d'objets géographiques est présentée combinant apprentissage automatique par programmation logique inductive et classement par l'approche multi-class rule set intersection. Ces approches sont appliquées à la cartographie de la bande côtière Guyanaise. Les résultats démontrent la faisabilité du paramétrage de la segmentation, mais également sa variabilité en fonction des classes de la carte de référence et des données d'entrée. Les résultats de la classification supervisée montrent qu'il est possible d'induire des règles de classification expressives, véhiculant des informations cohérentes et structurelles dans un contexte applicatif donnée et conduisant à des valeurs satisfaisantes de précision et de KAPPA (respectivement 84,6% et 0,7). Ce travail de thèse contribue ainsi à l'automatisation de la cartographie dynamique à partir d'images de télédétection et propose des perspectives originales et prometteuses.
Classical methods for satellite image analysis are inadequate for the current bulky data flow. Thus, automate the interpretation of such images becomes crucial for the analysis and management of phenomena changing in time and space, observable by satellite. Thus, this work aims at automating land cover cartography from satellite images, by expressive and easily interpretable mechanism, and by explicitly taking into account structural aspects of geographic information. It is part of the object-based image analysis framework, and assumes that it is possible to extract useful contextual knowledge from maps. Thus, a supervised parameterization methods of a segmentation algorithm is proposed. Secondly, a supervised classification of geographical objects is presented. It combines machine learning by inductive logic programming and the multi-class rule set intersection approach. These approaches are applied to the French Guiana coastline cartography. The results demonstrate the feasibility of the segmentation parameterization, but also its variability as a function of the reference map classes and of the input data. Yet, methodological developments allow to consider an operational implementation of such an approach. The results of the object supervised classification show that it is possible to induce expressive classification rules that convey consistent and structural information in a given application context and lead to reliable predictions, with overall accuracy and Kappa values equal to, respectively, 84,6% and 0,7. In conclusion, this work contributes to the automation of the dynamic cartography from remotely sensed images and proposes original and promising perpectives

http://www.theses.fr/2013AGUY0671/document

Éditeur(s) : HAL CCSD Elsevier
Résumé : International audience
The number of satellites and sensors devoted to Earth observation has become increasingly elevated, delivering extensive data, especially images. At the same time, the access to such data and the tools needed to process them has considerably improved. In the presence of such data flow, we need automatic image interpretation methods, especially when it comes to the monitoring and prediction of environmental and societal changes in highly dynamic socio-environmental contexts. This could be accomplished via artificial intelligence. The concept described here relies on the induction of classification rules that explicitly take into account structural knowledge, using Aleph, an Inductive Logic Programming (ILP) system, combined with a multi-class classification procedure. This methodology was used to monitor changes in land cover/use of the French Guiana coastline. One hundred and fifty-eight classification rules were induced from 3 diachronic land cover/use maps including 38 classes. These rules were expressed in first order logic language, which makes them easily understandable by non-experts. A 10-fold cross-validation gave significant average values of 84.62%, 99.57% and 77.22% for classification accuracy, specificity and sensitivity, respectively. Our methodology could be beneficial to automatically classify new objects and to facilitate object-based classification procedures.
ISSN: 0098-3004

hal-01369822
https://hal.archives-ouvertes.fr/hal-01369822
https://hal.archives-ouvertes.fr/hal-01369822/document
https://hal.archives-ouvertes.fr/hal-01369822/file/CAGEO-D-13-00538R1_article.pdf
DOI : 10.1016/j.cageo.2014.08.013

Éditeur(s) : Centre français du littoral
Résumé : This study presents the first results of an ongoing research program that aims to derive thematic maps of the intertidal lagoon of Arcachon (SW Atlantic coast of France) from space imagery. At this stage, we present the results of the tests performed on Formosat-2 imagery. Several classification strategies have been tried with the aim to discriminate the sedimentary facies and the main species of the lagoon. The classes calculated by an optimized unsupervised clustering method, based on simulated annealing global minimization technique, were used to train a supervised classification algorithm. This approach allowed us to derive a bio-sedimentary map which overall accuracy is about 84%. Also, this method has the advantage of describing the fraction of vegetation cover of the seagrass.
Cette étude présente les premiers résultats d’un vaste programme de recherche qui ambitionne de définir une méthode de cartographie des platiers intertidaux du Bassin d’Arcachon (France) par télédétection. Les résultats présentés ici concernent les tests effectués sur l’imagerie Formosat-2 dans le but de discriminer les sédiments et les principales espèces végétales de la lagune. Le résultat d'une classification non supervisée optimisée par la méthode du recuit simulé est ensuite utilisé pour entraîner une classification par minimum de distance. Cette approche permet d’obtenir une carte des faciès bio-sédimentaires dont la précision est estimée à plus de 84 %. Cette méthode présente, en outre, un excellent potentiel pour la détermination du pourcentage de couvert végétal des herbiers à zostères.
Paralia (1760-8716) (Centre français du littoral), 2008 , N. 10 , P. 563-572

Droits : info:eu-repo/semantics/openAccess
http://archimer.ifremer.fr/doc/00254/36572/35110.pdf
DOI:10.5150/jngcgc.2008.054-L
http://archimer.ifremer.fr/doc/00254/36572/

Résumé : Sea fish farms with production of more than 20 tons per year in France must obtain two operating licences: (i) one for Sea Farming (AECM), with the aim of ensuring that the granted site and use of the maritime public domain for exploitation will respect all restrictions of general interest; (ii) one for regulating Facilities Classified for the Protection of the Environment (ICPE). Although the first one requires a relatively simple licence request file, the second one demands a very complete file, which includes, beyond the notice of exploitation information, a complete impact study, as well as a hazards study and a health and safety notice. In this context, petitioners in Corsica (adjustment of status or new exploitation) are faced with the same difficulties, which highlighted the need for a methodological guide adapted to each region's specific situation, assembling in particular the necessary baseline data (legal, zootechnical, geographical, climatic, socio-economic, ecological...) as well as recognised methods for evaluating the potential effects of the farm on the environment. Development of this guide was supported by ADEC and supervised by a steering committee composed of representatives from the administrations concerned, fish farmers and scientific bodies. The significant aspects dealt with the effects of fish farming on Posidonie herbarium, a protected species very present in Corsica and with coordinating the two AECM and ICPE procedures. For each part of the ICPE file, the guide introduces the technical or scientific context and, depending upon the case, the state of the art, sources of available data, acquisition and methods of acquiring measurements and of assessing the potential effects, as well as practical editing recommendations. Finally, the guide is made complete by a model schedule of conditions designed to help petitioners to have a specialist research department incorporate all or part of the file. This guide primarily concerns first-time marine facilities for exploitation in Corsica, conceived of as in the open sea rather than in confined spaces. Nonetheless, any fish farmer or future fish farmer needing to process a request for an exploitation licence may find it useful.
Les piscicultures marines de plus de 20 t/an de production sont soumises en France à l'obtention de deux autorisations d'exploiter : (i) celle au titre des Cultures Marines (AECM), visant à s'assurer que le site concédé et l'usage du domaine public maritime pour l'exploitation permettent de respecter l'ensemble des contraintes d'intérêt général ; (ii) celle au titre de la réglementation des Installations Classées pour la Protection de l'Environnement (ICPE). Si la première nécessite un dossier de demande d'autorisation relativement simple, la seconde requiert un dossier très complet, qui comprend, outre une notice de renseignements sur l'exploitation, une étude d'impact complète, ainsi qu'une étude des dangers et une notice d'hygiène et de sécurité. Dans ce contexte, les demandeurs en Corse (régularisation ou exploitation nouvelle) sont confrontés aux mêmes difficultés, ce qui a mis en évidence le besoin d'un guide méthodologique adapté aux spécificités régionales, rassemblant en particulier les données de base nécessaires (juridiques, zootechniques, géographiques, climatiques, socio-économiques, écologiques...) ainsi que les méthodes reconnues de l'évaluation des effets potentiels de la ferme sur l'environnement. L'élaboration de ce guide a été soutenue par l'ADEC et suivie par un comité de pilotage composé de représentants des administrations concernées, des pisciculteurs et d'organismes scientifiques. Les aspects importants ont porté sur les effets de la pisciculture sur l'herbier de Posidonie, espèce protégée très présente en Corse et sur la coordination entre les deux procédures AECM et ICPE. Pour chaque partie du dossier ICPE, le guide présente le contexte technique ou scientifique et selon le cas, l'état de l'art, les sources de données disponibles, les méthodes d'acquisition des mesures et d'évaluation des effets potentiels, ainsi que des recommandations pratiques de rédaction. Enfin, le guide est complété par un cahier des charges type destiné à aider les demandeurs à confier à un bureau d'étude spécialisé la réalisation de tout ou partie de la constitution du dossier. Ce guide concerne prioritairement les installations marines de nouvelles exploitations en Corse, envisagées en mer ouverte plutôt que dans des espaces confinés. Néanmoins tout pisciculteur ou futur pisciculteur devant instruire une demande d'autorisation d'exploiter peut y trouver intérêt.

Droits : info:eu-repo/semantics/openAccess
http://archimer.ifremer.fr/doc/2004/rapport-2188.pdf
http://archimer.ifremer.fr/doc/00000/2188/