Descripteur
Documents disponibles dans cette catégorie (78)
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externes
Etendre la recherche sur niveau(x) vers le bas
Asymptotically exact data augmentation : models and Monte Carlo sampling with applications to Bayesian inference / Maxime Vono (2020)
Titre : Asymptotically exact data augmentation : models and Monte Carlo sampling with applications to Bayesian inference Type de document : Thèse/HDR Auteurs : Maxime Vono, Auteur ; Nicolas Dobigeon, Directeur de thèse ; Pierre Chainais, Auteur Editeur : Toulouse : Université de Toulouse Année de publication : 2020 Importance : 200 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse en vue de l'obtention du Doctorat de l'Université de Toulouse, Signal, Image, Acoustique et OptimisationLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement du signal
[Termes IGN] échantillonnage
[Termes IGN] échantillonnage de Gibbs
[Termes IGN] estimation bayesienne
[Termes IGN] méthode de Monte-Carlo
[Termes IGN] méthode de Monte-Carlo par chaînes de Markov
[Termes IGN] optimisation (mathématiques)
[Termes IGN] processus gaussien
[Termes IGN] régression linéaireIndex. décimale : THESE Thèses et HDR Résumé : (auteur) Numerous machine learning and signal/image processing tasks can be formulated as statistical inference problems. As an archetypal example, recommendation systems rely on the completion of partially observed user/item matrix, which can be conducted via the joint estimation of latent factors and activation coefficients. More formally, the object to be inferred is usually defined as the solution of a variational or stochastic optimization problem. In particular, within a Bayesian framework, this solution is defined as the minimizer of a cost function, referred to as the posterior loss. In the simple case when this function is chosen as quadratic, the Bayesian estimator is known to be the posterior mean which minimizes the mean square error and defined as an integral according to the posterior distribution. In most real-world applicative contexts, computing such integrals is not straightforward. One alternative lies in making use of Monte Carlo integration, which consists in approximating any expectation according to the posterior distribution by an empirical average involving samples from the posterior. This so-called Monte Carlo integration requires the availability of efficient algorithmic schemes able to generate samples from a desired posterior distribution. A huge literature dedicated to random variable generation has proposed various Monte Carlo algorithms. For instance, Markov chain Monte Carlo (MCMC) methods, whose particular instances are the famous Gibbs sampler and Metropolis-Hastings algorithm, define a wide class of algorithms which allow a Markov chain to be generated with the desired stationary distribution. Despite their seemingly simplicity and genericity, conventional MCMC algorithms may be computationally inefficient for large-scale, distributed and/or highly structured problems. The main objective of this thesis consists in introducing new models and related MCMC approaches to alleviate these issues. The intractability of the posterior distribution is tackled by proposing a class of approximate but asymptotically exact augmented (AXDA) models. Then, two Gibbs samplers targetting approximate posterior distributions based on the AXDA framework, are proposed and their benefits are illustrated on challenging signal processing, image processing and machine learning problems. A detailed theoretical study of the convergence rates associated to one of these two Gibbs samplers is also conducted and reveals explicit dependences with respect to the dimension, condition number of the negative log-posterior and prescribed precision. In this work, we also pay attention to the feasibility of the sampling steps involved in the proposed Gibbs samplers. Since one of this step requires to sample from a possibly high-dimensional Gaussian distribution, we review and unify existing approaches by introducing a framework which stands for the stochastic counterpart of the celebrated proximal point algorithm. This strong connection between simulation and optimization is not isolated in this thesis. Indeed, we also show that the derived Gibbs samplers share tight links with quadratic penalty methods and that the AXDA framework yields a class of envelope functions related to the Moreau one. Note de contenu : Introduction
1- Asymptotically exact data augmentation
2- Monte Carlo sampling from AXDA
3- 3A non-asymptotic convergence analysis of the Split Gibbs sampler
4- High-dimensional Gaussian sampling: A unifying approach based on a stochastic proximal point algorithm
5- Back to optimization: The tempered AXDA envelope
ConclusionNuméro de notice : 28575 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse française Note de thèse : thèse de Doctorat : Signal, Image, Acoustique et Optimisation : Toulouse : 2020 Organisme de stage : Institut de Recherche en Informatique de Toulouse En ligne : https://tel.archives-ouvertes.fr/tel-03143936/document Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97833
Titre : Bayesian inference on complicated data Type de document : Monographie Auteurs : Niansheng Tang, Éditeur scientifique Editeur : London [UK] : IntechOpen Année de publication : 2020 Importance : 118 p. Format : 19 x 27 cm ISBN/ISSN/EAN : 978-1-83962-704-0 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Statistiques
[Termes IGN] échantillonnage
[Termes IGN] échantillonnage de Gibbs
[Termes IGN] estimation bayesienne
[Termes IGN] filtrage bayésien
[Termes IGN] inférence statistique
[Termes IGN] méthode de Monte-Carlo par chaînes de Markov
[Termes IGN] théorème de BayesRésumé : (éditeur) Due to great applications in various fields, such as social science, biomedicine, genomics, and signal processing, and the improvement of computing ability, Bayesian inference has made substantial developments for analyzing complicated data. This book introduces key ideas of Bayesian sampling methods, Bayesian estimation, and selection of the prior. It is structured around topics on the impact of the choice of the prior on Bayesian statistics, some advances on Bayesian sampling methods, and Bayesian inference for complicated data including breast cancer data, cloud-based healthcare data, gene network data, and longitudinal data. This volume is designed for statisticians, engineers, doctors, and machine learning researchers. Note de contenu : 1- On the impact of the choice of the prior in Bayesian statistics
2- A brief tour of Bayesian sampling methods
3- A review on the exact Monte Carlo simulation
4- Bayesian analysis for random effects models
5- Bayesian inference of Gene regulatory network
6- Patient Bayesian inference: Cloud-based healthcare data analysis using constraint-based adaptive boost algorithm
7- The Bayesian posterior estimators under six loss functions for unrestricted and restricted parameter spacesNuméro de notice : 28590 Affiliation des auteurs : non IGN Thématique : MATHEMATIQUE Nature : Recueil / ouvrage collectif DOI : 10.5772/intechopen.83214 En ligne : https://doi.org/10.5772/intechopen.83214 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97937 Identification of alpine glaciers in the central Himalayas using fully polarimetric L-Band SAR data / Guo-Hui Yao in IEEE Transactions on geoscience and remote sensing, vol 58 n° 1 (January 2020)
[article]
Titre : Identification of alpine glaciers in the central Himalayas using fully polarimetric L-Band SAR data Type de document : Article/Communication Auteurs : Guo-Hui Yao, Auteur ; Chang-qing Ke, Auteur ; Xiaobing Zhou, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 691 - 703 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications
[Termes IGN] analyse multiéchelle
[Termes IGN] bande L
[Termes IGN] classification orientée objet
[Termes IGN] classification par séparateurs à vaste marge
[Termes IGN] données polarimétriques
[Termes IGN] échantillonnage
[Termes IGN] glacier
[Termes IGN] Himalaya
[Termes IGN] image ALOS-PALSAR
[Termes IGN] image Landsat-OLI
[Termes IGN] image radar moirée
[Termes IGN] interferométrie différentielle
[Termes IGN] matrice de covariance
[Termes IGN] précision de la classification
[Termes IGN] segmentationRésumé : (auteur) To study the applicability of full polarimetric synthetic aperture radar (SAR) data to identify alpine glaciers in the central Himalayas, six polarimetric decomposition methods were used to obtain 20 polarimetric characteristic parameters based on the Advanced Land Observing Satellite 2 (ALOS-2) Phased Array type L-band SAR (PALSAR) data. Object-oriented multiscale segmentation was performed on a Landsat 8 Operational Land Imager (OLI) image prior to classification, and the vector boundaries of different types of training samples were selected from the segmented results. We performed a support vector machine (SVM)-based classification on the characteristic parameters from each polarimetric decomposition. All 20 parameters were then screened and combined according to different requirements: the degree of separability of different types of training samples and the type of scattering mechanisms. The results show that the classification accuracy of the incoherent decomposition characteristics based on the covariance matrix is the best, reaching 87%, and it can exceed 91% after adding the local incidence angle to the suite of classifiers. Eventually, more than 93% accuracy was achieved using a combination of multiple polarimetric parameters, which reduced the misclassification between bare ice and rock. We also analyzed the use of controlling factors on the accuracy of alpine glacier identification and found that the polarimetric information and aspect of the glacier surface are the most important factors. The former is the main basis for identification but the latter will confuse the feature distributions of different categories and cause misclassification. Numéro de notice : A2020-077 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2019.2939430 Date de publication en ligne : 25/09/2019 En ligne : https://doi.org/10.1109/TGRS.2019.2939430 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94613
in IEEE Transactions on geoscience and remote sensing > vol 58 n° 1 (January 2020) . - pp 691 - 703[article]The influence of sampling design on spatial data quality in a geographic citizen science project / Greg Brown in Transactions in GIS, Vol 23 n° 6 (November 2019)
[article]
Titre : The influence of sampling design on spatial data quality in a geographic citizen science project Type de document : Article/Communication Auteurs : Greg Brown, Auteur ; Jonathan Rhodes, Auteur ; Daniel Lunney, Auteur ; Ross Goldingay, Auteur ; et al., Auteur Année de publication : 2019 Article en page(s) : pp 1184 - 1203 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Systèmes d'information géographique
[Termes IGN] Australie
[Termes IGN] base de données localisées
[Termes IGN] cartographie collaborative
[Termes IGN] données localisées des bénévoles
[Termes IGN] échantillonnage
[Termes IGN] fiabilité des données
[Termes IGN] habitat animal
[Termes IGN] migration animale
[Termes IGN] précision des données
[Termes IGN] SIG participatifRésumé : (auteur) Geographic citizen science has much potential to assist in wildlife research and conservation, but the quality of observation data is a key concern. We examined the effects of sampling design on the quality of spatial data collected for a koala citizen science project in Australia. Data were collected from three samples—volunteers (n = 454), an Internet panel (n = 103), and landowners (n = 35)—to assess spatial data quality, a dimension of citizen science projects rarely considered. The locational accuracy of koala observations among the samples was similar when benchmarked against authoritative data (i.e., an expert‐derived koala distribution model), but there were differences in the quantity of data generated. Fewer koala location data were generated per participant by the Internet panel sample than the volunteer or landowner samples. Spatial preferences for land uses affecting koala conservation were also mapped, with landowners more likely to map locations for residential and tourism development and volunteers less likely. These spatial preferences have the potential to influence the social acceptability of future koala conservation proposals. With careful sampling design, both citizen observations and land use preferences can be included within the same project to augment scientific assessments and identify conservation opportunities and constraints. Numéro de notice : A2019-566 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12568 Date de publication en ligne : 11/07/2019 En ligne : https://onlinelibrary.wiley.com/doi/10.1111/tgis.12568 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94417
in Transactions in GIS > Vol 23 n° 6 (November 2019) . - pp 1184 - 1203[article]PpC: a new method to reduce the density of lidar data. Does it affect the DEM accuracy? / Sandra Bujan in Photogrammetric record, vol 34 n° 167 (September 2019)
[article]
Titre : PpC: a new method to reduce the density of lidar data. Does it affect the DEM accuracy? Type de document : Article/Communication Auteurs : Sandra Bujan, Auteur ; Edouardo M. González‐Ferreiro, Auteur ; Miguel Cordero, Auteur ; David Miranda, Auteur Année de publication : 2019 Article en page(s) : pp Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie
[Termes IGN] densité des points
[Termes IGN] données lidar
[Termes IGN] données localisées 3D
[Termes IGN] échantillonnage
[Termes IGN] modèle numérique de surface
[Termes IGN] pente
[Termes IGN] précision
[Termes IGN] R (langage)
[Termes IGN] réductionRésumé : (auteur) In cost–benefit analysis of lidar data acquisition, point density is often artificially reduced in order to examine how this affects the quality of derived products. However, the performance of the different density reduction methods has not yet been compared and their influence on the accuracy of the models and results has not been evaluated. A novel method for reducing the point density, termed Proportional per Cell (PpC), is presented and compared with the performance of three other reduction methods, examining their influence on the accuracy of lidar‐derived digital surface models using ISPRS reference data. The results indicate that the PpC method was better at conserving the characteristics of the original data. However, point density, sample type and slope had a greater influence than the reduction method used. Numéro de notice : A2019-499 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/phor.12295 Date de publication en ligne : 10/10/2019 En ligne : https://doi.org/10.1111/phor.12295 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93763
in Photogrammetric record > vol 34 n° 167 (September 2019) . - pp[article]Diptera in clear-felling stumps like it dry / Mats Jonsell in Scandinavian journal of forest research, vol 34 n° 8 (August 2019)PermalinkTwo contemporary and efficient two-stage sampling methods for estimating the volume of forest stands: a brief overview and unified mathematical description / Aristeidis Georgakis in Open journal of forestry, vol 9 n° 3 (July 2019)PermalinkGenetic diversity and structure of Silver fir (Abies alba Mill.) at the south-eastern limit of its distribution range / Maria Teodosiu in Annals of forest research, vol 62 n° 2 (June - December 2019)PermalinkVirtual Support Vector Machines with self-learning strategy for classification of multispectral remote sensing imagery / Christian Geiss in ISPRS Journal of photogrammetry and remote sensing, vol 151 (May 2019)PermalinkInterpreting effects of multiple, large-scale disturbances using national forest inventory data: A case study of standing dead trees in east Texas, USA / Christopher B. Edgar in Forest ecology and management, vol 437 (1 April 2019)PermalinkIs tree age or tree size reducing height increment in Abies alba Mill. at its southernmost distribution limit? / Pasquale A. Marziliano in Annals of Forest Science, vol 76 n° 1 (March 2019)PermalinkA multi-faceted CNN architecture for automatic classification of mobile LiDAR data and an algorithm to reproduce point cloud samples for enhanced training / Bhavesh Kumar in ISPRS Journal of photogrammetry and remote sensing, vol 147 (January 2019)PermalinkThe French NFI : flexibility at the heart of the design / François Morneau (2019)PermalinkDésambiguïsation des entités spatiales par apprentissage actif / Amal Chihaoui in Revue internationale de géomatique, vol 28 n° 2 (avril - juin 2018)PermalinkAn (almost) automated process to track the Martians dunes : ac.GetPreciseShifts / Arthur Coqué (2018)PermalinkMonitoring des impacts du changement climatique (ICC) sur la forêt - croissance des résineux dans un contexte de réchauffement [diaporama] / Jean-Daniel Bontemps (2018)PermalinkTree size thresholds produce biased estimates of forest biomass dynamics / Eric B. Searle in Forest ecology and management, vol 400 (15 September 2017)PermalinkA review of sampling effects and response bias in internet participatory mapping (PPGIS/PGIS/VGI) / Greg Brown in Transactions in GIS, vol 21 n° 1 (February 2017)PermalinkCartographie de l'occupation des sols à partir de séries temporelles d'images satellitaires à hautes résolutions : identification et traitement des données mal étiquetées / Charlotte Pelletier (2017)PermalinkEstimates of stem wood increments in forest resources: comparison of different approaches in forest inventory: consequences for international reporting: case study of European forests / Andrius Kuliesis in Annals of Forest Science, vol 73 n° 4 (December 2016)PermalinkHow many samples are needed? An investigation of binary logistic regression for selective omission in a road network / Qi Zhou in Cartography and Geographic Information Science, vol 43 n° 5 (November 2016)PermalinkBroad scale forest cover reconstruction from historical topographic maps / Dominik Kaim in Applied Geography, vol 67 (February 2016)PermalinkStatistical rigor in LiDAR-assisted estimation of aboveground forest biomass / Timothy G. Gregoire in Remote sensing of environment, vol 173 (February 2016)PermalinkUse of models in large-area forest surveys: comparing model-assisted, model-based and hybrid estimation / Göran Stahl in Forest ecosystems, vol 3 (2016)PermalinkHow much do we know about the endangered Atlantic Forest? Reviewing nearly 70 years of information on tree community surveys / Renato A.F. de Lima in Biodiversity & Conservation, vol 24 n° 9 (September 2015)PermalinkLand cover dynamics monitoring with Landsat data in Kunming, China: a cost-effective sampling and modelling scheme using Google Earth imagery and random forests / Ning Lu in Geocarto international, vol 30 n° 1 - 2 (January - February 2015)PermalinkAssociation-matrix-based sample consensus approach for automated registration of terrestrial laser scans using linear features / Kaleel Al-Durgham in Photogrammetric Engineering & Remote Sensing, PERS, vol 80 n° 11 (November 2014)PermalinkL'inventaire des ressources forestières en France : un nouveau regard sur des nouvelles forêts / Jean-Christophe Hervé in Revue forestière française, vol 66 n° 3 (mai - juin 2014)PermalinkEvaluating the “geographical awareness” of individuals: an exploratory analysis of Twitter data / Chen Xu in Cartography and Geographic Information Science, vol 40 n° 2 (March 2013)PermalinkPermalinkPermalinkIntegration of water transport pathways in a maple tree: responses of sap flow to branch severing / Nadezhda Nadezhdina in Annals of Forest Science, vol 67 n° 1 (January-February 2010)PermalinkRENECOFOR. Dix ans de suivi de la végétation forestière : aspects méthodologiques et évolution temporelle de la flore (1994/1995-2005) / Frédéric Archaux (2009)PermalinkL'utilisation des SIG pour l'analyse des disparités spatiales de santé dans la ville de Vientiane (Laos) / J. Vallee in Le monde des cartes, n° 197 (septembre 2008)PermalinkEstimation of local forest attributes, utilizing two-phase sampling and auxiliary data / Sakari Tuominen (2007)PermalinkDecreasing computational time of urban cellular automata through model portability / C. Dietzel in Geoinformatica, vol 10 n° 2 (June - August 2006)PermalinkSampling scheme optimization from hyperspectral data / Pravesh Debba (2006)PermalinkCaractérisation d'un habitat forestier tempéré par télédétection satellitale pour le suivi de populations aviennes : cas des mésanges en forêt de Larivour (Aube, France) / V. Godard in Photo interprétation, vol 41 n° 4 (Novembre 2005)PermalinkData mining of cellular automata's transition rules / X. Li in International journal of geographical information science IJGIS, vol 18 n° 8 (december 2004)PermalinkLes statistiques en géographie / Pierre Dumolard (2003)PermalinkConférence d'apprentissage 99, actes de CAP'99, Ecole Polytechnique, Palaiseau, 15-18 juin 1999 / Michèle Sebag (1999)PermalinkAutomated DTM validation and progressive sampling algorithm of finite element array relaxation / Urho Rauhala in Photogrammetric Engineering & Remote Sensing, PERS, vol 55 n° 4 (april 1989)PermalinkLarge-scale aerial photographic systems for forest sampling in Canada / R.D. Spencer in Canadian surveyor, vol 41 n° 1 (Spring 1987)PermalinkStructures for geo-information and their application in selective sampling for digital terrain models / B. Makarovic in ITC journal, vol 1984 n° 4 (December 1984)Permalink