Descripteur
Documents disponibles dans cette catégorie (1866)
![](./images/expand_all.gif)
![](./images/collapse_all.gif)
Etendre la recherche sur niveau(x) vers le bas
Hyperparameter optimization of neural network-driven spatial models accelerated using cyber-enabled high-performance computing / Minrui Zheng in International journal of geographical information science IJGIS, Vol 33 n° 1-2 (January - February 2019)
![]()
[article]
Titre : Hyperparameter optimization of neural network-driven spatial models accelerated using cyber-enabled high-performance computing Type de document : Article/Communication Auteurs : Minrui Zheng, Auteur ; Wenwu Tang, Auteur ; Xiang Zhao, Auteur Année de publication : 2019 Article en page(s) : pp 314 - 345 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle
[Termes IGN] algorithme d'apprentissage
[Termes IGN] analyse spatiale
[Termes IGN] apprentissage profond
[Termes IGN] Caroline du Nord (Etats-Unis)
[Termes IGN] données spatiotemporelles
[Termes IGN] géostatistique
[Termes IGN] méthode des moindres carrés
[Termes IGN] modèle empirique
[Termes IGN] modèle numérique de surface
[Termes IGN] modélisation spatiale
[Termes IGN] optimisation (mathématiques)
[Termes IGN] régression linéaire
[Termes IGN] réseau neuronal artificiel
[Termes IGN] système d'information foncièreRésumé : (auteur) Artificial neural networks (ANNs) have been extensively used for the spatially explicit modeling of complex geographic phenomena. However, because of the complexity of the computational process, there has been an inadequate investigation on the parameter configuration of neural networks. Most studies in the literature from GIScience rely on a trial-and-error approach to select the parameter setting for ANN-driven spatial models. Hyperparameter optimization provides support for selecting the optimal architectures of ANNs. Thus, in this study, we develop an automated hyperparameter selection approach to identify optimal neural networks for spatial modeling. Further, the use of hyperparameter optimization is challenging because hyperparameter space is often large and the associated computational demand is heavy. Therefore, we utilize high-performance computing to accelerate the model selection process. Furthermore, we involve spatial statistics approaches to improve the efficiency of hyperparameter optimization. The spatial model used in our case study is a land price evaluation model in Mecklenburg County, North Carolina, USA. Our results demonstrate that the automated selection approach improves the model-level performance compared with linear regression, and the high-performance computing and spatial statistics approaches are of great help for accelerating and enhancing the selection of optimal neural networks for spatial modeling. Numéro de notice : A2019-022 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2018.1530355 Date de publication en ligne : 12/10/2018 En ligne : https://doi.org/10.1080/13658816.2018.1530355 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91689
in International journal of geographical information science IJGIS > Vol 33 n° 1-2 (January - February 2019) . - pp 314 - 345[article]Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 079-2019011 RAB Revue Centre de documentation En réserve L003 Disponible Integration of lidar data and GIS data for point cloud semantic enrichment at the point level / Harith Aljumaily in Photogrammetric Engineering & Remote Sensing, PERS, vol 85 n° 1 (January 2019)
![]()
[article]
Titre : Integration of lidar data and GIS data for point cloud semantic enrichment at the point level Type de document : Article/Communication Auteurs : Harith Aljumaily, Auteur ; Debra F. Laefer, Auteur ; Dolores Cuadra, Auteur Année de publication : 2019 Article en page(s) : pp 29 - 42 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie
[Termes IGN] analyse de groupement
[Termes IGN] détection du bâti
[Termes IGN] données lidar
[Termes IGN] données localisées 3D
[Termes IGN] Dublin (Irlande ; ville)
[Termes IGN] enrichissement sémantique
[Termes IGN] extraction de la végétation
[Termes IGN] extraction du réseau routier
[Termes IGN] flore urbaine
[Termes IGN] image multibande
[Termes IGN] information sémantique
[Termes IGN] interpolation linéaire
[Termes IGN] OpenStreetMap
[Termes IGN] réseau routier
[Termes IGN] segmentation
[Termes IGN] segmentation sémantique
[Termes IGN] semis de points
[Termes IGN] système de gestion de base de données
[Termes IGN] zone urbaineRésumé : (auteur) Commercial aerial laser scanning is generally delivered with point-by-point metadata for object identification, but current vendor-generated classification approaches (which rely exclusively on that data) generate high misclassification rates in urban areas. To overcome this problem and provide a fully scalable solution that harnesses distributed computing capabilities, this paper introduces a novel system, employing a MapReduce framework and existing GIS-based data, to provide more detailed and accurate classification. The approach goes beyond traditional gross-level classification (roads, buildings, trees, noise) by enriching the point cloud metadata with detailed semantic information about the object type. The approach was evaluated using two datasets of differing point density, separated by eight years for the same study area in Dublin, Ireland. As evaluated against manually classified data, classification quality ranged from 76% to 91% depending upon category and only 8% remained unclassified, as opposed to the commercial vendor's classification quality which ranged from 43% to 78% with 82% left unclassified. Numéro de notice : A2019-027 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.14358/PERS.85.1.29 Date de publication en ligne : 01/01/2019 En ligne : https://doi.org/10.14358/PERS.85.1.29 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91964
in Photogrammetric Engineering & Remote Sensing, PERS > vol 85 n° 1 (January 2019) . - pp 29 - 42[article]Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 105-2019011 SL Revue Centre de documentation Revues en salle Disponible Mass variation observing system by high low inter-satellite links (MOBILE) : a new concept for sustained observation of mass transport from space / Roland Pail in Journal of geodetic science, vol 9 n° 1 (January 2019)
![]()
[article]
Titre : Mass variation observing system by high low inter-satellite links (MOBILE) : a new concept for sustained observation of mass transport from space Type de document : Article/Communication Auteurs : Roland Pail, Auteur ; Jonathan Bamber, Auteur ; Richard Biancale, Auteur ; Rory Bingham, Auteur ; Carla Braitenberg, Auteur ; Annette Eicker, Auteur ; Frank Flechtner, Auteur ; Thomas Gruber, Auteur ; Andreas Güntner, Auteur ; Gerhard Heinzel, Auteur ; Martin Horwath, Auteur ; Laurent Longuevergne, Auteur ; J. Muller, Auteur ; Isabelle Panet , Auteur ; Hubert Savenije, Auteur ; S. Seneviratne, Auteur ; Nico Sneeuw, Auteur ; Tonie M. van Dam, Auteur ; Bert Wouters, Auteur
Année de publication : 2019 Projets : 1-Pas de projet / Article en page(s) : pp 48 - 58 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géodésie physique
[Termes IGN] champ de pesanteur terrestre
[Termes IGN] gravimétrie spatiale
[Termes IGN] harmonique sphérique
[Termes IGN] masseRésumé : (auteur) As changes in gravity are directly related to mass variability, satellite missions observing the Earth’s time varying gravity field are a unique tool for observing mass transport processes in the Earth system, such as the water cycle, rapid changes in the cryosphere, oceans, and solid Earth processes, on a global scale. The observation of Earth’s gravity field was successfully performed by the GRACE and GOCE satellite missions, and will be continued by the GRACE Follow-On mission. A comprehensive team of European scientists proposed the next-generation gravity field mission MOBILE in response to the European Space Agency (ESA) call for a Core Mission in the frame of Earth Explorer 10 (EE10). MOBILE is based on the innovative observational concept of a high-low tracking formation with micrometer ranging accuracy, complemented by new instrument concepts. Since a high-low tracking mission primarily observes the radial component of gravity-induced orbit perturbations, the error structure is close to isotropic. This geometry significantly reduces artefacts of previous along-track ranging low-low formations (GRACE, GRACE-Follow-On) such as the typical striping patterns. The minimum configuration consists of at least two medium-Earth orbiters (MEOs) at 10000 km altitude or higher, and one low-Earth orbiter (LEO) at 350-400 km. The main instrument is a laser-based distance or distance change measurement system, which is placed at the LEO. The MEOs are equipped either with passive reflectors or transponders. In a numerical closed-loop simulation, it was demonstrated that this minimum configuration is in agreement with the threshold science requirements of 5 mm equivalent water height (EWH) accuracy at 400 km wavelength, and 10 cm EWH at 200 km. MOBILE provides promising potential future perspectives by linking the concept to existing space infrastructure such as Galileo next-generation, as future element of the Copernicus/Sentinel programme, and holds the potential of miniaturization even up to swarm configurations. As such MOBILE can be considered as a precursor and role model for a sustained mass transport observing system from space. Numéro de notice : A2019-635 Affiliation des auteurs : Géodésie+Ext (mi2018-2019) Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1515/jogs-2019-0006 Date de publication en ligne : 21/10/2019 En ligne : https://doi.org/10.1515/jogs-2019-0006 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95454
in Journal of geodetic science > vol 9 n° 1 (January 2019) . - pp 48 - 58[article]Optimisation of GNSS networks, considering baseline correlations / M. Amin Alizadeh-Khameneh in Survey review, vol 51 n° 364 (January 2019)
![]()
[article]
Titre : Optimisation of GNSS networks, considering baseline correlations Type de document : Article/Communication Auteurs : M. Amin Alizadeh-Khameneh, Auteur ; Lars E. Sjöberg, Auteur ; Anna B. O. Jensen, Auteur Année de publication : 2019 Article en page(s) : pp 35 - 42 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Systèmes de référence et réseaux
[Termes IGN] corrélation
[Termes IGN] données GNSS
[Termes IGN] double différence
[Termes IGN] ligne de base
[Termes IGN] optimisation (mathématiques)
[Termes IGN] réseau géodésique local
[Termes IGN] SuèdeRésumé : (Auteur) By considering global navigation satellite system (GNSS) observations, one can perform optimisation according to some pre-defined criteria and come up with the best location of receivers and optimum number of baselines. In practice, it is quite common to neglect the effect of correlations between baselines, and instead assume single-baseline-adjusted data in the optimisation procedure. However, in each session of observation, usually more than two receivers are simultaneously taking data from a number of common GNSS satellites, implying that the single- or double-difference observations are correlated. Our study designs an optimal observation plan for a GPS network in Skåne in southern Sweden, with the aim of determining possible displacements. Assuming three receivers in each session of observations leads to correlation between the GPS baselines, and consequently a fully populated weight matrix for each session of observation. A bi-objective optimisation model of precision and reliability is chosen to optimise the variance factor of each session, and eventually, design an observation plan. It is shown in this study that observing six out of ten possible sessions is sufficient to enable the network to detect a 5 mm displacement at each station. Assuming that the double-difference phase observations are uncorrelated changes the observation plan by retaining two more sessions. However, defining the weight matrix based on the double-difference observations requires the correlations to be taken into account, and neglecting them leads to incorrect results. Numéro de notice : A2019-187 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Numéro de périodique nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/00396265.2017.1342896 Date de publication en ligne : 26/06/2017 En ligne : https://doi.org/10.1080/00396265.2017.1342896 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92618
in Survey review > vol 51 n° 364 (January 2019) . - pp 35 - 42[article]
Titre : Optimization in control applications Type de document : Monographie Auteurs : Guillermo Valencia-Palomo, Éditeur scientifique ; Francisco Ronay Lopez-Estrada, Éditeur scientifique Editeur : Bâle [Suisse] : Multidisciplinary Digital Publishing Institute MDPI Année de publication : 2019 Importance : 256 p. Format : 16 x 24 cm ISBN/ISSN/EAN : 978-3-03897-448-2 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Mathématique
[Termes IGN] modèle mathématique
[Termes IGN] optimisation (mathématiques)
[Termes IGN] programmation stochastiqueRésumé : (auteur) Mathematical optimization is the selection of the best element in a set with respect to a given criterion. Optimization has become one of the most-used tools in modern control theory for computing the control law, adjusting the controller parameters (tuning), model fitting, and finding suitable conditions in order to fulfill a given closed-loop property, among others. In the simplest case, optimization consists of maximizing or minimizing a function by systematically choosing input values from a valid input set and computing the function value. Nevertheless, real-world control systems need to comply with several conditions and constraints that have to be taken into account in the problem formulation—these represent challenges in the application of the optimization algorithms.The aim of this Special Issue is to offer the state-of-the-art of the most advanced optimization techniques (online and offline) and their applications in control engineering.] Note de contenu : 1- Rapid solution of optimal control problems by a functional spreadsheet paradigm: A practical method for the non-programme
2- Novel spreadsheet direct method for optimal control problems
3- Time needed to control an epidemic with restricted resources in SIR model with short-term controlled population: A fixed point method for a free isoperimetric optimal control problem
4- Optimal strategies for psoriasis treatment
5- Optimal control analysis of a mathematical model for breast cancer
6- Cost-effective analysis of control strategies to reduce the prevalence of cutaneous
leishmaniasis, based on a mathematical model
7- Optimal control and computational method for the resolution of isoperimetric problem in a discrete-time SIRS system
8- Solution of optimal harvesting problem by finite difference approximations of
size-structured population model
9- Solution of fuzzy differential equations using fuzzy Sumudu transforms
10- A simple spectral observer
11- Differential evolution algorithm for multilevel assignment problem: A case study in chicken transportation
12- Modeling and simulation of a hydraulic network for leak diagnosisNuméro de notice : 28503 Affiliation des auteurs : non IGN Thématique : MATHEMATIQUE Nature : Monographie DOI : 10.3390/books978-3-03897-448-2 En ligne : https://doi.org/10.3390/books978-3-03897-448-2 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97002 PermalinkPermalinkPotentialités de l’imagerie couleur embarquée pour la détection et la cartographie des maladies fongiques de la vigne / Florent Abdelghafour (2019)
PermalinkPermalinkQuery rewriting for semantic query optimization in spatial databases / Eduardo Mella in Geoinformatica, vol 23 n° 1 (January 2019)
PermalinkRetour d'expérience de l'école OpenMOLE "ExModelo", organisée en partenariat avec le méso-centre du CRIANN / Mathieu Leclaire (2019)
PermalinkPermalinkPermalinkVariational learning of mixture wishart model for PolSAR image classification / Qian Wu in IEEE Transactions on geoscience and remote sensing, vol 57 n° 1 (January 2019)
PermalinkUn algorithme pour battre le record du SwissTrainChallenge : poser le pied dans chacun des 26 cantons le plus rapidement possible en utilisant uniquement des transports publics / Emmanuel Clédat in XYZ, n° 157 (décembre 2018 - février 2019)
Permalink