Centre dedocumentation
scientifique

A hidden Markov model for matching spatial networks / Benoit Costes in Journal of Spatial Information Science (JoSIS), n° 18 (2019)  

Public [article]  inJournal of Spatial Information Science (JoSIS) > n° 18 (2019) . - pp 57 - 89 Titre : A hidden Markov model for matching spatial networks Type de document : Article/Communication Auteurs : Benoit Costes , Auteur ; Julien Perret , Auteur Année de publication : 2019 Projets : SODUCO / Perret, Julien Article en page(s) : pp 57 - 89 Note générale : bibliographie We thank the entire GeoHistoricalData team for their combined efforts in co-constructing open geohistorical data, Romain Reuillon, Mathieu Leclaire and the entire OpenMOLE team for their assistance in the exploration and calibration of the models used in the article. We also thank the anonymous reviewers for their feedback and gratefully acknowledge the support of the French Agence Nationale de la Recherche (ANR), under grant ANR-18-CE38-0013 (SoDUCo project). Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes descripteurs IGN] analyse de sensibilité [Termes descripteurs IGN] appariement de réseaux [Termes descripteurs IGN] Hidden Markov Model (HMM) [Termes descripteurs IGN] modèle topologique réseau [Termes descripteurs IGN] réseau ferroviaire [Termes descripteurs IGN] réseau fluvial [Termes descripteurs IGN] réseau routier Résumé : (auteur) Datasets of the same geographic space at different scales and temporalities are increasingly abundant, paving the way for new scientific research. These datasets require data integration, which implies linking homologous entities in a process called data matching that remains a challenging task, despite a quite substantial literature, because of data imperfections and heterogeneities. In this paper, we present an approach for matching spatial networks based on a hidden Markov model (HMM) that takes full benefit of the underlying topology of networks. The approach is assessed using four heterogeneous datasets (streets, roads, railway, and hydrographic networks), showing that the HMM algorithm is robust in regards to data heterogeneities and imperfections (geometric discrepancies and differences in level of details) and adaptable to match any type of spatial networks. It also has the advantage of requiring no mandatory parameters, as proven by a sensitivity exploration, except a distance threshold that filters potential matching candidates in order to speed-up the process. Finally, a comparison with a commonly cited approach highlights good matching accuracy and completeness. Numéro de notice : A2019-274 Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.5311/JOSIS.2019.18.489 date de publication en ligne : 01/07/2019 En ligne : https://doi.org/10.5311/JOSIS.2019.18.489 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95337 [article]

OpenStreetMap in GIScience / Jamal Jokar Arsanjani (2015)

Public Titre : OpenStreetMap in GIScience : experiences, research, and applications Type de document : Monographie Auteurs : Jamal Jokar Arsanjani, Editeur scientifique ; Alexander Zipf, Editeur scientifique ; Peter Mooney, Editeur scientifique ; Marco Helbich, Editeur scientifique Editeur : Berlin, Heidelberg, Vienne, New York, ... : Springer Année de publication : 2015 Collection : Lecture notes in Geoinformation and Cartography, ISSN 1863-2246 Importance : 324 p. Format : 16 x 24 cm ISBN/ISSN/EAN : 978-3-319-14279-1 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Bases de données localisées [Termes descripteurs IGN] analyse de données [Termes descripteurs IGN] base de données foncières [Termes descripteurs IGN] cartographie collaborative [Termes descripteurs IGN] données localisées des bénévoles [Termes descripteurs IGN] données statistiques [Termes descripteurs IGN] graphe [Termes descripteurs IGN] impact social [Termes descripteurs IGN] itinéraire [Termes descripteurs IGN] modèle topologique réseau [Termes descripteurs IGN] occupation du sol [Termes descripteurs IGN] OpenStreetMap [Termes descripteurs IGN] qualité des données Index. décimale : 37.10 Bases de données géographiques Résumé : (Editeur) This edited volume presents a collection of lessons learned with, and research conducted on, OpenStreetMap, the goal being to promote the project’s integration. The respective chapters address a) state-of-the-art and cutting-edge approaches to data quality analysis in OpenStreetMap, b) investigations on understanding OpenStreetMap contributors and the nature of their contributions, c) identifying patterns of contributions and contributors, d) applications of OpenStreetMap in different domains, e) mining value-added knowledge and information from OpenStreetMap, f) limitations in the analysis OpenStreetMap data, and g) integrating OpenStreetMap with commercial and non-commercial datasets. The book offers an ideal opportunity to present and disseminate a number of cutting-edge developments and applications in the field of geography, spatial statistics, GIS, social science, and cartography. Note de contenu : Part 1 - Data management and quality Part 2 - Social context Part 3 - Network modeling and routing Part 4 - Land management and urban form Part 5 - Outlook Numéro de notice : 22415 Thématique : GEOMATIQUE Nature : Recueil / ouvrage collectif Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=79437

Contient

• OpenStreetMap in GIScience : experiences, research, and applications. Inferring the Scale of OpenStreetMap Features / Guillaume Touya (2015)  

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
22415-01	37.10	Livre	Centre de documentation	Géomatique	Disponible

Spatially modelling pathways of migratory birds for nature reserve site selection / J.A. Downs in International journal of geographical information science IJGIS, vol 22 n° 6-7 (june 2008)

Public [article]  inInternational journal of geographical information science IJGIS > vol 22 n° 6-7 (june 2008) . - pp 687 - 702 Titre : Spatially modelling pathways of migratory birds for nature reserve site selection Type de document : Article/Communication Auteurs : J.A. Downs, Auteur ; M.W. Horner, Auteur Année de publication : 2008 Article en page(s) : pp 687 - 702 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications SIG [Termes descripteurs IGN] habitat animal [Termes descripteurs IGN] migration animale [Termes descripteurs IGN] modèle topologique réseau [Termes descripteurs IGN] oiseau [Termes descripteurs IGN] outil d'aide à la décision [Termes descripteurs IGN] réserve naturelle [Termes descripteurs IGN] système d'information géographique [Termes descripteurs IGN] zone humide Résumé : (Auteur) Conserving habitat for migratory birds presents a unique set of challenges, because multiple reserves distributed across space are required for complete protection of single species. We developed the Flight Leg Allocation Problem (FLAP), a distance-constrained shortest path problem, to identify optimal configurations of stopover habitats for migratory bird conservation. FLAP is based on a relational network topology model, where stopovers are represented as nodes and potential pathways by links. FLAP finds the optimal migratory pathway that consists of the fewest number of stops in the shortest distance, given that flocks of birds are limited by maximum daily flight capabilities and constrained by carrying capacities of individual habitats. We first present the FLAP model formulation and describe results of an empirical test for a large wetland dataset under different climatic conditions. Our results illustrate how migratory birds might respond to changes in both the temporal and spatial distribution of available stopovers. We also discuss conservation implications for using FLAP to identify priority sites for migratory birds in nature reserve networks. Additionally, the methods presented in this paper may be useful for modelling other types of spatially and temporally dynamic networks. Copyright Taylor & Francis Numéro de notice : A2008-228 Thématique : GEOMATIQUE Nature : Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=29223 [article]

Réservation

Réserver ce document

Exemplaires (2)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
079-08041	RAB	Revue	Centre de documentation	En réserve 3L	Disponible
079-08042	RAB	Revue	Centre de documentation	En réserve 3L	Disponible

Neural network model for standard PCA and its variants applied to remote sensing / S. Chitroub in International Journal of Remote Sensing IJRS, vol 26 n° 10 (May 2005)

Public [article]  inInternational Journal of Remote Sensing IJRS > vol 26 n° 10 (May 2005) . - pp 2197 - 2218 Titre : Neural network model for standard PCA and its variants applied to remote sensing Type de document : Article/Communication Auteurs : S. Chitroub, Auteur Année de publication : 2005 Article en page(s) : pp 2197 - 2218 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] analyse en composantes principales [Termes descripteurs IGN] apprentissage automatique [Termes descripteurs IGN] diagonalisation [Termes descripteurs IGN] extraction automatique [Termes descripteurs IGN] image Landsat-TM [Termes descripteurs IGN] image multibande [Termes descripteurs IGN] matrice de covariance [Termes descripteurs IGN] modèle topologique réseau [Termes descripteurs IGN] réseau neuronal artificiel [Termes descripteurs IGN] valeur propre Résumé : (Auteur) The conventional approach for principal component analysis (PCA) and its variants applied to remote sensing involves the computation of the input data covariance/correlation matrix and/or that of noise and application of diagonalization procedures for extracting the eigenvalues and corresponding eigenvectors. When the data dimension grows significantly, the matrix computations and manipulations become practically inefficient and inaccurate due to round-off errors. In addition, all the eigenvalues and their corresponding eigenvectors have to be evaluated. These deficiencies make the conventional scheme inefficient for remote sensing applications. For that we propose here a neural network model that performs the PCA and its variants directly from the original data without any additional non-neuronal computations or preliminary matrix estimation. Since the end user is usually not a neural network specialist, the neural network model as well as its execution are carefully designed in order to be automated as much as possible. This includes both the design of the network topology and the input/output representation as well as the design of the training algorithms. The global convergence of the model is studied. Its application has been realized on Landsat Thematic Mapper (TM) multispectral data. The obtained results show that the model performs well. Numéro de notice : A2005-260 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=27396 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
080-05101	RAB	Revue	Centre de documentation	En réserve 3L	Disponible