Centre de documentation
scientifique

A back-propagation neural network-based approach for multi-represented feature matching in update propagation / Yanxia Wang in Transactions in GIS, vol 19 n° 6 (December 2015)  

Public [article]  inTransactions in GIS > vol 19 n° 6 (December 2015) . - pp 964 – 993 Titre : A back-propagation neural network-based approach for multi-represented feature matching in update propagation Type de document : Article/Communication Auteurs : Yanxia Wang, Auteur ; Deng Chen, Auteur ; Zhiyuan Zhao, Auteur ; et al., Auteur Année de publication : 2015 Article en page(s) : pp 964 – 993 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Bases de données localisées [Termes IGN] appariement de données localisées [Termes IGN] apprentissage automatique [Termes IGN] Chine [Termes IGN] mise à jour de base de données [Termes IGN] objet géographique zonal [Termes IGN] pondération [Termes IGN] représentation multiple [Termes IGN] réseau neuronal artificiel Résumé : (auteur) Spatial data infrastructures, which are characterized by multi-represented datasets, are prevalent throughout the world. The multi-represented datasets contain different representations for identical real-world entities. Therefore, update propagation is useful and required for maintaining multi-represented datasets. The key to update propagation is the detection of identical features in different datasets that represent corresponding real-world entities and the detection of changes in updated datasets. Using polygon features of settlements as examples, this article addresses these key problems and proposes an approach for multi-represented feature matching based on spatial similarity and a back-propagation neural network (BPNN). Although this approach only utilizes the measures of distance, area, direction and length, it dynamically and objectively determines the weight of each measure through intelligent learning; in contrast, traditional approaches determine weight using expertise. Therefore, the weight may be variable in different data contexts but not for different levels of expertise. This approach can be applied not only to one-to-one matching but also to one-to-many and many-to-many matching. Experiments are designed using two different approaches and four datasets that encompass an area in China. The goals are to demonstrate the weight differences in different data contexts and to measure the performance of the BPNN-based feature matching approach. Numéro de notice : A2015--077 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12138 En ligne : http://dx.doi.org/10.1111/tgis.12138 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=81352 [article]

Web map-based POI visualization for spatial decision support / Changbin Yu in Cartography and Geographic Information Science, vol 40 n° 3 (June 2013)  

Public [article]  inCartography and Geographic Information Science > vol 40 n° 3 (June 2013) . - pp 172 - 182 Titre : Web map-based POI visualization for spatial decision support Type de document : Article/Communication Auteurs : Changbin Yu, Auteur ; Qingyun Du, Auteur ; Zhiyuan Zhao, Auteur ; Ke Nie, Auteur Année de publication : 2013 Article en page(s) : pp 172 - 182 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web [Termes IGN] Chine [Termes IGN] image multidimensionnelle [Termes IGN] outil d'aide à la décision [Termes IGN] point d'intérêt [Termes IGN] visualisation cartographique [Termes IGN] web mapping Résumé : (Auteur) The ability to extract useful information from data is a topic of considerable interest, especially with regard to organizing point-of-interest (POI) information containing many attributes as well as data about business. In generating intuitive results from investigations of traditional relational databases, traditional scientific visualization approaches for multidimensional data (e.g., Visualization in Scientific Computing) are inefficient, and deficiencies are often encountered when organizing multidimensional POIs using current online mapping tools (e.g., Google Maps). A new web visualization strategy combining a tile base map and POI symbols is proposed in this study to address the problem. In this strategy, web maps are used as the background, and POI symbols are overlaid on top of the geographical base map through a web visualization. The design and implementation of the variable model of the POI symbol were developed based on the principles of cognitive psychology. Using the information management system of welfare lottery terminals in Hubei Province in China as an example, the system architecture and functions were built using the hypermedia model, and detailed spatial decision support was provided based on the proposed visual environment integrating DCM (i.e., Digital Cartographic Model) and DLM (i.e., Digital Landscape Model) together. Numéro de notice : A2013-750 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1080/15230406.2013.807030 En ligne : https://doi.org/10.1080/15230406.2013.807030 Format de la ressource électronique : url Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=32886 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
032-2013031	RAB	Revue	Centre de documentation	En réserve L003	Disponible