Centre de documentation
scientifique

Dépouillements

A knowledge representation model based on the geographic spatiotemporal process / Kun Zheng in International journal of geographical information science IJGIS, vol 36 n° 4 (April 2022)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 36 n° 4 (April 2022) . - pp 674 - 691 Titre : A knowledge representation model based on the geographic spatiotemporal process Type de document : Article/Communication Auteurs : Kun Zheng, Auteur ; Ming Hui Xie, Auteur ; Jin Biao Zhang, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 674 - 691 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes IGN] analyse comparative [Termes IGN] analyse diachronique [Termes IGN] approche hiérarchique [Termes IGN] ontologie [Termes IGN] raisonnement spatiotemporel [Termes IGN] représentation des connaissances [Termes IGN] représentation du changement [Termes IGN] représentation géographique [Termes IGN] réseau sémantique Résumé : (auteur) Knowledge graphs (KGs) represent entities and relations as computable networks, which is of great value for discovering hidden knowledge and patterns. Geographic KGs mainly describe static facts and have difficulty representing changes, greatly limiting their application in geographic spatiotemporal processes. By analyzing the spatiotemporal features and evolution of geographic elements, this study presents the geographic evolutionary knowledge graph (GEKG). Its representation model has five core elements: time, geographic event (geo-event), geographic entity (geo-entity), activity and property, and defines six relations: logical, semantic, evolutionary and temporal relation, participation and inclusion. It establishes a hierarchical cubical model structure and each temporal layer extends vertically and horizontally starting with the earliest geo-event. Vertical expansion refers to the connection between different kinds of element, such as the participation relation between geo-entities and geo-events. Horizontal expansion indicates the association between the same kinds of element, such as the semantic relation between geo-entities. For different layers, the spatiotemporal differences of elements produce the evolutionary relation. Finally, the comparison of GEKG with Yet Another Great Ontology (YAGO) and Geographic Knowledge Graph (GeoKG) shows that GEKG has more advantages in representing geographic evolutionary knowledge, revealing the evolution mechanism of geographic elements and the evolutionary reasons. Numéro de notice : A2022-255 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2021.1962527 Date de publication en ligne : 05/08/2021 En ligne : https://doi.org/10.1080/13658816.2021.1962527 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100228 [article]

Discovering co-location patterns in multivariate spatial flow data / Jiannan Cai in International journal of geographical information science IJGIS, vol 36 n° 4 (April 2022)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 36 n° 4 (April 2022) . - pp 720 - 748 Titre : Discovering co-location patterns in multivariate spatial flow data Type de document : Article/Communication Auteurs : Jiannan Cai, Auteur ; Mei-Po Kwan, Auteur Année de publication : 2022 Article en page(s) : pp 720 - 748 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] analyse bivariée [Termes IGN] analyse de groupement [Termes IGN] analyse univariée [Termes IGN] autocorrélation spatiale [Termes IGN] Chicago (Illinois) [Termes IGN] co-positionnement [Termes IGN] données de flux [Termes IGN] données socio-économiques [Termes IGN] dynamique spatiale [Termes IGN] enquête [Termes IGN] exploration de données géographiques [Termes IGN] migration pendulaire [Termes IGN] origine - destination [Termes IGN] voisinage (relation topologique) Résumé : (auteur) Spatial flow co-location patterns (FCLPs) are important for understanding the spatial dynamics and associations of movements. However, conventional point-based co-location pattern discovery methods ignore spatial movements between locations and thus may generate erroneous findings when applied to spatial flows. Despite recent advances, there is still a lack of methods for analyzing multivariate flows. To bridge the gap, this paper formulates a novel problem of FCLP discovery and presents an effective detection method based on frequent-pattern mining and spatial statistics. We first define a flow co-location index to quantify the co-location frequency of different features in flow neighborhoods, and then employ a bottom-up method to discover all frequent FCLPs. To further establish the statistical significance of the results, we develop a flow pattern reconstruction method to model the benchmark null hypothesis of independence conditioning on univariate flow characteristics (e.g. flow autocorrelation). Synthetic experiments with predefined FCLPs verify the advantages of our method in terms of correctness over available alternatives. A case study using individual home-work commuting flow data in the Chicago Metropolitan Area demonstrates that residence- or workplace-based co-location patterns tend to overestimate the co-location frequency of people with different occupations and could lead to inconsistent results. Numéro de notice : A2022-256 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2021.1980217 Date de publication en ligne : 20/09/2021 En ligne : https://doi.org/10.1080/13658816.2021.1980217 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100229 [article]

An exact statistical method for analyzing co-location on a street network and its computational implementation / Wataru Morioka in International journal of geographical information science IJGIS, vol 36 n° 4 (April 2022)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 36 n° 4 (April 2022) . - pp 773 - 798 Titre : An exact statistical method for analyzing co-location on a street network and its computational implementation Type de document : Article/Communication Auteurs : Wataru Morioka, Auteur ; Mei-Po Kwan, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 773 - 798 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] analyse de groupement [Termes IGN] co-positionnement [Termes IGN] distance euclidienne [Termes IGN] fonction K de Ripley [Termes IGN] implémentation (informatique) [Termes IGN] méthode statistique [Termes IGN] réseau routier [Termes IGN] Tokyo (Japon) [Termes IGN] zone tampon Résumé : (auteur) In many central districts in cities across the world, different types of stores form clusters resulting from the benefits of spatial agglomeration. To precisely analyze co-location relationships in a micro-scale space, this study develops a new statistical method by addressing the limitations of the ordinary cross K function method. The objectives of this paper are, first, to formulate an exact statistical method for analyzing co-location along streets in a central district constrained by a street network; second, to implement this statistical method in computational procedures. Third, this method is extended to the analysis of repulsive-location, i.e. phenomena of stores locating repulsively among different types of stores. Fourth, the paper shows a graph-theoretic diagram illustrating the spatial structure of stores in a central district consisting of bilateral, unilateral co-location and repulsive-location. Last, the proposed method is applied to eight different types of stores in a trendy district in Tokyo. The results show that the method is useful for revealing the spatial structure consisting of co-location and repulsive-location in the central district. Numéro de notice : A2022-257 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2021.1976409 Date de publication en ligne : 16/09/2021 En ligne : https://doi.org/10.1080/13658816.2021.1976409 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100230 [article]

Enriching the metadata of map images: a deep learning approach with GIS-based data augmentation / Yingjie Hu in International journal of geographical information science IJGIS, vol 36 n° 4 (April 2022)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 36 n° 4 (April 2022) . - pp 799 - 821 Titre : Enriching the metadata of map images: a deep learning approach with GIS-based data augmentation Type de document : Article/Communication Auteurs : Yingjie Hu, Auteur ; Zhipeng Gui, Auteur ; Jimin Wang, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 799 - 821 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web [Termes IGN] apprentissage profond [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] descripteur [Termes IGN] données d'entrainement sans étiquette [Termes IGN] image cartographique [Termes IGN] métadonnées [Termes IGN] projection [Termes IGN] système d'information géographique [Termes IGN] Web Map Service [Termes IGN] web mapping Résumé : (auteur) Maps in the form of digital images are widely available in geoportals, Web pages, and other data sources. The metadata of map images, such as spatial extents and place names, are critical for their indexing and searching. However, many map images have either mismatched metadata or no metadata at all. Recent developments in deep learning offer new possibilities for enriching the metadata of map images via image-based information extraction. One major challenge of using deep learning models is that they often require large amounts of training data that have to be manually labeled. To address this challenge, this paper presents a deep learning approach with GIS-based data augmentation that can automatically generate labeled training map images from shapefiles using GIS operations. We utilize such an approach to enrich the metadata of map images by adding spatial extents and place names extracted from map images. We evaluate this GIS-based data augmentation approach by using it to train multiple deep learning models and testing them on two different datasets: a Web Map Service image dataset at the continental scale and an online map image dataset at the state scale. We then discuss the advantages and limitations of the proposed approach. Numéro de notice : A2022-258 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : https://doi.org/10.1080/13658816.2021.1968407 En ligne : https://doi.org/10.1080/13658816.2021.1968407 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100231 [article]