Détail de l'auteur
Auteur Yu Liu |
Documents disponibles écrits par cet auteur (9)
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externesSpatial regression graph convolutional neural networks: A deep learning paradigm for spatial multivariate distributions / Di Zhu in Geoinformatica, vol 26 n° 4 (October 2022)
Titre : Spatial regression graph convolutional neural networks: A deep learning paradigm for spatial multivariate distributions Type de document : Article/Communication Auteurs : Di Zhu, Auteur ; Yu Liu, Auteur ; Xin Yao, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 645 - 676 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique
[Termes IGN] analyse multivariée
[Termes IGN] analyse spatiale
[Termes IGN] apprentissage profond
[Termes IGN] distribution spatiale
[Termes IGN] échantillonnage
[Termes IGN] intelligence artificielle
[Termes IGN] régression
[Termes IGN] régression géographiquement pondérée
[Termes IGN] réseau neuronal convolutif
[Termes IGN] réseau neuronal de graphesMots-clés libres : Geospatial artificial intelligence (GeoAI) Résumé : (auteur) Geospatial artificial intelligence (GeoAI) has emerged as a subfield of GIScience that uses artificial intelligence approaches and machine learning techniques for geographic knowledge discovery. The non-regularity of data structures has recently led to different variants of graph neural networks in the field of computer science, with graph convolutional neural networks being one of the most prominent that operate on non-euclidean structured data where the numbers of nodes connections vary and the nodes are unordered. These networks use graph convolution – commonly known as filters or kernels – in place of general matrix multiplication in at least one of their layers. This paper suggests spatial regression graph convolutional neural networks (SRGCNNs) as a deep learning paradigm that is capable of handling a wide range of geographical tasks where multivariate spatial data needs modeling and prediction. The feasibility of SRGCNNs lies in the feature propagation mechanisms, the spatial locality nature, and a semi-supervised training strategy. In the experiments, this paper demonstrates the operation of SRGCNNs with social media check-in data in Beijing and house price data in San Diego. The results indicate that a well-trained SRGCNN model is capable of learning from samples and performing reasonable predictions for unobserved locations. The paper also presents the effectiveness of incorporating the idea of geographically weighted regression for handling heterogeneity between locations in the model approach. Compared to conventional spatial regression approaches, SRGCNN-based models tend to generate much more accurate and stable results, especially when the sampling ratio is low. This study offers to bridge the methodological gap between graph deep learning and spatial regression analytics. The proposed idea serves as an example to illustrate how spatial analytics can be combined with state-of-the-art deep learning models, and to enlighten future research at the front of GeoAI. Numéro de notice : A2022-865 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/INFORMATIQUE Nature : Article DOI : 10.1007/s10707-021-00454-x Date de publication en ligne : 02/11/2021 En ligne : https://doi.org/10.1007/s10707-021-00454-x Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102158
in Geoinformatica > vol 26 n° 4 (October 2022) . - pp 645 - 676[article]
Titre : How urban places are visited by social groups? Evidence from matrix factorization on mobile phone data Type de document : Article/Communication Auteurs : Chaogui Kang, Auteur ; Li Shi, Auteur ; Fahui Wang, Auteur ; Yu Liu, Auteur Année de publication : 2020 Article en page(s) : pp 1504 - 1525 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale
[Termes IGN] Chine
[Termes IGN] contenu généré par les utilisateurs
[Termes IGN] données spatiotemporelles
[Termes IGN] ethnographie
[Termes IGN] factorisation de matrice non-négative
[Termes IGN] matrice de co-occurrence
[Termes IGN] production participative
[Termes IGN] réseau social
[Termes IGN] site urbain
[Termes IGN] téléphonie mobile
[Termes IGN] urbanismeRésumé : (Auteur) This research attempts to build a unified framework for distinguishing the spatiotemporal visit patterns of urban places by different social groups using mobile phone data in Harbin, China. Social groups are detected by their social ties in the ego‐to‐ego mobile phone call network and are embedded in physical space according to their home locations. Popular urban places are detected from user‐generated content as the basic spatial analysis unit. Coupling subscribers’ footprints and urban places in physical space, the spatiotemporal visit patterns of urban places by distinct social groups are uncovered and interpreted by non‐negative matrix factorization. The proposed framework enables us to answer several critical questions from three perspectives: (1) How to model popular urban places in terms of vague boundary, land use, and semantic features based on crowdsourcing data?; (2) How to evaluate interaction between individuals for inspecting the relationship between spatial proximity and social ties based on spatiotemporal co‐occurrence?; and (3) How to distinguish urban place visit preferences for social groups associated with different socio‐demographic characteristics? Our research could assist urban planners and municipal managers to identify critical urban places frequented by different population groups according to their roles and social/cultural characteristics for improvement of urban facility allocation. Numéro de notice : A2020-767 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/URBANISME Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12654 Date de publication en ligne : 30/06/2020 En ligne : https://doi.org/10.1111/tgis.12654 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96658
in Transactions in GIS > Vol 24 n° 6 (December 2020) . - pp 1504 - 1525[article]
Titre : A fuzzy formal concept analysis-based approach to uncovering spatial hierarchies among vague places extracted from user-generated data Type de document : Article/Communication Auteurs : Xiaoyu Wu, Auteur ; Jianying Wang, Auteur ; Li Shi, Auteur ; Yong Gao, Auteur ; Yu Liu, Auteur Année de publication : 2019 Article en page(s) : pp 991 - 1016 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale
[Termes IGN] contenu généré par les utilisateurs
[Termes IGN] incertitude géométrique
[Termes IGN] logique floue
[Termes IGN] processus de hiérarchisation analytique floueRésumé : (Auteur) The spatial hierarchy of part-whole relationships is an essential characteristic of the platial world. Constructing spatial hierarchies of places is valuable in association analysis and qualitative spatial reasoning. The emergence of large amounts of geotagged user-generated content provides strong support for modelling places. However, the vague nature of places and the complex spatial relationships among places make it intractable to understand and represent the hierarchies among places. In this paper, we introduce a fuzzy formal concept analysis-based approach to uncovering the spatial hierarchies among vague places. Each place is represented as a concept that consists of its extent and its intent. Based on the place concepts, the spatial hierarchies are generated and expressed as a graph that is easy to comprehend and contains abundant information on spatial relations. We also demonstrate the rationality of our result by comparing it with the result of a questionnaire survey. Numéro de notice : A2019-442 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2019.1566550 Date de publication en ligne : 22/01/2019 En ligne : https://doi.org/10.1080/13658816.2019.1566550 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92776
in International journal of geographical information science IJGIS > Vol 33 n° 5-6 (May - June 2019) . - pp 991 - 1016[article]Exemplaires(2)
Code-barres Cote Support Localisation Section Disponibilité 079-2019051 RAB Revue Centre de documentation En réserve L003 Disponible 079-2019052 RAB Revue Centre de documentation En réserve L003 Disponible
Titre : A generalized theory of the figure of the Earth : formulae Type de document : Article/Communication Auteurs : Chengli Huang, Auteur ; Yu Liu, Auteur ; Chenjun Liu, Auteur ; Mian Zhang, Auteur Année de publication : 2019 Article en page(s) : pp 297 - 317 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géodésie
[Termes IGN] croute terrestre
[Termes IGN] ellipticité (géométrie)
[Termes IGN] équation de Clairaut
[Termes IGN] figure de la Terre
[Termes IGN] surface de référenceRésumé : (Auteur) Traditionally a laterally homogeneous and spherical base Earth model (e.g., the PREM model) is considered as input when computing the Earth’s equipotential surfaces, which are then resulted to be in symmetric shape. However, the Earth, known with a complex distribution of interior material and density, especially in the upper mantle and the crust, cannot be treated as a symmetric sphere. Recently, a CRUST1.0 model of crust layer is published and well accepted. But the effect caused by the asymmetric crust (and mantle) on equilibrium figures of the Earth cannot be analyzed by the traditional theories. A generalized theory of the figure of the Earth to third-order precision is firstly proposed in this paper, as well as the iterative calculation strategy to solve the complex equation system. In order to validate this generalized theory, the degeneration of this generalized theory with the PREM model is made and is compared with traditional theories, and it is shown that the result of this generalized theory, after degeneration, is consistent very well with traditional theory. Meanwhile, the effect (including both the direct and indirect effects) of the crust layer, from the CRUST1.0 model, on the figures of equipotential surfaces of the Earth’s interior, as well as their effects on the global dynamics flattening, will be presented as an application of this theory in accompanying paper. Numéro de notice : A2019-150 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s00190-018-1159-6 Date de publication en ligne : 15/06/2018 En ligne : https://doi.org/10.1007/s00190-018-1159-6 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92488
in Journal of geodesy > vol 93 n° 3 (March 2019) . - pp 297 - 317[article]
Titre : A generalized theory of the figure of the Earth : on the global dynamical flattening Type de document : Article/Communication Auteurs : Chenjun Liu, Auteur ; Chengli Huang, Auteur ; Yu Liu, Auteur ; Mian Zhang, Auteur Année de publication : 2019 Article en page(s) : pp 319 - 331 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géodésie
[Termes IGN] aplatissement
[Termes IGN] croute terrestre
[Termes IGN] isostasie
[Termes IGN] manteau terrestre
[Termes IGN] moment d'inertie
[Termes IGN] noyau terrestre
[Termes IGN] rotation de la TerreRésumé : (Auteur) A generalized theory of the figures of the Earth’s interior to a third-order precision of ellipticity is proposed in accompanying paper in which all the odd degree and nonzero order spherical harmonic terms are included. As both the direct and indirect contributions of the asymmetric crust are included, this theory makes a significant improvement for calculating the asymmetric equilibrium figures of the real Earth comparing with the traditional theories which can only deal with the ideal symmetric Earth. The principal moments of inertia (PMOI: A, B, C) and global dynamical flattening (H) are important quantities in studying the rotating Earth. Precession and gravity observations give observation value of H (Hobs≈1/305.4559) with very high precision, while its theoretical calculated value (Htheory≈1/308.5) from traditional theories and a starting symmetric Earth model (like PREM model) is about 1% less than Hobs. Using the new theory in accompanying paper and replacing the homogeneous outermost crust and oceanic layers in PREM with CRUST1.0 model, we recalculate the equilibrium figures of the Earth’s interior and finally get new values of PMOI and Htheory (≈1/304.7167) whose consistency with Hobs are significantly improved to 0.24%. Furthermore, the asymmetric figures of some interesting boundaries, like inner core boundary, core-mantle boundary, are also given as by-products of this work as these boundaries’ figures are key input for studies of their topographic effect on global rotation and geodynamics, like nutation, normal modes, especially like free core nutation. Numéro de notice : A2019-151 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s00190-018-1163-x Date de publication en ligne : 22/06/2018 En ligne : https://doi.org/10.1007/s00190-018-1163-x Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92490
in Journal of geodesy > vol 93 n° 3 (March 2019) . - pp 319 - 331[article]vol 36 n°2 - March 2012 - Special Issue: Geoinformatics 2010 (Bulletin de Computers, Environment and Urban Systems) / Yu Liu
Permalink
