Centre dedocumentation
scientifique

MTMGNN: Multi-time multi-graph neural network for metro passenger flow prediction / Du Yin in Geoinformatica, vol 27 n° 1 (January 2023)  

Public [article]  inGeoinformatica > vol 27 n° 1 (January 2023) . - pp 77 - 105 Titre : MTMGNN: Multi-time multi-graph neural network for metro passenger flow prediction Type de document : Article/Communication Auteurs : Du Yin, Auteur ; Renhe Jiang, Auteur ; Jiewen Deng, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : pp 77 - 105 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] attention (apprentissage automatique) [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] déformation temporelle dynamique (algorithme) [Termes IGN] données multitemporelles [Termes IGN] données spatiotemporelles [Termes IGN] flux [Termes IGN] gestion de trafic [Termes IGN] origine - destination [Termes IGN] réseau neuronal de graphes [Termes IGN] système de transport intelligent [Termes IGN] trafic urbain [Termes IGN] transport public [Termes IGN] utilisateur Résumé : (auteur) The passenger flow prediction of the public metro system is a core and critical part of the intelligent transportation system, and is essential for traffic management, metro planning, and emergency safety measures. Most methods chose the recent segment from historical data as input to predict the future traffic flow; however, this would lead to the loss of the inherent characteristic information of the metro passenger flow’s daily morning and evening peak. Therefore, this study aggregates the recent-term and long-term information and use a long-term Gated Convolutional Neural Network (Gated CNN) to extract the temporal feature from the complex historical data. On the other hand, typical models did not consider the different spatial dependencies between different metro stations; this work proposes various adjacent relationships to characterize the degree of association between nodes. In order to extract spatial and temporal features at the same time, the historical data of recent-term and long-term is merged together to extract spatial features through a multi-graph neural network module. By combining Gated CNN and multi-graph module, we propose a multi-time multi-graph neural network named MTMGNN for metro passenger flow prediction. The result of our experiment on real-world datasets shows that our model MTMGNN is better than all state-of-art methods. Numéro de notice : A2023-113 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1007/s10707-022-00466-1 Date de publication en ligne : 25/04/2022 En ligne : https://doi.org/10.1007/s10707-022-00466-1 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102478 [article]

Predicting total electron content in ionosphere using vector autoregression model during geomagnetic storm / Sumitra Iyer in Journal of applied geodesy, vol 15 n° 4 (October 2021)  

Public [article]  inJournal of applied geodesy > vol 15 n° 4 (October 2021) . - pp 279 - 291 Titre : Predicting total electron content in ionosphere using vector autoregression model during geomagnetic storm Type de document : Article/Communication Auteurs : Sumitra Iyer, Auteur ; Alka Mahajan, Auteur Année de publication : 2021 Article en page(s) : pp 279 - 291 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géodésie spatiale [Termes IGN] auto-régression [Termes IGN] déformation temporelle dynamique (algorithme) [Termes IGN] format RINEX [Termes IGN] Inde [Termes IGN] modèle de simulation [Termes IGN] modèle ionosphérique [Termes IGN] série temporelle [Termes IGN] signal GPS [Termes IGN] tempête magnétique [Termes IGN] teneur totale en électrons [Termes IGN] teneur verticale totale en électrons Résumé : (auteur) The ionospheric total electron content (TEC) severely impacts the positional accuracy of a single frequency Global Positioning System (GPS) receiver at the equatorial latitudes. The ionosphere causes a frequency-dependent group delay in the GPS-ranging signals, which reduces the receiver’s accuracy. Further, the variations in TEC due to various space weather phenomena make the ionosphere’s behaviour nonhomogeneous and complex. Hence, developing an accurate forecast model that can track the dynamic behaviour of the ionosphere remains a challenge. However, advances in emerging data-driven algorithms have been found helpful in tracking non-stationary behavior in TEC. These models help forecast the delays in advance. The multivariate Vector Autoregression model (VAR) predicts the Ionospheric TEC in the proposed model. The prediction model uses input data compiled in real-time from the lag values of incoming TEC data and features extracted from TEC. The TEC is predicted in real-time and tested for different prediction intervals. The metrics – Mean Percentage Error (MAPE), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE) are used for testing and validating the accuracy of the model statistically. Testing the predicted output accuracy is also done with the dynamic time warping (DTW) algorithm by comparing it with the actual value obtained from the dual-frequency receiver. The model is tested for storm days of the year 2015 for Bangalore and Hyderabad stations and found to be reliable and accurate. A prediction interval of twenty-minute shows the highest accuracy with an error within 10 TECU for all the storm days. Numéro de notice : A2021-745 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article DOI : 10.1515/jag-2021-0015 Date de publication en ligne : 23/06/2021 En ligne : https://doi.org/10.1515/jag-2021-0015 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98717 [article]

Artificial neural networks in agriculture / Sebastian Kujawa (2021)  

Public Titre : Artificial neural networks in agriculture Type de document : Monographie Auteurs : Sebastian Kujawa, Éditeur scientifique ; Gniewko Niedbała, Éditeur scientifique Editeur : Bâle [Suisse] : Multidisciplinary Digital Publishing Institute MDPI Année de publication : 2021 Importance : 283 p. Format : 16 x 23 cm ISBN/ISSN/EAN : 978-3-0365-1579-3 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] agriculture [Termes IGN] apprentissage profond [Termes IGN] carte de la végétation [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] classification par réseau neuronal récurrent [Termes IGN] couvert végétal [Termes IGN] déformation temporelle dynamique (algorithme) [Termes IGN] détection d'arbres [Termes IGN] Google Earth [Termes IGN] image à haute résolution [Termes IGN] phénologie [Termes IGN] réseau neuronal artificiel [Termes IGN] surveillance agricole Résumé : (éditeur) Modern agriculture needs to have high production efficiency combined with a high quality of obtained products. This applies to both crop and livestock production. To meet these requirements, advanced methods of data analysis are more and more frequently used, including those derived from artificial intelligence methods. Artificial neural networks (ANNs) are one of the most popular tools of this kind. They are widely used in solving various classification and prediction tasks, for some time also in the broadly defined field of agriculture. They can form part of precision farming and decision support systems. Artificial neural networks can replace the classical methods of modelling many issues, and are one of the main alternatives to classical mathematical models. The spectrum of applications of artificial neural networks is very wide. For a long time now, researchers from all over the world have been using these tools to support agricultural production, making it more efficient and providing the highest-quality products possible. Note de contenu : 1- Plant and weed identifier robot as an agroecological tool using artificial neural networks for image identification 2- Oil palm tree detection and health classification on high-resolution imagery using deep learning 3- Average degree of coverage and coverage unevenness coefficient as parameters for spraying quality assessment 4- The relationship between soil electrical parameters and compaction of Sandy Clay Loam soil 5- Evaluation of convolutional neural networks’ hyperparameters with transfer learning to determine sorting of Ripe Medjool dates 6- Mapping paddy rice using weakly supervised long short-term memory network with time series sentinel optical and SAR images 7- Time series prediction with artificial neural networks: An analysis using Brazilian soybean production 8- Machine learning for plant breeding and biotechnology 9- A hybrid CFS filter and RF-RFE wrapper-based feature extraction for enhanced agricultural crop yield prediction modeling 10- Crop growth stage GPP-driven spectral model for evaluation of cultivated land quality using GA-BPNN 11- Corn grain yield estimation from vegetation indices, canopy cover, plant density, and a neural network using multispectral and RGB images acquired with unmanned aerial vehicles 12- Modeling the dynamic response of plant growth to root zone temperature in hydroponic Chili pepper plant using neural networks 13- ANN-based continual classification in agriculture 14- Application of artificial neural networks to analyze the concentration of ferulic acid, deoxynivalenol, and nivalenol in winter wheat grain 15- Neural visual detection of grain weevil (sitophilus granarius L.) Numéro de notice : 28624 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE/INFORMATIQUE Nature : Recueil / ouvrage collectif DOI : 10.3390/books978-3-0365-1579-3 En ligne : https://doi.org/10.3390/books978-3-0365-1579-3 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99553

Ensemble learning methods on the space of covariance matrices : application to remote sensing scene and multivariate time series classification / Sara Akodad (2021)  

Public Titre : Ensemble learning methods on the space of covariance matrices : application to remote sensing scene and multivariate time series classification Type de document : Thèse/HDR Auteurs : Sara Akodad, Auteur ; Christian Germain, Directeur de thèse ; Lionel Bombrun, Directeur de thèse Editeur : Bordeaux : Université de Bordeaux Année de publication : 2021 Importance : 220 p. Format : 21 x 30 cm Note générale : bibliographie Thèse présentée pour obtenir le grade de Docteur de l'Université de Bordeaux, Spécialité Automatique, Productique, Signal et Image, Ingénierie cognitique Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte [Termes IGN] analyse multivariée [Termes IGN] Castanea sativa [Termes IGN] classification dirigée [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] déformation temporelle dynamique (algorithme) [Termes IGN] géométrie euclidienne [Termes IGN] image Sentinel-MSI [Termes IGN] image Sentinel-SAR [Termes IGN] maladie phytosanitaire [Termes IGN] matrice de covariance [Termes IGN] processus gaussien [Termes IGN] série temporelle [Termes IGN] surveillance forestière Résumé : (auteur) In view of the growing success of second-order statistics in classification problems, the work of this thesis has been oriented towards the development of learning methods in manifolds. Indeed, covariance matrices are symmetric positive definite matrices that live in a non-Euclidean space. It is therefore necessary to adapt the classical tools of Euclidean geometry to handle this type of data. To do that, we have proposed to exploit the log-Euclidean metric. This latter allows to project the set of covariance matrices on a tangent plane to the manifold defined at a reference point, classically chosen equal to the identity matrix, followed by a vectorization step to obtain the log-Euclidean representation. On this tangent plane, it is possible to define parametric Gaussian models as well as Gaussian mixture models. Nevertheless, this projection on a single tangent plane can induce distortions. In order to overcome this limitation, we have proposed a GMM model composed of several tangent planes, where the reference points are defined by the centers of each cluster.In view of the success of neural networks, in particular convolutional neural networks (CNNs), we have proposed two hybrid transfer learning approaches based on the covariance matrix computed locally and globally on the CNN convolutional layers’ outputs. The local approach relies on the covariance matrices extracted locally on the first layers of a CNN, which are then encoded by the Fisher vectors computed on their log-Euclidean representation, while for the global approach, a single covariance matrix is computed on the feature maps of the CNN deep layers. Moreover, in order to give more importance to the objects of interest present in the images, we proposed to use a covariance matrix weighted by the saliency information. Furthermore, in order to take advantage of both local and global aspects, these two approaches are subsequently combined in an ensemble strategy.On the other hand, the availability of multivariate time series has aroused the interest of the remote sensing community and more generally of machine learning researchers for the development of new learning strategies dedicated to supervised classification. In particular, methods based on the calculation of point-to-point distance between series. Moreover, two series belonging to the same class can evolve in different ways, which can induce temporal distortions (translation, compression, dilation, etc.). To avoid this, warping methods allow to align the time series. In order to extend this approach to time series of covariance matrices, while ensuring invariance to the re-parametrization of the series, we were interested in the TSRVF representation. In the same context, several ensemble methods have been proposed in the literature, including TCK, which relies on similarity computation to classify time series. We have proposed to extend this strategy to covariance matrices by introducing the SO-TCK approach which relies on the log-Euclidean representation of such matrices. Finally, the last axis of this thesis concerns the modeling of temporal trajectories of signals measured by the radar (Sentinel 1) and optical (Sentinel 2) sensors. In particular, we are interested in the forestry problem of the chestnut ink disease in the Montmorency forest. For this purpose, we developed classification and regression models to predict a health status score from the covariance matrix computed on multi-temporal radiometric attributes. Note de contenu : Introduction 1- Riemannian geometry and statistical modeling on the space of Symmetric Positive Definite (SPD) matrices 2- Ensemble learning approaches based on covariance pooling of CNN Features 3- Symmetric positive definite matrix time series classification 4- Forest health monitoring using Sentinel-1 and Sentinel-2 time series Conclusions and perspectives Numéro de notice : 28605 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE/MATHEMATIQUE Nature : Thèse française Note de thèse : Thèse de Doctorat : Automatique, Productique, Signal et Image, Ingénierie cognitique : Bordeaux : 2021 Organisme de stage : IMS DOI : sans En ligne : https://tel.archives-ouvertes.fr/tel-03484011 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99446

A global analysis of cities’ geosocial temporal signatures for points of interest hours of operation / Kevin Sparks in International journal of geographical information science IJGIS, vol 34 n° 4 (April 2020)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 34 n° 4 (April 2020) . - pp 759 - 776 Titre : A global analysis of cities’ geosocial temporal signatures for points of interest hours of operation Type de document : Article/Communication Auteurs : Kevin Sparks, Auteur ; Gautam Thakur, Auteur ; Amol Pasarkar, Auteur ; Marie Urban, Auteur Année de publication : 2020 Article en page(s) : pp 759 - 776 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] analyse comparative [Termes IGN] analyse spatio-temporelle [Termes IGN] climat urbain [Termes IGN] contenu généré par les utilisateurs [Termes IGN] coutume [Termes IGN] déformation temporelle dynamique (algorithme) [Termes IGN] démographie [Termes IGN] données géophysiques [Termes IGN] données issues des réseaux sociaux [Termes IGN] estimation quantitative [Termes IGN] ethnologie [Termes IGN] géographie sociale [Termes IGN] gestion urbaine [Termes IGN] milieu urbain [Termes IGN] modèle dynamique [Termes IGN] modélisation spatio-temporelle [Termes IGN] point d'intérêt [Termes IGN] réseau social [Termes IGN] trace numérique Résumé : (auteur) The temporal nature of humans interaction with Points of Interest (POIs) in cities can differ depending on place type and regional location. Times when many people are likely to visit restaurants (place type) in Italy, may differ from times when many people are likely to visit restaurants in Lebanon (i.e. regional differences). Geosocial data are a powerful resource to model these temporal differences in cities, as traditional methods used to study cross-cultural differences do not scale to a global level. As cities continue to grow in population and economic development, research identifying the social and geophysical (e.g., climate) factors that influence city function remains important and incomplete. In this work, we take a quantitative approach, applying dynamic time warping and hierarchical clustering on temporal signatures to model geosocial temporal patterns for Retail and Restaurant Facebook POIs hours of operation for more than 100 cities in 90 countries around the world. Results show cities’ temporal patterns cluster to reflect the cultural region they represent. Furthermore, temporal patterns are influenced by a mix of social and geophysical factors. Trends in the data suggest social factors influence unique drops in temporal signatures, and geophysical factors influence when daily temporal patterns start and finish. Numéro de notice : A2020-294 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/URBANISME Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2019.1615069 Date de publication en ligne : 04/06/2019 En ligne : https://doi.org/10.1080/13658816.2019.1615069 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95126 [article]

Satellite image time series analysis under time warping / F. Petitjean in IEEE Transactions on geoscience and remote sensing, vol 50 n° 8 (August 2012)  

Permalink