Descripteur
Termes IGN > mathématiques > statistique mathématique
statistique mathématique
Commentaire :
>>
biométrie,
échantillonnage (statistique), probabilité, statistique. >>Terme(s) spécifique(s) : analyse de régression, analyse de variance, analyse des données, analyse multivariée, analyse séquentielle, calcul d'erreur, carré latin, corrélation (statistique), efficacité asymptotique (statistique), fonction pseudo-aléatoire, loi des grands nombres, modèle linéaire (statistique), modèle non linéaire (statistique), moindre carré, physique statistique, plan d'expérience, rang et sélection (statistique), rupture (statistique), SAS (logiciel), série chronologique, statistique non paramétrique, statistique robuste, tableau de contingence, test d'hypothèses (statistique), statistique stellaire. Equiv. LCSH : Mathematical statistics. Domaine(s) : 510. |
Documents disponibles dans cette catégorie (6560)
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externes
Etendre la recherche sur niveau(x) vers le bas
Investigation of recognition and classification of forest fires based on fusion color and textural features of images / Cong Li in Forests, vol 13 n° 10 (October 2022)
[article]
Titre : Investigation of recognition and classification of forest fires based on fusion color and textural features of images Type de document : Article/Communication Auteurs : Cong Li, Auteur ; Qiang Liu, Auteur ; Binrui Li, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 1719 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] analyse texturale
[Termes IGN] base de données d'images
[Termes IGN] classification par séparateurs à vaste marge
[Termes IGN] extraction de traits caractéristiques
[Termes IGN] image RVB
[Termes IGN] incendie de forêt
[Termes IGN] matrice de co-occurrence
[Termes IGN] motif binaire local
[Termes IGN] niveau de gris (image)Résumé : (auteur) An image recognition and classification method based on fusion color and textural features was studied. Firstly, the suspected forest fire region was segmented via the fusion RGB-YCbCr color spaces. Then, 10 kinds of textural features were extracted by a local binary pattern (LBP) algorithm and 4 kinds of textural features were extracted by a gray-level co-occurrence matrix (GLCM) algorithm from the suspected fire region. In terms of its application, a database of the forest fire textural feature vector of three scenes was constructed, including forest images without fire, forest images with fire, and forest images with fire-like interference. The existence of forest fires can be recognized based on the database via a support vector machine (SVM). The results showed that the method’s recognition rate for forest fires reached 93.15% and that it had a strong robustness with respect to distinguishing fire-like interference, which provides a more effective scheme for forest fire recognition. Numéro de notice : A2022-834 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.3390/f13101719 Date de publication en ligne : 18/10/2022 En ligne : https://doi.org/10.3390/f13101719 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102030
in Forests > vol 13 n° 10 (October 2022) . - n° 1719[article]Machine learning and natural language processing of social media data for event detection in smart cities / Andrei Hodorog in Sustainable Cities and Society, vol 85 (October 2022)
[article]
Titre : Machine learning and natural language processing of social media data for event detection in smart cities Type de document : Article/Communication Auteurs : Andrei Hodorog, Auteur ; Ioan Petri, Auteur ; yacine Rezgui, Auteur Année de publication : 2022 Article en page(s) : n° 104026 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web
[Termes IGN] apprentissage automatique
[Termes IGN] classification bayesienne
[Termes IGN] détection d'événement
[Termes IGN] données issues des réseaux sociaux
[Termes IGN] outil d'aide à la décision
[Termes IGN] régression multiple
[Termes IGN] taxinomie
[Termes IGN] traitement du langage naturel
[Termes IGN] ville intelligenteRésumé : (auteur) Social media data analysis in a smart city context can represent an efficacious instrument to inform decision making. The manuscript strives to leverage the power of Natural Language Processing (NLP) techniques applied to Twitter messages using supervised learning to achieve real-time automated event detection in smart cities. A semantic-based taxonomy of risks is devised to discover and analyse associated events from data streams, with a view to: (i) read and process, in real-time, published texts (ii) classify each text into one representative real-world category (iii) assign a citizen satisfaction value to each event. To select the language processing models striking the best balance between accuracy and processing speed, we conducted a pre-emptive evaluation, comparing several baseline language models formerly employed by researchers for event classification. A heuristic analysis of several smart cities and community initiatives was conducted, with a view to define real-world scenarios as basis for determining correlations between two or more co-occurring event types and their associated levels of citizen satisfaction, while further considering environmental factors. Based on Multiple Regression Analysis (MRA), we established the relationships between scenario variables, obtaining a variance of 60%–90% between the dependent and independent variables. The selected combination of supervised NLP techniques leverages an accuracy of 88.5%. We found that all regression models had at least one variable below the 0.05 threshold of the , therefore at least one statistically significant independent variable. These findings ultimately illustrate how citizens, taking the role of active social sensors, can yield vital data that authorities can use to make educated decisions and sustainably construct smarter cities. Numéro de notice : A2022-764 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1016/j.scs.2022.104026 Date de publication en ligne : 02/07/2022 En ligne : https://doi.org/10.1016/j.scs.2022.104026 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101785
in Sustainable Cities and Society > vol 85 (October 2022) . - n° 104026[article]Modelling and prediction of GNSS time series using GBDT, LSTM and SVM machine learning approaches / Wenzong Gao in Journal of geodesy, vol 96 n° 10 (October 2022)
[article]
Titre : Modelling and prediction of GNSS time series using GBDT, LSTM and SVM machine learning approaches Type de document : Article/Communication Auteurs : Wenzong Gao, Auteur ; Zhao Li, Auteur ; Qusen Chen, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 71 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] classification par réseau neuronal récurrent
[Termes IGN] classification par séparateurs à vaste marge
[Termes IGN] déformation de la croute terrestre
[Termes IGN] données GNSS
[Termes IGN] Extreme Gradient Machine
[Termes IGN] modèle de simulation
[Termes IGN] série temporelle
[Vedettes matières IGN] Traitement de données GNSSRésumé : (auteur) Global navigation satellite system (GNSS) site coordinate time series provides essential data for geodynamic and geophysical studies, realisation of a regional or global geodetic reference frames, and crustal deformation research. The coordinate time series has been conventionally modelled by least squares (LS) fitting with harmonic functions, alongside many other analysis methods. As a key limitation, the traditional modelling approaches simply use the functions of time variable, despite good knowledge of various underlying physical mechanisms responsible for the site displacements. This paper examines the use of machine learning (ML) models to reflect the effects or residential effects of physical variables related to Sun and the Moon ephemerides, polar motion, temperature, atmospheric pressure, and hydrology on the site displacements. To form the ML problem, these variables are constructed as the input vector of each ML training sample, while the vertical displacement of a GNSS site is regarded as the output value. In the evaluation experiments, three ML approaches, namely the gradient boosting decision tree (GBDT) approach, long short-term memory (LSTM) approach, and support vector machine (SVM) approach, are introduced and evaluated with the time series datasets collected from 9 GNSS sites over the period of 13 years. The results indicate that all three approaches achieve similar fitting precision in the range of 3–5 mm in the vertical displacement component, which is an improvement in over 30% with respect to the traditional LS fitting precision in the range of 4–7 mm. The prediction of the vertical time series with the three ML approaches shows the precision in the range of 4–7 mm over the future 24- month period. The results also indicate the relative importance of different physical features causing the displacements of each site. Overall, ML approaches demonstrate better performance and effectiveness in modelling and prediction of GNSS time series, thus impacting maintenance of geodetic reference frames, geodynamics, geophysics, and crustal deformation analysis. Numéro de notice : A2022-737 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s00190-022-01662-5 Date de publication en ligne : 27/09/2022 En ligne : https://doi.org/10.1007/s00190-022-01662-5 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101709
in Journal of geodesy > vol 96 n° 10 (October 2022) . - n° 71[article]Monitoring spatiotemporal soil moisture changes in the subsurface of forest sites using electrical resistivity tomography (ERT) / Julian Fäth in Journal of Forestry Research, vol 33 n° 5 (October 2022)
[article]
Titre : Monitoring spatiotemporal soil moisture changes in the subsurface of forest sites using electrical resistivity tomography (ERT) Type de document : Article/Communication Auteurs : Julian Fäth, Auteur ; Julius Kunz, Auteur ; Christof Kneisel, Auteur Année de publication : 2022 Article en page(s) : pp 1649 - 1662 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] Bavière (Allemagne)
[Termes IGN] changement climatique
[Termes IGN] détection de changement
[Termes IGN] données spatiotemporelles
[Termes IGN] écologie forestière
[Termes IGN] forêt tempérée
[Termes IGN] humidité du sol
[Termes IGN] résistivité
[Termes IGN] sécheresse
[Termes IGN] série temporelle
[Termes IGN] tomographie
[Termes IGN] variation saisonnièreRésumé : (auteur) The effects of drought on tree mortality at forest stands are not completely understood. For assessing their water supply, knowledge of the small-scale distribution of soil moisture as well as its temporal changes is a key issue in an era of climate change. However, traditional methods like taking soil samples or installing data loggers solely collect parameters of a single point or of a small soil volume. Electrical resistivity tomography (ERT) is a suitable method for monitoring soil moisture changes and has rarely been used in forests. This method was applied at two forest sites in Bavaria, Germany to obtain high-resolution data of temporal soil moisture variations. Geoelectrical measurements (2D and 3D) were conducted at both sites over several years (2015–2018/2020) and compared with soil moisture data (matric potential or volumetric water content) for the monitoring plots. The greatest variations in resistivity values that highly correlate with soil moisture data were found in the main rooting zone. Using the ERT data, temporal trends could be tracked in several dimensions, such as the interannual increase in the depth of influence from drought events and their duration, as well as rising resistivity values going along with decreasing soil moisture. The results reveal that resistivity changes are a good proxy for seasonal and interannual soil moisture variations. Therefore, 2D- and 3D-ERT are recommended as comparatively non-laborious methods for small-spatial scale monitoring of soil moisture changes in the main rooting zone and the underlying subsurface of forested sites. Higher spatial and temporal resolution allows a better understanding of the water supply for trees, especially in times of drought. Numéro de notice : A2022-778 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.1007/s11676-022-01498-x Date de publication en ligne : 18/06/2022 En ligne : https://doi.org/10.1007/s11676-022-01498-x Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101838
in Journal of Forestry Research > vol 33 n° 5 (October 2022) . - pp 1649 - 1662[article]Multi‑constellation GNSS interferometric reflectometry for the correction of long-term snow height retrieval on sloping topography / Wei Zhou in GPS solutions, vol 26 n° 4 (October 2022)
[article]
Titre : Multi‑constellation GNSS interferometric reflectometry for the correction of long-term snow height retrieval on sloping topography Type de document : Article/Communication Auteurs : Wei Zhou, Auteur ; Liangke Huang, Auteur ; Bing Ji, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 140 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] hauteur (coordonnée)
[Termes IGN] manteau neigeux
[Termes IGN] pente
[Termes IGN] Ransac (algorithme)
[Termes IGN] rapport signal sur bruit
[Termes IGN] réflectométrie par GNSS
[Termes IGN] signal GNSS
[Termes IGN] système de référence altimétrique
[Termes IGN] topographie locale
[Termes IGN] transformation en ondelettes
[Termes IGN] valeur aberrante
[Vedettes matières IGN] AltimétrieRésumé : (auteur) Snow is a key parameter for global climate and hydrological systems. Global Navigation Satellite System interferometric reflectometry (GNSS-IR) has been applied to accurately monitor snow height (SH) with low cost and high temporal–spatial resolution. We proposed an improved GNSS-IR method using detrended signal-to-noise ratio (δSNR) arcs corresponding to multipath reflection tracks with different azimuths. After using wavelet decomposition and random sample consensus, noise with various frequencies for SNR arcs and outliers of reflector height (RH) estimations have been sequentially mitigated to enhance the availability of the proposed method. Thus, a height datum based on the ground RHs retrieved from multi-GNSS SNR data is established to compensate for the influence of topography variation with different azimuths in SH retrieval. The approximately 3-month δSNR datasets collected from three stations deployed on sloping topography were used to retrieve SH and compared with the existing method and in situ measurements. The results show that the root mean square errors of the retrievals derived from the proposed method for the three sites are between 4 and 8 cm, and the corresponding correlation surpasses 0.95 when compared to the reference SH datasets. Additionally, we compare the performance of a retrieval with the existing GNSS-IR Web App, and it shows an improvement in RMSE of about 7 cm. Furthermore, because topography variation has been considered, the average correction of SH retrievals is between 2 and 4 cm. The solution with the proposed method helps develop the applications of the GNSS-IR technique on complex topography. Numéro de notice : A2022-712 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article DOI : 10.1007/s10291-022-01333-0 Date de publication en ligne : 15/09/2022 En ligne : https://doi.org/10.1007/s10291-022-01333-0 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101590
in GPS solutions > vol 26 n° 4 (October 2022) . - n° 140[article]Multisource forest inventories: A model-based approach using k-NN to reconcile forest attributes statistics and map products / Ankit Sagar in ISPRS Journal of photogrammetry and remote sensing, vol 192 (October 2022)PermalinkNovel algorithm based on geometric characteristics for tree branch skeleton extraction from LiDAR point cloud / Jie Yang in Forests, vol 13 n° 10 (October 2022)PermalinkA relation-augmented embedded graph attention network for remote sensing object detection / Shu Tian in IEEE Transactions on geoscience and remote sensing, vol 60 n° 10 (October 2022)PermalinkSemi-supervised adversarial recognition of refined window structures for inverse procedural façade modelling / Han Hu in ISPRS Journal of photogrammetry and remote sensing, vol 192 (October 2022)PermalinkSingle-image super-resolution for remote sensing images using a deep generative adversarial network with local and global attention mechanisms / Yadong Li in IEEE Transactions on geoscience and remote sensing, vol 60 n° 10 (October 2022)PermalinkSpatial regression graph convolutional neural networks: A deep learning paradigm for spatial multivariate distributions / Di Zhu in Geoinformatica, vol 26 n° 4 (October 2022)PermalinkSpatio-temporal graph convolutional networks for road network inundation status prediction during urban flooding / Faxi Yuan in Computers, Environment and Urban Systems, vol 97 (October 2022)PermalinkThe fractional vegetation cover (FVC) and associated driving factors of modeling in mining areas / Jun Li in Photogrammetric Engineering & Remote Sensing, PERS, vol 88 n° 10 (October 2022)PermalinkThe iterative convolution–thresholding method (ICTM) for image segmentation / Dong Wang in Pattern recognition, vol 130 (October 2022)PermalinkA comparative assessment of modeling groundwater vulnerability using DRASTIC method from GIS and a novel classification method using machine learning classifiers / Qasim Khan in Geocarto international, vol 37 n° 20 ([20/09/2022])Permalink