Centre dedocumentation
scientifique

Probabilistic positioning in mobile phone network and its consequences for the privacy of mobility data / Aleksey Ogulenko in Computers, Environment and Urban Systems, vol 85 (January 2021)  

Public [article]  inComputers, Environment and Urban Systems > vol 85 (January 2021) . - n° 101550 Titre : Probabilistic positioning in mobile phone network and its consequences for the privacy of mobility data Type de document : Article/Communication Auteurs : Aleksey Ogulenko, Auteur ; Itzhak Benenson, Auteur ; Itzhak Omer, Auteur Année de publication : 2021 Article en page(s) : n° 101550 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes descripteurs IGN] antenne [Termes descripteurs IGN] classification bayesienne [Termes descripteurs IGN] confidentialité [Termes descripteurs IGN] diagramme de Voronoï [Termes descripteurs IGN] estimation bayesienne [Termes descripteurs IGN] inférence [Termes descripteurs IGN] protection de la vie privée [Termes descripteurs IGN] réseau téléphonique [Termes descripteurs IGN] téléphonie mobile [Termes descripteurs IGN] tessellation Résumé : (auteur) The traditional approach to mobile phone positioning is based on the assumption that the geographical location of a cell tower recorded in a Call Details Record (CDR) is a proxy for a device's location. A Voronoi tessellation is then constructed based on the entire network of cell towers and this tessellation is considered as a coordinate system, with the device located in a Voronoi polygon of a cell tower that is recorded in the CDR. If Voronoi-based positioning is correct, the uniqueness of the device trajectory is very high, and the device can be identified based on 3–5 of its recorded locations. We investigate a probabilistic approach to device positioning that is based on knowledge of each antennas' parameters and number of connections, as dependent on the distance to the antenna. The critical difference between the Voronoi-based and the real world layout is in the essential overlap of the antennas' service areas: The device that is located in a cell tower's polygon can be served by a more distant antenna that is chosen by the network system to balance the network load. Combining data on the distance distribution of the number of connections available for each antenna in the network, we resolve the overlap problem by applying Bayesian inference and construct a realistic distribution of the device location. Probabilistic device positioning demands a full revision of mobile phone privacy and new full set of tools for data analysis. Numéro de notice : A2021-005 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/MATHEMATIQUE Nature : Article DOI : 10.1016/j.compenvurbsys.2020.101550 date de publication en ligne : 14/10/2020 En ligne : https://doi.org/10.1016/j.compenvurbsys.2020.101550 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96272 [article]

Bayesian-deep-learning estimation of earthquake location from single-station observations / S. Mostafa Mousavi in IEEE Transactions on geoscience and remote sensing, vol 58 n° 11 (November 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 58 n° 11 (November 2020) . - pp 8211 - 8224 Titre : Bayesian-deep-learning estimation of earthquake location from single-station observations Type de document : Article/Communication Auteurs : S. Mostafa Mousavi, Auteur ; Gregory C. Beroza, Auteur Année de publication : 2020 Article en page(s) : pp 8211 - 8224 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement du signal [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] classification bayesienne [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] détection du signal [Termes descripteurs IGN] épicentre [Termes descripteurs IGN] estimation bayesienne [Termes descripteurs IGN] onde sismique [Termes descripteurs IGN] régression [Termes descripteurs IGN] séisme [Termes descripteurs IGN] station d'observation [Termes descripteurs IGN] surveillance géologique [Termes descripteurs IGN] temps de propagation Résumé : (auteur) We present a deep-learning method for a single-station earthquake location, which we approach as a regression problem using two separate Bayesian neural networks. We use a multitask temporal convolutional neural network to learn epicentral distance and P travel time from 1-min seismograms. The network estimates epicentral distance and P travel time with mean errors of 0.23 km and 0.03 s and standard deviations of 5.42 km and 0.66 s, respectively, along with their epistemic and aleatory uncertainties. We design a separate multi-input network using standard convolutional layers to estimate the back-azimuth angle and its epistemic uncertainty. This network estimates the direction from which seismic waves arrive at the station with a mean error of 1°. Using this information, we estimate the epicenter, origin time, and depth along with their confidence intervals. We use a global data set of earthquake signals recorded within 1° (~112 km) from the event to build the model and demonstrate its performance. Our model can predict epicenter, origin time, and depth with mean errors of 7.3 km, 0.4 s, and 6.7 km, respectively, at different locations around the world. Our approach can be used for fast earthquake source characterization with a limited number of observations and also for estimating the location of earthquakes that are sparsely recorded—either because they are small or because stations are widely separated. Numéro de notice : A2020-684 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.2988770 date de publication en ligne : 06/05/2020 En ligne : https://doi.org/10.1109/TGRS.2020.2988770 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96209 [article]

Object-based classification of mixed forest types in Mongolia / E. Nyamjargal in Geocarto international, vol 35 n° 14 ([15/10/2020])  

Public [article]  inGeocarto international > vol 35 n° 14 [15/10/2020] . - pp 1615 - 1626 Titre : Object-based classification of mixed forest types in Mongolia Type de document : Article/Communication Auteurs : E. Nyamjargal, Auteur ; D. Amarsaikhan, Auteur ; A. Munkh-Erdene, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 1615 - 1626 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] analyse d'image orientée objet [Termes descripteurs IGN] approche hiérarchique [Termes descripteurs IGN] approche pixel [Termes descripteurs IGN] carte forestière [Termes descripteurs IGN] classification bayesienne [Termes descripteurs IGN] classification orientée objet [Termes descripteurs IGN] forêt [Termes descripteurs IGN] image multibande [Termes descripteurs IGN] image multitemporelle [Termes descripteurs IGN] image Sentinel-MSI [Termes descripteurs IGN] méthode du maximum de vraisemblance (estimation) [Termes descripteurs IGN] Mongolie [Termes descripteurs IGN] peuplement mélangé Résumé : (auteur) The aim of this study is to produce updated forest map of the Bogdkhan Mountain, Mongolia using multitemporal Sentinel-2A images. The target area has highly mixed forest types and it is very difficult to differentiate the fuzzy boundaries among different forest types. To extract the forest class information, an object-based classification technique is applied and a rule-base to separate the mixed classes is developed. The rule-base uses a hierarchy of rules describing different conditions under which the actual classification has to be performed. To compare the result of the developed method with a result of a pixel-based approach, a Bayesian maximum likelihood classification is applied. The final result indicates overall accuracy of 90.87% for the object-based classification, while for the pixel-based approach it is 79.89%. Overall, the research indicates that the object-based method that uses a thoroughly defined segmentation and a well-constructed rule-base can significantly improve the classification of mixed forest types and produce of a reliable forest map. Numéro de notice : A2020-619 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2019.1583775 date de publication en ligne : 10/06/2019 En ligne : https://doi.org/10.1080/10106049.2019.1583775 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95995 [article]

Near-real time forecasting and change detection for an open ecosystem with complex natural dynamics / Jasper A. Slingsby in ISPRS Journal of photogrammetry and remote sensing, vol 166 (August 2020)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 166 (August 2020) . - pp 15 - 25 Titre : Near-real time forecasting and change detection for an open ecosystem with complex natural dynamics Type de document : Article/Communication Auteurs : Jasper A. Slingsby, Auteur ; Glenn R. Moncrieff, Auteur ; Adam M. Wilson, Auteur Année de publication : 2020 Article en page(s) : pp 15 - 25 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes descripteurs IGN] approche hiérarchique [Termes descripteurs IGN] biodiversité [Termes descripteurs IGN] classification bayesienne [Termes descripteurs IGN] détection de changement [Termes descripteurs IGN] écosystème [Termes descripteurs IGN] incendie [Termes descripteurs IGN] internet interactif [Termes descripteurs IGN] Le Cap [Termes descripteurs IGN] milieu naturel [Termes descripteurs IGN] modèle dynamique [Termes descripteurs IGN] Normalized Difference Vegetation Index [Termes descripteurs IGN] surveillance de la végétation [Termes descripteurs IGN] surveillance écologique Résumé : (auteur) Managing fire, water, biodiversity and carbon stocks can greatly benefit from early warning of changes in the state of vegetation. While near-real time tools to detect forest change based on satellite remote sensing exist, these ecosystems have relatively stable natural vegetation dynamics. Open (i.e. non-forest) ecosystems like grasslands, savannas and shrublands are more challenging as they show complex natural dynamics due to factors such as fire, postfire recovery, greater contribution of bare soil to observed vegetation indices, as well as high sensitivity to rainfall and strong seasonality. Tools to aid the management of open ecosystems are desperately required as they dominate much of the globe and harbour substantial biodiversity and carbon. We present an innovative approach that overcomes the difficulties posed by open ecosystems by using a spatio-temporal hierarchical Bayesian model that uses data on climate, topography, soils and fire history to generate ecological forecasts of the expected land surface signal under natural conditions. This allows us to monitor and detect abrupt or gradual changes in the state of an ecosystem in near-real time by identifying areas where the observed vegetation signal has deviated from the expected natural variation. We apply our approach to a case study from the hyperdiverse fire-dependent African shrubland, the fynbos of the Cape Floristic Region, a Global Biodiversity Hotspot and UNESCO World Heritage Site that faces a number of threats to vegetation health and ecosystem function. The case study demonstrates that our approach is useful for identifying a range of change agents such as fire, alien plant species invasions, drought, pathogen outbreaks and clearing of vegetation. We describe and provide our full workflow, including an interactive web application. Our approach is highly versatile, allowing us to collect data on the impacts of change agents for research in ecology and earth system science, and to predict aspects of ecosystem structure and function such as biomass, fire return interval and the influence of vegetation on hydrology Numéro de notice : A2020-349 Affiliation des auteurs : non IGN Thématique : BIODIVERSITE/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.05.017 date de publication en ligne : 05/06/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.05.017 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95231 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2020081	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2020083	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2020082	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Volcano-seismic transfer learning and uncertainty quantification with bayesian neural networks / Angel Bueno in IEEE Transactions on geoscience and remote sensing, vol 58 n° 2 (February 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 58 n° 2 (February 2020) . - pp Titre : Volcano-seismic transfer learning and uncertainty quantification with bayesian neural networks Type de document : Article/Communication Auteurs : Angel Bueno, Auteur ; Carmen Benitez, Auteur ; Silvio De Angelis, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Statistiques [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] classification bayesienne [Termes descripteurs IGN] classification par réseau neuronal [Termes descripteurs IGN] forme d'onde [Termes descripteurs IGN] incertitude des données [Termes descripteurs IGN] réseau bayesien [Termes descripteurs IGN] réseau de neurones profond [Termes descripteurs IGN] Russie [Termes descripteurs IGN] séisme [Termes descripteurs IGN] sismologie [Termes descripteurs IGN] surveillance géologique [Termes descripteurs IGN] volcanologie [Termes descripteurs IGN] Washington (Etats-Unis ; état) Résumé : (auteur) Over the past few years, deep learning (DL) has emerged as an important tool in the fields of volcano and earthquake seismology. However, these methods have been applied without performing thorough analyses of the associated uncertainties. Here, we propose a solution to enhance volcano-seismic monitoring systems, through probabilistic Bayesian DL; we implement and demonstrate a workflow for waveform classification, rapid quantification of the associated uncertainty, and link these uncertainties to changes in volcanic unrest. Specifically, we introduce Bayesian neural networks (BNNs) to perform event identification, classification, and their estimated uncertainty on data gathered at two active volcanoes, Mount St. Helens, Washington, USA, and Bezymianny, Kamchatka, Russia. We demonstrate how BNNs achieve excellent performance (92.08%) in discriminating both the type of event and its origin when the two data sets are merged together, and no additional training information is provided. Finally, we demonstrate that the data representations learned by the BNNs are transferable across different eruptive periods. We also find that the estimated uncertainty is related to changes in the state of unrest at the volcanoes and propose that it could be used to gauge whether the learned models may be exported to other eruptive scenarios. Numéro de notice : A2020-094 Affiliation des auteurs : non IGN Thématique : MATHEMATIQUE/POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2019.2941494 date de publication en ligne : 07/10/2019 En ligne : https://doi.org/10.1109/TGRS.2019.2941494 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94657 [article]

Semantic segmentation of road furniture in mobile laser scanning data / Fashuai Li in ISPRS Journal of photogrammetry and remote sensing, vol 154 (August 2019)  

Permalink

Simultaneous chain-forming and generalization of road networks / Susanne Wenzel in Photogrammetric Engineering & Remote Sensing, PERS, vol 85 n° 1 (January 2019)  

Permalink

A hybrid ensemble learning method for tourist route recommendations based on geo-tagged social networks / Lin Wan in International journal of geographical information science IJGIS, vol 32 n° 11-12 (November - December 2018)  

Permalink

Hierarchical cellular automata for visual saliency / Yao Qin in International journal of computer vision, vol 126 n° 7 (July 2018)  

Permalink

Combining land cover products using a minimum divergence and a Bayesian data fusion approach / Sarah Gengler in International journal of geographical information science IJGIS, vol 32 n° 3-4 (March - April 2018)  

Permalink

Nouvelle méthode en cascade pour la classification hiérarchique multi-temporelle ou multi-capteur d'images satellitaires haute résolution / Ihsen Hedhli in Revue Française de Photogrammétrie et de Télédétection, n° 216 (février 2018)

Permalink

Machine learning and pose estimation for autonomous robot grasping with collaborative robots / Victor Talbot (2018) 

Permalink

Fusing tree‐ring and forest inventory data to infer influences on tree growth / Margaret E.K. Evans in Ecosphere, vol 8 n° 7 (July 2017)  

Permalink

Amélioration de la vitesse et de la qualité d'image du rendu basé image / Rodrigo Ortiz Cayón (2017)  

Permalink

An Introduction to Machine Learning / Miroslav Kubat (2017)  

Permalink