Centre dedocumentation
scientifique

Comparison between convolutional neural networks and random forest for local climate zone classification in mega urban areas using Landsat images / Cheolhee Yoo in ISPRS Journal of photogrammetry and remote sensing, vol 157 (November 2019)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 157 (November 2019) . - pp 155 - 170 Titre : Comparison between convolutional neural networks and random forest for local climate zone classification in mega urban areas using Landsat images Type de document : Article/Communication Auteurs : Cheolhee Yoo, Auteur ; Daehyeon Han, Auteur ; Jungho Im, Auteur ; Benjamin Bechtel, Auteur Année de publication : 2019 Article en page(s) : pp 155 - 170 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] analyse comparative [Termes descripteurs IGN] apprentissage automatique [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] Chicago (Illinois) [Termes descripteurs IGN] classification par forêts aléatoires [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] climat urbain [Termes descripteurs IGN] Hong-Kong [Termes descripteurs IGN] ilot thermique urbain [Termes descripteurs IGN] image Landsat-8 [Termes descripteurs IGN] Madrid (Espagne) [Termes descripteurs IGN] Rome [Termes descripteurs IGN] World Urban Database and Access Portal Tools [Termes descripteurs IGN] zone urbaine dense Résumé : (Auteur) The Local Climate Zone (LCZ) scheme is a classification system providing a standardization framework to present the characteristics of urban forms and functions, especially for urban heat island (UHI) research. Landsat-based 100 m resolution LCZ maps have been classified by the World Urban Database and Portal Tool (WUDAPT) method using a random forest (RF) machine learning classifier. Some studies have proposed modified RF and convolutional neural network (CNN) approaches. This study aims to compare CNN with an RF classifier for LCZ mapping in great detail. We designed five schemes (three RF-based schemes (S1–S3) and two CNN-based ones (S4–S5)), which consist of various combinations of input features from bitemporal Landsat 8 data over four global mega cities: Rome, Hong Kong, Madrid, and Chicago. Among the five schemes, the CNN-based one with the incorporation of a larger neighborhood information showed the best classification performance. When compared to the WUDAPT workflow, the overall accuracies for entire land cover classes (OA) and for urban LCZ types (i.e., LCZ1-10; OAurb) increased by about 6–8% and 10–13%, respectively, for the four cities. The transferability of LCZ models for the four cities were evaluated, showing that CNN consistently resulted in higher accuracy (increased by about 7–18% and 18–29% for OA and OAurb, respectively) than RF. This study revealed that the CNN classifier classified particularly well for the specific LCZ classes in which buildings were mixed with trees or buildings or plants were sparsely distributed. The research findings can provide a basis for guidance of future LCZ classification using deep learning. Numéro de notice : A2019-495 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.09.009 date de publication en ligne : 19/09/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.09.009 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93728 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2019111	RAB	Revue	Centre de documentation	En réserve 3L	Disponible
081-2019113	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2019112	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Crowdsourcing functions of the living city from Twitter and Foursquare data / Xiaolu Zhou in Cartography and Geographic Information Science, vol 43 n° 5 (November 2016)  

Public [article]  inCartography and Geographic Information Science > vol 43 n° 5 (November 2016) . - pp 393 - 404 Titre : Crowdsourcing functions of the living city from Twitter and Foursquare data Type de document : Article/Communication Auteurs : Xiaolu Zhou, Auteur ; Liang Zhang, Auteur Année de publication : 2016 Article en page(s) : pp 393 - 404 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes descripteurs IGN] analyse spatio-temporelle [Termes descripteurs IGN] Boston (Massachusetts) [Termes descripteurs IGN] Chicago (Illinois) [Termes descripteurs IGN] dimension temporelle [Termes descripteurs IGN] données issues des réseaux sociaux [Termes descripteurs IGN] données localisées des bénévoles [Termes descripteurs IGN] géoétiquetage [Termes descripteurs IGN] planification urbaine [Termes descripteurs IGN] réseau social [Termes descripteurs IGN] système d'information géographique [Termes descripteurs IGN] ville Résumé : (Auteur) Urban functions are closely related to people’s spatiotemporal activity patterns, transportation needs, and a city’s business distribution and development trends. Studies investigating urban functions have used different data sources, such as remotely sensed imageries, observation, photography, and cognitive maps. However, these data sources usually suffer from low spatial, temporal, and thematic resolution. This article attempts to investigate human activities to understand urban functions through crowdsourcing social media data. In this study, we mined Twitter and Foursquare data to extract and analyze six types of human activities. The spatiotemporal analysis revealed hotspots for different activity intensities at different temporal resolution. We also applied the classified model in a real-time system to extract information of various urban functions. This study demonstrates the significance and usefulness of social sensing in analyzing urban functions. By combining different platforms of social media data and analyzing people’s geo-tagged city experience, this article contributes to leverage voluntary local knowledge to better depict human dynamics, discover spatiotemporal city characteristics, and convey information about cities. Numéro de notice : A2016-690 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/URBANISME Nature : Article DOI : 10.1080/15230406.2015.1128852 En ligne : https://doi.org/10.1080/15230406.2015.1128852 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82018 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
032-2016051	SL	Revue	Centre de documentation	Revues en salle	Disponible

Privacy and spatial pattern preservation in masked GPS trajectory data / Dara E. Seidl in International journal of geographical information science IJGIS, vol 30 n° 3-4 (March - April 2016)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 30 n° 3-4 (March - April 2016) . - pp 785 - 800 Titre : Privacy and spatial pattern preservation in masked GPS trajectory data Type de document : Article/Communication Auteurs : Dara E. Seidl, Auteur ; Piotr Jankowski, Auteur ; Ming-Hsiang Tsou, Auteur Année de publication : 2016 Article en page(s) : pp 785 - 800 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes descripteurs IGN] Atlanta (Géorgie) [Termes descripteurs IGN] Chicago (Illinois) [Termes descripteurs IGN] itinéraire [Termes descripteurs IGN] protection de la vie privée [Termes descripteurs IGN] régression linéaire [Termes descripteurs IGN] seuillage [Termes descripteurs IGN] traitement de données localisées [Termes descripteurs IGN] trajectographie par GNSS Résumé : (Auteur) Personal trajectory data are increasingly collected for a variety of academic and recreational pursuits. As access to location data widens and locations are linked to other information repositories, individuals become increasingly vulnerable to identification. The quality and precision of spatially linked attributes are essential to accurate analysis; yet, there is a trade-off between privacy and geographic data resolution. Obfuscation of point data, or masking, is a solution that aims to protect privacy and maximize preservation of spatial pattern. Trajectory data, with multiple locations recorded for an entity over time, is a strong personal identifier. This study explores the balance between privacy and spatial pattern resulting from two methods of obfuscation for personal GPS data: grid masking and random perturbation. These methods are applied to travel survey GPS data in the greater metropolitan regions of Chicago and Atlanta. The rate of pattern correlation between the original and masked data sets declines as the distance thresholds for masking increase. Grid masking at the 250-m threshold preserves route anonymity better than other methods and distance thresholds tested, but preserves spatial pattern least. This study also finds via linear regression that median trip speed and road density are significant predictors of trip anonymity. Numéro de notice : A2016-097 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2015.1101767 En ligne : https://doi.org/10.1080/13658816.2015.1101767 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=79894 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
079-2016021	RAB	Revue	Centre de documentation	En réserve 3L	Disponible

Modeling commute patterns in Chicago in a GIS environment: a job-accessibility perspective / F. Wang in The professional geographer, vol 52 n° 1 (February 2000)

Public [article]  inThe professional geographer > vol 52 n° 1 (February 2000) . - pp 120 - 133 Titre : Modeling commute patterns in Chicago in a GIS environment: a job-accessibility perspective Type de document : Article/Communication Auteurs : F. Wang, Auteur Année de publication : 2000 Article en page(s) : pp 120 - 133 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Systèmes d'information géographique [Termes descripteurs IGN] accessibilité [Termes descripteurs IGN] Chicago (Illinois) [Termes descripteurs IGN] système d'information géographique [Termes descripteurs IGN] transport [Termes descripteurs IGN] travail Résumé : (Auteur) Using the newly released Census for Transportation Planning Package (CTPP) 1990, this research utilizes GIS tools to explain intraurban variations of commuting in Chicago at the Traffic Analysis Zone (TAZ) level. While commute times are directly available from the CTPP, commute distances are derived from the shortest time distances through real-world road networks. GIS surface modeling is used to help identify the major employment center (CBD) and other subcenters. The explanations of commute times and distances are attempted by various measures of job accessibility : the jobs-housing balance ratio defined in a floating catchment area, distances from the CBD and subcenters, and a gravity-based index that takes the effects of all jobs into account. These measurements better explain how far people commute than how much time they spend on commuting. The best model explains over 50% of the variation of commuting among 7,835 TAZs. This is a significant improvement over existing literature, which at best explained less than 30 percent. Copyright Association of American Geographers Numéro de notice : A2000-169 Thématique : GEOMATIQUE/INFORMATIQUE Nature : Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=21585 [article]

Thematic Mapper thermal infrared data in discriminating selected urban features / S.M. Leak in International Journal of Remote Sensing IJRS, vol 11 n° 5 (May 1990)

Public [article]  inInternational Journal of Remote Sensing IJRS > vol 11 n° 5 (May 1990) . - pp 841 - 857 Titre : Thematic Mapper thermal infrared data in discriminating selected urban features Type de document : Article/Communication Auteurs : S.M. Leak, Auteur ; G. Venugopal, Auteur Année de publication : 1990 Article en page(s) : pp 841 - 857 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes descripteurs IGN] analyse discriminante [Termes descripteurs IGN] Chicago (Illinois) [Termes descripteurs IGN] image thermique [Termes descripteurs IGN] image TM (aérienne) [Termes descripteurs IGN] milieu urbain [Termes descripteurs IGN] occupation du sol [Termes descripteurs IGN] précision de la classification [Termes descripteurs IGN] rayonnement infrarouge thermique Résumé : (Auteur) This research was conducted to assess the utility of Landsat Thematic Mapper thermal data (10-4 to 12-5um) for urban feature analysis. Seven band thematic mapper data collected on 25 October, 1982 for the Chicago metropolitan area were used to determine the relative importance of the thermal band as a component of an urban land use classification. Analysis consisted of: (1) the use of a transformed divergence measure (separability) to test the interclass spectral variability of selected features for different channel combinations and (2) a comparison of classification results, with and without thermal data using a supervised layered classification algorithm. The use of thermal data resulted in an overall 9-3 per cent increase in classification accuracy. Elimination of classes such as forest, asphalt and railroad resulted in an increase of 12-0 per cent in classification performance. Examination of the separability analysis and classification results indicated there were specific areas of success resulting from the use of thermal data. Increased classification accuracy occurred in several classes such as shadow (+ 36-7 per cent), residential (+ 41-1 per cent), active industry (+ 20-0 per cent) and commercial industrial fringe (+ 77-1 per cent). These results demonstrated that the information content of thermal data was valuable for urban area analysis. Numéro de notice : A1990-091 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=25508 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
080-90051	RAB	Revue	Centre de documentation	En réserve 3L	Disponible