Centre de documentation
scientifique

Dépouillements

An effective ensemble classification framework using random forests and a correlation based feature selection technique / Dibyajyoti Chutia in Transactions in GIS, vol 21 n° 6 (December 2017)  

Public [article]  inTransactions in GIS > vol 21 n° 6 (December 2017) . - pp 1165 - 1178 Titre : An effective ensemble classification framework using random forests and a correlation based feature selection technique Type de document : Article/Communication Auteurs : Dibyajyoti Chutia, Auteur ; Dhruba Kumar Bhattacharyya, Auteur ; Jaganath Sarma, Auteur ; Penumetcha Narasa Lakshmi Raju, Auteur Année de publication : 2017 Article en page(s) : pp 1165 - 1178 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse comparative [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] corrélation à l'aide de traits caractéristiques [Termes IGN] image Landsat-ETM+ [Termes IGN] image Quickbird Résumé : (auteur) Accurate classification of heterogeneous land surfaces with homogeneous land cover classes is a challenging task as satellite images are characterized by a large number of features in the spectral and spatial domains. The identifying relevance of a feature or feature set is an important task for designing an effective classification scheme. Here, an ensemble of random forests (RF) classifiers is realized on the basis of relevance of features. Correlation‐based Feature Selection (CFS) was utilized to assess the relevance of a subset of features by studying the individual predictive ability of each feature along with the degree of redundancy between them. Predictability of RF was greatly improved by random selection of the relevant features in each of the splits. An investigation was carried out on different types of images from the Landsat Enhanced Thematic Mapper Plus (Landsat ETM+) and QuickBird sensors. It has been observed that the performance of the RF classifier was significantly improved while using the optimal set of relevant features compared with a few of the most advanced supervised classifiers such as maximum likelihood classifier (MLC), Navie Bayes, multi‐layer perception (MLP), support vector machine (SVM) and bagging. Numéro de notice : A2017-836 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12268 Date de publication en ligne : 27/04/2017 En ligne : https://doi.org/10.1111/tgis.12268 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89362 [article]

An efficient data organization and scheduling strategy for accelerating large vector data rendering / Mingqiang Guo in Transactions in GIS, vol 21 n° 6 (December 2017)  

Public [article]  inTransactions in GIS > vol 21 n° 6 (December 2017) . - pp 1217 - 1236 Titre : An efficient data organization and scheduling strategy for accelerating large vector data rendering Type de document : Article/Communication Auteurs : Mingqiang Guo, Auteur ; Ying Huang, Auteur ; et al., Auteur Année de publication : 2017 Article en page(s) : pp 1217 - 1236 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] données vectorielles [Termes IGN] processeur graphique [Termes IGN] processeur multicoeur [Termes IGN] rendu (géovisualisation) [Termes IGN] traitement parallèle [Vedettes matières IGN] Géovisualisation Résumé : (auteur) Rendering large volumes of vector data is computationally intensive and therefore time consuming, leading to lower efficiency and poorer interactive experience. Graphics processing units (GPUs) are powerful tools in data parallel processing but lie idle most of the time. In this study, we propose an approach to improve the performance of vector data rendering by using the parallel computing capability of many‐core GPUs. Vertex transformation, largely a mathematical calculation that does not require communication with the host storage device, is a time‐consuming procedure because all coordinates of each vector feature need to be transformed to screen vertices. Use of a GPU enables optimization of a general‐purpose mathematical calculation, enabling the procedure to be executed in parallel on a many‐core GPU and optimized effectively. This study mainly focuses on: (1) an organization and storage strategy for vector data based on equal pitch alignment, which can adapt to the GPU's calculating characteristics; (2) a paging‐coalescing transfer and memory access strategy for vector data between the CPU and the GPU; and (3) a balancing allocation strategy to take full advantage of all processing cores of the GPU. Experimental results demonstrate that the approach proposed can significantly improve the efficiency of vector data rendering. Numéro de notice : A2017-837 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12275 Date de publication en ligne : 23/05/2017 En ligne : https://doi.org/10.1111/tgis.12275 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89373 [article]

Extracting spatial patterns in bicycle routes from crowdsourced data / Jody Sultan in Transactions in GIS, vol 21 n° 6 (December 2017)  

Public [article]  inTransactions in GIS > vol 21 n° 6 (December 2017) . - pp 1321 - 1340 Titre : Extracting spatial patterns in bicycle routes from crowdsourced data Type de document : Article/Communication Auteurs : Jody Sultan, Auteur ; Gev Ben‐Haim, Auteur ; Jan‐Henrik Haunert, Auteur ; Sagi Dalyot, Auteur Année de publication : 2017 Article en page(s) : pp 1321 - 1340 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes IGN] Amsterdam (Pays-Bas) [Termes IGN] cycliste [Termes IGN] données localisées des bénévoles [Termes IGN] extraction de modèle [Termes IGN] trace GPS [Termes IGN] trajet (mobilité) Résumé : (auteur) Much is done nowadays to provide cyclists with safe and sustainable road infrastructure. Its development requires the investigation of road usage and interactions between traffic commuters. This article is focused on exploiting crowdsourced user‐generated data, namely GPS trajectories collected by cyclists and road network infrastructure generated by citizens, to extract and analyze spatial patterns and road‐type use of cyclists in urban environments. Since user‐generated data shows data‐deficiencies, we introduce tailored spatial data‐handling processes for which several algorithms are developed and implemented. These include data filtering and segmentation, map‐matching and spatial arrangement of GPS trajectories with the road network. A spatial analysis and a characterization of road‐type use are then carried out to investigate and identify specific spatial patterns of cycle routes. The proposed analysis was applied to the cities of Amsterdam (The Netherlands) and Osnabrück (Germany), proving its feasibility and reliability in mining road‐type use and extracting pattern information and preferences. This information can help users who wish to explore friendlier and more interesting cycle patterns, based on collective usage, as well as city planners and transportation experts wishing to pinpoint areas most in need of further development and planning. Numéro de notice : A2017-838 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12280 Date de publication en ligne : 06/06/2017 En ligne : https://doi.org/10.1111/tgis.12280 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89374 [article]

An analysis of movement patterns between zones using taxi GPS data / Zhanlong Chen in Transactions in GIS, vol 21 n° 6 (December 2017)  

Public [article]  inTransactions in GIS > vol 21 n° 6 (December 2017) . - pp 1341 - 1363 Titre : An analysis of movement patterns between zones using taxi GPS data Type de document : Article/Communication Auteurs : Zhanlong Chen, Auteur ; Xi Gong, Auteur ; Zhong Xie, Auteur Année de publication : 2017 Article en page(s) : pp 1341 - 1363 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] modèle numérique [Termes IGN] Pékin (Chine) [Termes IGN] trace GPS [Termes IGN] trajectographie par GPS [Termes IGN] trajet (mobilité) [Termes IGN] urbanisme [Termes IGN] véhicule automobile [Vedettes matières IGN] Géovisualisation Résumé : (auteur) The discovery of zones and people's movement patterns supports a better understanding of modern cities and enables a more comprehensive strategy for urban planning. This article proposes a modified method based on previous research to simultaneously discover people's zones and movement patterns, called movement patterns between functional zones (MPFZ). The method attempts to take full advantage of taxi GPS data to identify MPFZs by merging the movement traces satisfying the merging conditions. Considering movement directions, movement numbers and the adjacent constraints that consist of spatial relationship and attribute features, the merging conditions limit the movement traces to be merged. The new MPFZs are discovered by an iteration process and are measured by the following three evaluation indices: v‐value, a‐value and c‐value, which represent coverage, accuracy and their trade‐off. Using a real‐world taxi dataset of Beijing, 24 new MPFZs are discovered, which have higher v‐, a‐ and c‐values than the unmerged MPFZs. The results of the real‐world dataset experiment show that the proposed approach is effective and efficient. The proposed method can also be applied to other types of transportation data and regions by adjusting the dataset utilized and controlling the iteration process. Numéro de notice : A2017-839 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12281 Date de publication en ligne : 07/08/2017 En ligne : https://doi.org/10.1111/tgis.12281 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89375 [article]