[n° ou bulletin]
[n° ou bulletin]
|
Dépouillements
Ajouter le résultat dans votre panierTwo hidden layer neural network-based rotation forest ensemble for hyperspectral image classification / Laxmi Narayana Eeti in Geocarto international, vol 36 n° 16 ([01/09/2021])
[article]
Titre : Two hidden layer neural network-based rotation forest ensemble for hyperspectral image classification Type de document : Article/Communication Auteurs : Laxmi Narayana Eeti, Auteur ; Krishna Mohan Buddhiraju, Auteur Année de publication : 2021 Article en page(s) : pp 1820 - 1837 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] arbre de décision
[Termes IGN] classification par forêts d'arbres décisionnels
[Termes IGN] ensachage
[Termes IGN] image AVIRIS
[Termes IGN] image EO1-Hyperion
[Termes IGN] image hyperspectrale
[Termes IGN] image ROSIS
[Termes IGN] Perceptron multicouche
[Termes IGN] précision de la classification
[Termes IGN] réseau neuronal profond
[Termes IGN] Rotation Forest classificationRésumé : (auteur) Decision tree-based Rotation Forest could generate satisfactory but lower classification accuracy for a given training sample set and image data, owing to the inherent disadvantages in decision trees, namely myopic, replication and fragmentation problem. To improve performance of Rotation Forest technique, we propose to utilize two-hidden-layered-feedforward neural network as base classifier instead of decision tree. We examine the classification performance of proposed model under two situations, namely when free network parameters are maintained the same across all ensemble components and otherwise. The proposed model, where each component is initialized with different pair of initial weights and bias, performs better than decision tree-based Rotation Forest on three different Hyperspectral sensor datasets – AVIRIS, ROSIS and Hyperion. Improvements in classification accuracy are above 2% and up to 3% depending upon dataset. Also, the proposed model achieves improvement in accuracy over Random Forest in the range 4.2–8.8%. Numéro de notice : A2021-581 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2019.1678680 Date de publication en ligne : 21/10/2019 En ligne : https://doi.org/10.1080/10106049.2019.1678680 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98193
in Geocarto international > vol 36 n° 16 [01/09/2021] . - pp 1820 - 1837[article]Land degradation assessment in an African dryland context based on the Composite Land Degradation Index and mapping method / Felicia Akinyemi in Geocarto international, vol 36 n° 16 ([01/09/2021])
[article]
Titre : Land degradation assessment in an African dryland context based on the Composite Land Degradation Index and mapping method Type de document : Article/Communication Auteurs : Felicia Akinyemi, Auteur ; Laura T. Tlhalerwa, Auteur ; Peter N. Eze, Auteur Année de publication : 2021 Article en page(s) : pp 1838 - 1854 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Cartographie thématique
[Termes IGN] Botswana
[Termes IGN] carte de la végétation
[Termes IGN] dégradation de l'environnement
[Termes IGN] dégradation des sols
[Termes IGN] données de terrain
[Termes IGN] système d'information géographique
[Termes IGN] utilisation du sol
[Termes IGN] zone arideRésumé : (auteur) Increasing environmental and socioeconomic transformations in African drylands are driving land degradation. Using the Composite Land Degradation Index, this study assessed physical, chemical and biological degradation by determining their extent and severity. Palapye, an agro-pastoral region in eastern Botswana was used as a case study. Land degradation maps (status and indicators) were created with data from the field, soil chemical properties and image interpretation. Areas in the vicinity of settlements with Luvisols at elevations between 773 and 893 m were most degraded, implying impacts from human activities. This study developed a comprehensive list of of land degradation indicators for Botswana and created additional symbols for mapping indicators. Creation of these reference data for 2015 will facilitate the monitoring of land degradation in Palapye. The integrative and spatially explicit procedure utilized in this study can be adapted for assessing and validating local-level land degradation baseline and estimates towards operationalizing Land Degradation Neutrality in all countries. Numéro de notice : A2021-582 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2019.1678673 Date de publication en ligne : 25/10/2019 En ligne : https://doi.org/10.1080/10106049.2019.1678673 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98194
in Geocarto international > vol 36 n° 16 [01/09/2021] . - pp 1838 - 1854[article]